OpenHands
v1.16.0 open-sourceOpenHands: AI-Driven Development
sudo apt install ./Agent-Canvas-<version>.deb chmod +x Agent-Canvas-<version>.AppImage && ./Agent-Canvas-<version>.AppImage OH_RESOLVER_LABEL=my-team-resolver OH_DEPLOYMENT_MODE=enterprise_cloud OH_RESOLVER_LABEL=my-org-resolver /settings CLI_VI_MODE=true python -m openhands.core.cli /new /status /settings LOG_JSON=true docker run --rm -e LOG_JSON=true ghcr.io/all-hands-ai/openhands:0.28.0 [extended] my_custom_flag = "value" another_setting = 42
Summary
OpenHands is an open-source AI coding agent framework, released under the MIT license (with a source-available enterprise directory that requires a paid license after a month of use), that runs coding agents against real repositories and tasks. You can run it several ways: a single command starts its Agent Canvas web UI and backend locally, a Python SDK lets you define and run agents yourself or scale them to many instances in the cloud, and a hosted OpenHands Cloud or self-hosted Enterprise option adds GitHub, GitLab, Slack, and Jira integrations with multi-user permissions. It targets software engineering teams looking to automate everyday development work, from decomposing GitHub issues into tasks to running sub-agent delegation across specialized child agents. First committed in 2024, it now has 592 contributors and a release this week, suggesting active, well-supported development.
OpenHands: AI-Driven Development
What OpenHands answers
Which coding agents can I run through this besides OpenHands' own?
any ACP-compatible agent, including Claude Code, Codex, and Gemini, across local, remote, and cloud backends
Can I run agents in isolated environments with different resource needs?
sandbox environments support user-selectable grouping and can pin a preferred sandbox per session, including KVM passthrough for accelerated virtual machines instead of emulation
What happens when one agent task is too broad for a single agent?
the primary agent can delegate subtasks to specialized child agents, visualized in the chat UI as they run
Which trackers and chat tools does it actually hook into for triggering work?
GitHub, GitLab, Bitbucket, Jira, Linear, Slack, and Azure DevOps, with one-click webhook setup for Azure DevOps and email-based auto-linking for Jira Data Center
Can multiple teams or clients share one deployment without seeing each other's work?
organizations, invite links, and an org-only workspace flag separate users, though a single-org install routes unclaimed automation events to one default org
Do I have to babysit a running agent, or can I redirect it mid-task?
a dedicated interrupt endpoint lets you pause an agent reliably instead of waiting for it to finish or killing the process
Examples
Command line
No option matches that search.
| option | found in | since | description |
|---|
No option matches that search.
Values are placeholders taken from each option’s declared default. Nothing is executed here — the output shown is a recording of a run that already happened.
Release history
- docs update
OpenHands automation runs now expose a live phase field and support Git sync for automations.

- ›Automation runs now surface a live
phasefield reflecting the run's current state, visible on automation cards, in the Activity Log, and on the home screen, updating in real time as a run progresses (a failed run retains its last phase). - ›Adds Git sync support for automations.
- ›Exports now include the run's
phasefield alongside cost, with unavailable costs exported as a defined placeholder value.
- ›Automation runs now surface a live
- docs update
OpenHands adds a Getting Started checklist and a searchable LLM provider selector to the setup wizard.



└──▷ HOW TO FIND ITRestore the Getting Started checklist after dismissing it, so new team members can follow the onboarding flow.📍In the console, go to Settings › Application and enable the 'Show getting started checklist' switch.- ›Adds a 'Getting Started' checklist in the sidebar after setup wizard completion, tracking first-use actions (set up LLM, connect MCP servers, start a conversation, explore automations, customize agent, review settings), with auto-hide when all items are complete.
- ›Adds Show getting started checklist toggle in
Settings > Applicationto show or hide the checklist; setting persists across sessions. - ›Changes the OpenHands provider connection field from free text to a searchable supported-provider selector when adding an LLM provider.
- ›Sets OpenAI GPT-5.6 Sol as the default model and DeepSeek V4 Flash as the free OpenHands-routed model.
- docs update
OpenHands Agent Canvas ships early-preview desktop apps for macOS, Windows, and Linux (AppImage and .deb formats).
└──▷ TRY ITInstall the Agent Canvas desktop app on a Debian/Ubuntu system to run OpenHands locally without a browser.$ sudo apt install ./Agent-Canvas-<version>.debRun the Agent Canvas AppImage on a Linux system that does not use apt, without installation.$ chmod +x Agent-Canvas-<version>.AppImage && ./Agent-Canvas-<version>.AppImage- ›Adds native desktop app distribution for Agent Canvas on Linux as
Agent-Canvas-<version>.AppImage(run after marking executable) andAgent-Canvas-<version>.deb(install viasudo apt install ./Agent-Canvas-<version>.deb), with macOS and Windows builds also available as early preview.
- ›Adds native desktop app distribution for Agent Canvas on Linux as
- docs update
OpenHands prebuilt automations now support script bundles and multi-repo monitoring in a single automation.
└──▷ HOW TO FIND ITWhen setting up a catalog automation that monitors multiple repos, enter all target repositories in the single repository field so one automation covers your entire org.📍In the Agent Canvas, open Prebuilt Automations › select a catalog entry that accepts repositories › fill in the repository field with multiple repositories › complete the remaining required fields and install.- ›Adds script bundle support to catalog entries — a packaged set of files that installs as a deterministic automation, running its own logic for polling, deduplication, and fixed API calls, with the agent invoked only for judgment-required steps.
- ›Catalog entries that accept repositories can now collect multiple repositories in a single field, letting one automation monitor several repos at once.
- docs update
OpenHands Agent Canvas gains Git Sync: bidirectional automation versioning via a private Git repo with optional file encryption.
└──▷ HOW TO FIND ITSet up automatic Git Sync every 5 minutes to a private GitHub repo so automation changes are versioned and backed off-host continuously.📍In Agent Canvas, open the Automate view › select Git Sync › set Repository URL to 'https://github.com/example/automation-backup.git', Branch to 'main', Path to 'automations', Sync every (seconds) to '300', enter your HTTPS access token, then turn on Enable Git Sync and select Save and sync now.Review an automation change safely before it is applied by merging a PR into the synchronized branch and then triggering an immediate import.📍In Agent Canvas, open the Automate view › select Git Sync › select Sync now after merging your pull request into 'main', then open the affected automation and confirm the imported configuration before running it.Enable file-level encryption so sensitive prompts and scripts are stored as ciphertext in Git rather than readable YAML.📍In Agent Canvas, open the Automate view › select Git Sync › enter a strong value in the encryption key field › turn on Enable Git Sync › select Save and sync now. Store the key in a password manager — without it, encrypted files cannot be decrypted.- ›Adds Repository URL, Branch, Path, Access token, Sync every (seconds), commit author name/email, and encryption key fields to the Git Sync configuration panel in the Automate view.
- ›Adds Enable Git Sync toggle and Save and sync now action to activate bidirectional sync between an Agent Canvas Automation Server and a configured Git repository branch.
- ›Stores each automation under its own directory (e.g.
automations/daily-code-review/) with anautomation.yamlfile and atarball/subdirectory so Git shows meaningful diffs for uploaded bundles. - ›Adds a Sync now button to trigger an immediate sync cycle without waiting for the automatic interval; concurrent cycles are deduplicated.
- ›Adds optional file-level encryption: when an encryption key is set, automation files are committed as ciphertext rather than readable YAML, protecting sensitive prompts and scripts at rest in Git.
+3 moreshow less
- ›Adds a Sync Status section that displays the latest commit, last sync time, pending local changes, and any Git error after each cycle.
- ›Supports a pull-request-based review workflow: changes merged into the synchronized branch are imported on the next cycle, while pending local changes take precedence over incoming Git changes for that cycle.
- ›Git Sync is available only for local (non-cloud) Agent Canvas backends; cloud backends are explicitly unsupported.
- docs update
OpenHands adds a Getting Started checklist with progress tracking and a persistent visibility toggle in Settings.



└──▷ HOW TO FIND ITRestore the Getting Started checklist after it has been dismissed or auto-hidden.📍In the OpenHands UI, go to Settings › Application and enable the 'Show getting started checklist' switch.- ›Adds a 'Getting Started' checklist in the sidebar after setup wizard completion, guiding users through LLM setup, MCP server connection, starting a conversation, exploring automations, and customizing the agent — each item linking directly to its relevant page.
- ›Checklist tracks completion progress, auto-hides when all items are done, and can be toggled via Show getting started checklist switch under
Settings > Application, with the preference persisting across sessions.
- v1.16.0
OpenHands v1.16.0 adds Canvas Extensions, a Linux desktop installer, LLM-provider selection, a skills allow-list, and live automation phase visibility.
└──▷ GET THIS VERSION$ git clone --branch v1.16.0 https://github.com/OpenHands/OpenHands.git # already have the repo? check out this version: $ git checkout v1.16.0
- ›Adds Canvas Extensions frontend: load pages, configure the sidebar, and customize the canvas surface.
- ›Adds a Linux desktop installer build (
.debpackage) via updated CI and maintainer scripts. - ›Adds an LLM-switching toggle in Agent settings, letting users change the active model without leaving the agent configuration screen.
- ›Adds LLM provider selection in Settings, restricting the UI to only supported providers.
- ›Replaces the all-on skill catalog with an explicit allow-list, giving operators fine-grained control over which skills the agent can use.
+4 moreshow less
- ›Adds live phase display for automation runs, showing the current execution phase in the sidebar in real time.
- ›Enables pinning a favorite sidebar page as the default home route.
- ›Links file paths mentioned in chat to the Files drawer, making referenced paths directly navigable.
- ›Skips onboarding when a user-added Local backend already has a usable LLM configured.
- v1.15.0
OpenHands v1.15.0 adds a getting-started checklist, LLM provider-connections UI, automations catalog installer, and a conversation overview panel.
└──▷ GET THIS VERSION$ git clone --branch v1.15.0 https://github.com/OpenHands/OpenHands.git # already have the repo? check out this version: $ git checkout v1.15.0
- ›Adds an LLM provider-connections UI for the local agent-server, letting practitioners configure provider connections directly from the interface.
- ›Adds a getting-started checklist in the sidebar with a settings toggle to guide new users through initial setup.
- ›Adds the ability to install an automations catalog entry that ships a script bundle, expanding the automations workflow.
- ›Adds a conversation overview panel and unified commits drawer to the conversation view.
- ›Shows the workspace path in the Files view for easier orientation within multi-folder workspaces.
+1 moreshow less
- ›Batches
StreamingDeltaEventsso the UI keeps pace with fast models, enabling reliable real-time streaming at higher throughput.
- 0.53.0
OpenHands now publishes an API — 43 endpoints across 3 areas: Api, Alive, Health
- ›Api (41 endpoints) — create, read, update, delete
- ›Alive (1 endpoint) — read
- ›Health (1 endpoint) — read
- v1.14.0
OpenHands v1.14.0 adds Git Sync automation, LLM pre-flight validation, structured Canvas error outcomes, and sets Kimi K3 as the free default Canvas model.
└──▷ GET THIS VERSION$ git clone --branch v1.14.0 https://github.com/All-Hands-AI/OpenHands.git # already have the repo? check out this version: $ git checkout v1.14.0
- ›Adds a Git Sync page under Automations for managing repository synchronization workflows.
- ›Adds LLM pre-flight validation when saving LLM profiles, blocking misconfigured settings before they are persisted.
- ›Canvas now presents structured error outcomes, surfacing failure details in a readable format rather than raw output.
- ›Sets Kimi K3 as the default Canvas model and tags it as free.
- v1.14.0
OpenHands v1.14.0 adds Git Sync automation, LLM pre-flight validation, structured Canvas error outcomes, and sets Kimi K3 as the free default Canvas model.
└──▷ GET THIS VERSION$ git clone --branch v1.14.0 https://github.com/OpenHands/OpenHands.git # already have the repo? check out this version: $ git checkout v1.14.0
- ›Adds a Git Sync page under Automations for managing repository synchronization workflows.
- ›Adds LLM pre-flight validation when saving LLM profiles, blocking misconfigured settings before they take effect.
- ›Canvas now surfaces structured error outcomes, giving clearer feedback when agent tasks fail.
- ›Sets Kimi K3 as the default Canvas model and tags it as free.
- v1.14.0
OpenHands v1.14.0 adds Git Sync automation, LLM pre-flight validation, structured Canvas error outcomes, and sets Kimi K3 as the free default Canvas model.
└──▷ GET THIS VERSION$ git clone --branch v1.14.0 https://github.com/OpenHands/OpenHands.git # already have the repo? check out this version: $ git checkout v1.14.0
- ›Adds a Git Sync page under Automations for managing repository synchronization workflows.
- ›Adds LLM pre-flight validation when saving LLM profiles, blocking misconfigured settings before they take effect.
- ›Canvas now surfaces structured error outcomes, giving clearer feedback when agent tasks fail.
- ›Sets Kimi K3 as the default Canvas model and tags it as free.
- v1.13.0
OpenHands v1.13.0 adds conversation archiving, inline markdown previews, a context-window meter with manual compaction, and an issue readiness gate.
└──▷ GET THIS VERSION$ git clone --branch v1.13.0 https://github.com/All-Hands-AI/OpenHands.git # already have the repo? check out this version: $ git checkout v1.13.0
- ›Adds client-side conversation archive so users can archive and manage past conversations directly in the UI.
- ›Adds inline markdown artifact previews inside the chat panel, rendering markdown output without leaving the conversation.
- ›Adds a context window usage meter, usage drawer, and manual compaction control so practitioners can monitor and manage LLM context consumption.
- ›Adds a ready-for-dev issue readiness gate with type-specific criteria to gate issues before they are handed to the agent.
- v1.13.0
OpenHands v1.13.0 adds conversation archiving, inline markdown previews, a context window usage meter, and an issue readiness gate.
└──▷ GET THIS VERSION$ git clone --branch v1.13.0 https://github.com/OpenHands/OpenHands.git # already have the repo? check out this version: $ git checkout v1.13.0
- ›Adds a context window usage meter, usage drawer, and manual compaction so practitioners can monitor and control context consumption in real time.
- ›Adds client-side conversation archive to organize and declutter past agent sessions.
- ›Adds inline markdown artifact previews directly in the chat interface.
- ›Adds a ready-for-dev issue readiness gate with type-specific criteria to validate issues before the agent picks them up.
- v1.13.0
OpenHands v1.13.0 adds conversation archiving, inline markdown previews, a context window usage meter, and an issue readiness gate.
└──▷ GET THIS VERSION$ git clone --branch v1.13.0 https://github.com/OpenHands/OpenHands.git # already have the repo? check out this version: $ git checkout v1.13.0
- ›Adds a context window usage meter, usage drawer, and manual compaction so practitioners can monitor and control context consumption in real time.
- ›Adds client-side conversation archive to organize and declutter past agent sessions.
- ›Adds inline markdown artifact previews directly in the chat interface.
- ›Adds a ready-for-dev issue readiness gate with type-specific criteria to validate issues before the agent picks them up.
- v1.11.0
OpenHands v1.11.0 adds per-run LLM cost visibility, tag filtering for automations, and typed child-conversation actions.
└──▷ GET THIS VERSION$ git clone --branch v1.11.0 https://github.com/All-Hands-AI/OpenHands.git # already have the repo? check out this version: $ git checkout v1.11.0
- ›Adds per-run LLM cost display in the Activity Log and exports, giving operators visibility into token spend for each individual run.
- ›Adds automation tag filter and recognition, enabling users to filter automations by tag in the UI.
- ›Adds tag chips, overflow handling, and hovercard labels to the conversations view for at-a-glance context.
- ›Adds a typed agent action for launching local or Cloud child conversations, expanding programmatic multi-conversation workflows.
- ›Reorders the Customize navigation section for improved discoverability.
+1 moreshow less
- ›Keeps the Automations pane visible on the home screen even when empty, reducing confusion for new automation setups.
- v1.11.0
OpenHands v1.11.0 adds per-run LLM cost tracking, tag filtering for automations, and typed child-conversation agent actions.
└──▷ GET THIS VERSION$ git clone --branch v1.11.0 https://github.com/OpenHands/OpenHands.git # already have the repo? check out this version: $ git checkout v1.11.0
- ›Adds per-run LLM cost display in the Activity Log and exports, giving teams visibility into spend at the individual run level.
- ›Adds a typed agent action for launching local or Cloud child conversations, enabling agents to programmatically spawn sub-conversations.
- ›Adds automation tag filter and recognition, letting users filter the Automations pane by tag.
- ›Adds tag chips, overflow handling, and hovercard labels to the conversations view for richer conversation metadata display.
- ›Keeps the Automations pane visible when empty so the panel is always accessible.
+2 moreshow less
- ›Reorders the Customize navigation section for improved discoverability.
- ›Polishes the Agent Canvas version update UI in Settings.
- v1.11.0
OpenHands v1.11.0 adds per-run LLM cost tracking, tag filtering for automations, and typed child-conversation agent actions.
└──▷ GET THIS VERSION$ git clone --branch v1.11.0 https://github.com/OpenHands/OpenHands.git # already have the repo? check out this version: $ git checkout v1.11.0
- ›Adds per-run LLM cost display in the Activity Log and exports, giving teams visibility into spend at the individual run level.
- ›Adds a typed agent action for launching local or Cloud child conversations, enabling agents to programmatically spawn sub-conversations.
- ›Adds automation tag filter and recognition, letting users filter the Automations pane by tag.
- ›Adds tag chips, overflow handling, and hovercard labels to the conversations view for richer conversation metadata display.
- ›Keeps the Automations pane visible when empty so the panel is always accessible.
+2 moreshow less
- ›Reorders the Customize navigation section for improved discoverability.
- ›Polishes the Agent Canvas version update UI in Settings.
- v1.10.0
OpenHands v1.10.0 adds activity log export, a featured automations dashboard, manifest-driven automation sub-pages, and faceted skills filtering.
└──▷ GET THIS VERSION$ git clone --branch v1.10.0 https://github.com/All-Hands-AI/OpenHands.git # already have the repo? check out this version: $ git checkout v1.10.0
- ›Adds activity log export capability to the interface.
- ›Ships a featured automations landing dashboard for discovering and launching automations.
- ›Adds manifest-driven sub-pages to the automation interface, enabling structured multi-page automation flows.
- ›Adds a faceted rail filter to the Skills page for narrowing down skills by category.
- ›Sets the Canvas default model to GLM 5.2.
- v1.10.0
OpenHands v1.10.0 adds activity log export, a featured automations dashboard, manifest-driven automation sub-pages, and faceted skills filtering.
└──▷ GET THIS VERSION$ git clone --branch v1.10.0 https://github.com/OpenHands/OpenHands.git # already have the repo? check out this version: $ git checkout v1.10.0
- ›Adds activity log export capability to the interface.
- ›Ships a featured automations landing dashboard for discovering and launching automations.
- ›Adds manifest-driven sub-pages to the automation interface, enabling structured automation workflows.
- ›Adds a faceted filter rail to the Skills page for narrowing skills by category.
- ›Sets the Canvas default model to GLM 5.2.
- v1.10.0
OpenHands v1.10.0 adds activity log export, a featured automations dashboard, manifest-driven automation sub-pages, and faceted skills filtering.
└──▷ GET THIS VERSION$ git clone --branch v1.10.0 https://github.com/OpenHands/OpenHands.git # already have the repo? check out this version: $ git checkout v1.10.0
- ›Adds activity log export capability to the interface.
- ›Ships a featured automations landing dashboard for discovering and launching automations.
- ›Adds manifest-driven sub-pages to the automation interface, enabling structured automation workflows.
- ›Adds a faceted filter rail to the Skills page for narrowing skills by category.
- ›Sets the Canvas default model to GLM 5.2.
- v1.9.0
OpenHands v1.9.0 adds live agent activity in chat, a streamlined backend chooser, and an extension-manifest host.
└──▷ GET THIS VERSION$ git clone --branch v1.9.0 https://github.com/All-Hands-AI/OpenHands.git # already have the repo? check out this version: $ git checkout v1.9.0
- ›Adds a compact Cloud vs Agent-server add-backend chooser to streamline switching between backend types.
- ›Shows live agent activity directly in the chat UI so users can follow along in real time.
- ›Introduces a domain-neutral extension-manifest host to support broader extension compatibility.
- v1.9.0
OpenHands v1.9.0 adds live agent activity in chat, a compact backend chooser, and an extension-manifest host.
└──▷ GET THIS VERSION$ git clone --branch v1.9.0 https://github.com/OpenHands/OpenHands.git # already have the repo? check out this version: $ git checkout v1.9.0
- ›Shows live agent activity streamed directly in the chat view so users can follow what the agent is doing in real time.
- ›Adds a compact Cloud vs Agent-server backend chooser UI to the backends settings, making it faster to switch between hosting modes.
- ›Introduces a domain-neutral extension-manifest host to support loading extensions independently of the deployment domain.
- ›Drives the automation UI from the interface manifest, enabling manifest-controlled automation flows.
- v1.9.0
OpenHands v1.9.0 adds live agent activity in chat, a compact backend chooser, and an extension-manifest host.
└──▷ GET THIS VERSION$ git clone --branch v1.9.0 https://github.com/OpenHands/OpenHands.git # already have the repo? check out this version: $ git checkout v1.9.0
- ›Shows live agent activity streamed directly in the chat view so users can follow what the agent is doing in real time.
- ›Adds a compact Cloud vs Agent-server backend chooser UI to the backends settings, making it faster to switch between hosting modes.
- ›Introduces a domain-neutral extension-manifest host to support loading extensions independently of the deployment domain.
- ›Drives the automation UI from the interface manifest, enabling manifest-controlled automation flows.
- v1.8.0
OpenHands v1.8.0 adds per-card enable/disable toggling for installed MCP servers.
└──▷ GET THIS VERSION$ git clone --branch v1.8.0 https://github.com/All-Hands-AI/OpenHands.git # already have the repo? check out this version: $ git checkout v1.8.0
- ›Adds the ability to enable or disable an installed MCP server directly from its card in the UI, without uninstalling it.
- v1.8.0
OpenHands v1.8.0 adds the ability to enable or disable installed MCP servers directly from their card in the UI.
└──▷ GET THIS VERSION$ git clone --branch v1.8.0 https://github.com/OpenHands/OpenHands.git # already have the repo? check out this version: $ git checkout v1.8.0
- ›Adds a toggle on each installed MCP server's card to enable or disable it without uninstalling.
- v1.8.0
OpenHands v1.8.0 adds the ability to enable or disable installed MCP servers directly from their card in the UI.
└──▷ GET THIS VERSION$ git clone --branch v1.8.0 https://github.com/OpenHands/OpenHands.git # already have the repo? check out this version: $ git checkout v1.8.0
- ›Adds a toggle on each installed MCP server's card to enable or disable it without uninstalling.
- v1.7.0
OpenHands v1.7.0 adds persistent agent memory toggle, LLM selector always visible, and secret overwrite from edit form.
└──▷ GET THIS VERSION$ git clone --branch v1.7.0 https://github.com/All-Hands-AI/OpenHands.git # already have the repo? check out this version: $ git checkout v1.7.0
- ›Adds a persistent agent memory toggle in the UI, letting users enable or disable memory retention across agent sessions.
- ›LLM selector is now always visible in the UI; agent-profile switching has been moved to the tools menu.
- ›Allows overwriting an existing secret value directly from the secret edit form.
- v1.7.0
OpenHands v1.7.0 adds persistent agent memory toggle, always-visible LLM selector, and secret overwriting from the edit form.
└──▷ GET THIS VERSION$ git clone --branch v1.7.0 https://github.com/OpenHands/OpenHands.git # already have the repo? check out this version: $ git checkout v1.7.0
- ›Adds a persistent agent memory toggle so agents can retain context across sessions.
- ›Makes the LLM selector always visible in the UI; moves agent-profile switching into the tools menu.
- ›Allows overwriting an existing secret value directly from the secret edit form.
- v1.7.0
OpenHands v1.7.0 adds persistent agent memory toggle, always-visible LLM selector, and secret overwriting from the edit form.
└──▷ GET THIS VERSION$ git clone --branch v1.7.0 https://github.com/OpenHands/OpenHands.git # already have the repo? check out this version: $ git checkout v1.7.0
- ›Adds a persistent agent memory toggle so agents can retain context across sessions.
- ›Makes the LLM selector always visible in the UI; moves agent-profile switching into the tools menu.
- ›Allows overwriting an existing secret value directly from the secret edit form.
- cloud-1.47.0
OpenHands cloud-1.47.0 gates Agent Canvas behind SaaS authentication.
└──▷ GET THIS VERSION$ git clone --branch cloud-1.47.0 https://github.com/All-Hands-AI/OpenHands.git # already have the repo? check out this version: $ git checkout cloud-1.47.0
- ›Protects Agent Canvas behind SaaS authentication, restricting access to authenticated users.
- cloud-1.47.0
OpenHands cloud-1.47.0 gates Agent Canvas behind SaaS authentication.
└──▷ GET THIS VERSION$ git clone --branch cloud-1.47.0 https://github.com/OpenHands/OpenHands.git # already have the repo? check out this version: $ git checkout cloud-1.47.0
- ›Agent Canvas is now protected behind SaaS authentication, restricting access to authenticated users only.
- cloud-1.47.0
OpenHands cloud-1.47.0 gates Agent Canvas behind SaaS authentication.
└──▷ GET THIS VERSION$ git clone --branch cloud-1.47.0 https://github.com/OpenHands/OpenHands.git # already have the repo? check out this version: $ git checkout cloud-1.47.0
- ›Agent Canvas is now protected behind SaaS authentication, restricting access to authenticated users only.
- cloud-1.46.0
OpenHands 1.46 adds configurable BYOR key alias patterns and enriched final archive manifests.
└──▷ GET THIS VERSION$ git clone --branch cloud-1.46.0 https://github.com/All-Hands-AI/OpenHands.git # already have the repo? check out this version: $ git checkout cloud-1.46.0
- ›Enables configurable key alias patterns for Bring Your Own Router (BYOR) keys in enterprise deployments.
- ›Enriches final archive manifests with additional metadata and removes initial snapshots to streamline workspace archives.
- 1.11.0
OpenHands 1.11.0 adds Agent Profiles, a Budgets dashboard, expanded usage monitoring, and email surface visibility.
└──▷ GET THIS VERSION$ git clone --branch 1.11.0 https://github.com/All-Hands-AI/OpenHands.git # already have the repo? check out this version: $ git checkout 1.11.0
└──▷ HOW TO FIND ITCheck whether your SMTP or Resend email integration is active without digging through config files.📍In the console, go to Settings › Email and verify that the email provider status is shown as enabled.Monitor team spend and enforce cost limits by reviewing the new Budgets dashboard.📍In the console, go to Budgets to view configured budget limits and current usage, and to the Usage Dashboard for a breakdown of consumption by user or project.- ›Adds Agent Profiles on the cloud/SaaS backend, enabling enterprise teams to configure and manage distinct agent personas.
- ›Introduces a Budgets dashboard and expands the Usage Dashboard for spend tracking and resource monitoring.
- ›New budgets and usage monitoring UI surfaces consumption data directly in the product.
- ›Surfaces email provider status (SMTP/Resend) so admins can confirm email delivery is enabled.
- ›Passes repository metadata to observability traces, enriching trace context for debugging agent runs.
- cloud-1.45.0
OpenHands 1.45 adds Agent Profiles, a Budgets dashboard, expanded Usage Dashboard, and email provider status surfacing.
└──▷ GET THIS VERSION$ git clone --branch cloud-1.45.0 https://github.com/All-Hands-AI/OpenHands.git # already have the repo? check out this version: $ git checkout cloud-1.45.0
- ›Adds Agent Profiles support on the cloud/SaaS backend, enabling enterprise-level agent configuration management.
- ›Introduces a Budgets dashboard for tracking and enforcing spending limits.
- ›Expands the Usage Dashboard with additional monitoring metrics and UI.
- ›Surfaces email-enabled status for SMTP and Resend email providers in the admin UI.
- cloud-1.44.0
OpenHands 1.44.0 adds repository metadata to observability traces for richer debugging context.
└──▷ GET THIS VERSION$ git clone --branch cloud-1.44.0 https://github.com/All-Hands-AI/OpenHands.git # already have the repo? check out this version: $ git checkout cloud-1.44.0
- ›Includes repository metadata in observability traces, enabling richer context when debugging agent runs.
- cloud-1.43.0
OpenHands cloud gains SMTP email service, user login tracking, and a renamed Usage & Monitoring dashboard.
└──▷ GET THIS VERSION$ git clone --branch cloud-1.43.0 https://github.com/All-Hands-AI/OpenHands.git # already have the repo? check out this version: $ git checkout cloud-1.43.0
- ›Adds SMTP email service integration for outbound email delivery.
- ›Surfaces email-enabled status for both SMTP and Resend email providers in the UI.
- ›Tracks user login timestamps for visibility into account activity.
- ›Renames the admin dashboard to 'Usage & Monitoring'.
- 1.10.0
OpenHands 1.10.0 adds SMTP email service, user login timestamp tracking, and renames the admin dashboard to Usage & Monitoring.
└──▷ GET THIS VERSION$ git clone --branch 1.10.0 https://github.com/All-Hands-AI/OpenHands.git # already have the repo? check out this version: $ git checkout 1.10.0
- ›Adds SMTP email service integration for outbound email delivery alongside the existing Resend provider.
- ›Surfaces email-enabled status in the UI for both SMTP and Resend configurations.
- ›Tracks user login timestamps for audit and monitoring purposes.
- ›Renames the admin dashboard to 'Usage & Monitoring'.
- cloud-1.42.0
OpenHands 1.42.0 adds a super-admin management API for granting, revoking, and listing admin privileges in enterprise deployments.
└──▷ GET THIS VERSION$ git clone --branch cloud-1.42.0 https://github.com/All-Hands-AI/OpenHands.git # already have the repo? check out this version: $ git checkout cloud-1.42.0
- ›New enterprise super-admin management endpoint lets administrators programmatically grant, revoke, and list super-admin roles via API.
- 1.9.1
OpenHands 1.9.1 adds a super-admin management API for granting, revoking, and listing admin privileges.
└──▷ GET THIS VERSION$ git clone --branch 1.9.1 https://github.com/All-Hands-AI/OpenHands.git # already have the repo? check out this version: $ git checkout 1.9.1
- ›New enterprise/auth super-admin management endpoint supports grant, revoke, and list operations for super-admin roles.
- cloud-1.41.0
OpenHands 1.41 adds tree-sitter semantic chunking, parallel tool calls, time-bounded API keys, and an org admin conversation dashboard.
└──▷ GET THIS VERSION$ git clone --branch cloud-1.41.0 https://github.com/All-Hands-AI/OpenHands.git # already have the repo? check out this version: $ git checkout cloud-1.41.0
└──▷ HOW TO FIND ITRestrict an API key to a specific validity window so it auto-expires after a contractor engagement ends.📍In the console, go to Settings › API Keys, create or edit a key, and set the 'Not Before' and 'Expires At' fields to define the active window.Speed up agent tasks that invoke multiple tools by allowing them to run concurrently instead of sequentially.📍In the console, go to Agent Settings and set 'tool_concurrency_limit' to the desired number of parallel tool calls (e.g., 4).- ›Adds semantic file chunking using tree-sitter AST parsing for more accurate code understanding during agent tasks.
- ›New organization conversation admin dashboard gives org admins visibility into all conversations under their org.
- ›Workspace state is now snapshotted at session start and archived before deletion, preserving production workspace history.
- ›Parallel tool calls are now configurable via a
tool_concurrency_limitagent setting, enabling concurrent tool execution. - ›API keys gain optional active-window controls (
not_beforeandexpires_at) for time-bounded access.
+7 moreshow less
- ›API keys now support an explicit 'unbound' org scope as a first-class option.
- ›New
GET /organizations/{id}/meendpoint exposes the caller's permissions within an organization. - ›Enterprise super roles can be assigned via
user.role_idwith permission fallback for fine-grained access control. - ›Repo and branch metadata is now attached to Laminar trace entries for better observability of agent runs.
- ›Dynamic marketplace support added for plugin registration, enabling third-party plugin discovery.
- ›SaaS auth now accepts an
api_keycookie as a fallback credential alongside header-based auth. - ›Jira Data Center integration panel now surfaces member-appropriate guidance instead of the admin setup form for non-admin users.
- 1.9.0
OpenHands 1.9.0 adds multi-model LLM discovery, Azure DevOps resolver, MCP server config for ACP agents, sub-agent task visualizer, and enterprise admin provisioning.
└──▷ GET THIS VERSION$ git clone --branch 1.9.0 https://github.com/All-Hands-AI/OpenHands.git # already have the repo? check out this version: $ git checkout 1.9.0
└──▷ USE ITSet a per-deployment resolver label to customize which resolver macro handles automation events.OH_RESOLVER_LABEL=my-team-resolver
Set the deployment mode to enterprise cloud to gate cloud-account CTAs appropriately.OH_DEPLOYMENT_MODE=enterprise_cloud
- ›Adds
hide_personal_workspacesflag to restrict org-only OHE installs to organization workspaces only. - ›Adds
switch_acp_modelproxy endpoint for switching LLM models mid-conversation in cloud ACP sessions. - ›Adds model dropdown and credential fields to the agent settings page for ACP agents.
- ›Supports MCP server configuration for ACP agents.
- ›Adds OHE multi-model LLM discovery with BYOK gating, proxy discovery, catalogue union, and UX.
+29 moreshow less
- ›Exposes copyable invite links so organization invitations work without email delivery.
- ›Accepts pending invitations by verified-email match at sign-in, removing friction for new members.
- ›Auto-accepts invitation links on click instead of showing a confirm/cancel modal.
- ›Adds explicit
OH_DEPLOYMENT_MODEflag to gate cloud-account CTAs to enterprise cloud deployments. - ›Adds
OH_RESOLVER_LABELenvironment variable for per-deployment resolver macro customization. - ›Adds Azure DevOps resolver with @mentions support and org-level one-click webhook setup.
- ›Adds Jira Data Center email-mode auto-link, targeted repo lookup, and picker mentions.
- ›Persists and injects per-user OAuth tokens in Jira DC resolver conversations.
- ›Supports Slack attachments in agent context.
- ›Adds sub-agent task (TaskToolSet) visualizer to the chat UI.
- ›Adds a 'Full Git history' user setting.
- ›Adds enterprise admin user-provisioning endpoint.
- ›Adds
default_sandbox_spec_idto user settings. - ›Adds parallel tool calls via
tool_concurrency_limitin agent settings. - ›Implements semantic file chunking using tree-sitter AST parsing.
- ›Adds organization conversation admin dashboard.
- ›Captures production workspace state with initial snapshot at start and archive before delete.
- ›Adds super roles via
user.role_idwith permission fallback for enterprise auth. - ›Exposes caller permissions on
GET /organizations/{id}/me. - ›Adds optional active window (
not_before&expires_at) for API keys. - ›Makes 'unbound' org scope an explicit, first-class option for API keys.
- ›Adds dynamic marketplace support for plugin registration.
- ›Accepts
api_keycookie as a fallback credential for SaaS auth. - ›Parallelizes GitHub GraphQL queries in
get_suggested_tasksfor faster task suggestions. - ›Surfaces a clear error when a custom sandbox image's agent-server SDK version mismatches.
- ›Routes unclaimed automation events to the default org on single-org installs.
- ›Adds repo/branch metadata to Laminar trace entries.
- ›Exposes the automations menu item for all users.
- ›Uses interrupt endpoint for agent pause UI interactions.
- ›Adds
- cloud-1.40.0
OpenHands 1.40 adds full Git history cloning, a default sandbox spec setting, Azure DevOps webhook setup, and richer Jira DC integration.
└──▷ GET THIS VERSION$ git clone --branch cloud-1.40.0 https://github.com/All-Hands-AI/OpenHands.git # already have the repo? check out this version: $ git checkout cloud-1.40.0
└──▷ HOW TO FIND ITPin a specific sandbox environment for all your agent runs so you don't have to reconfigure it per session.📍In the console, go to Settings › User Settings and set the Default Sandbox Spec to your preferred environment via thedefault_sandbox_spec_idfield.Enable full Git history cloning when your agents need to analyze commit history or run git-log-based tools.📍In the console, go to Settings › User Settings and enable the Full Git History option.Set up org-level Azure DevOps webhooks in one click to automatically trigger OpenHands resolvers on mentions.📍In the console, go to Settings › Integrations › Azure DevOps and use the one-click webhook setup under your organization.- ›Adds a user setting to enable full Git history cloning (instead of shallow clones) for agents that need deep commit context.
- ›Adds
default_sandbox_spec_idto user settings, letting users pin a preferred sandbox environment across sessions. - ›Adds an enterprise admin endpoint for programmatic user provisioning.
- ›Adds Azure DevOps resolver mentions and org-level one-click webhook setup, simplifying CI/CD trigger configuration.
- ›Enhances Jira Data Center integration with email-mode auto-linking, targeted repository lookup, and picker mentions.
+1 moreshow less
- ›Introduces a dedicated interrupt endpoint powering the agent pause UI, enabling more reliable mid-task agent control.
- cloud-1.39.0
OpenHands 1.39.0 adds ACP model switching, MCP server config for ACP agents, Slack attachment context, multi-model LLM discovery, copyable invite links, and a sub-agent task visualizer.
└──▷ GET THIS VERSION$ git clone --branch cloud-1.39.0 https://github.com/All-Hands-AI/OpenHands.git # already have the repo? check out this version: $ git checkout cloud-1.39.0
└──▷ TRY ITPin a custom resolver label per deployment so automation events are routed to the correct resolver macro.$ OH_RESOLVER_LABEL=my-org-resolverCopy and share an org invite link directly from the console so new members can join without waiting for an email.📍In the console, go to Settings › Organization › Members and click "Copy invite link" to share a URL that auto-accepts on click.- ›Adds
switch_acp_modelproxy endpoint enabling model switching for cloud ACP conversations. - ›Adds model dropdown and credential fields to the agent settings page for ACP agents.
- ›Supports MCP server configuration for ACP agents.
- ›Enables multi-model LLM discovery and BYOK gating for OpenHands Enterprise (OHE) installs, including proxy discovery and catalogue union.
- ›Adds
hide_personal_workspacesflag to restrict OHE installs to org-only workspaces.
+16 moreshow less
- ›Adds explicit
OH_DEPLOYMENT_MODEflag to control deployment mode and gate cloud-account CTAs to enterprise cloud. - ›Adds
OH_RESOLVER_LABELenv var to configure a per-deployment resolver macro. - ›Exposes copyable invite links so org invitations work without email delivery.
- ›Auto-accepts invitation links on click, removing the confirm/cancel modal.
- ›Accepts pending invitations by verified-email match at sign-in.
- ›Adds validation for secret names to ensure valid environment variable format.
- ›Surfaces Slack attachments as context in agent conversations.
- ›Adds a sub-agent task (TaskToolSet) visualizer to the chat UI.
- ›Adds
DynamicRemoteSandboxSpecServicebacked by runtime-API warm configs for dynamic sandbox provisioning. - ›Parallelizes GitHub GraphQL queries in
get_suggested_tasksfor faster task suggestions. - ›Surfaces a clear error in the UI when a custom sandbox image's agent-server SDK version mismatches.
- ›Persists and injects per-user OAuth tokens in Jira Data Center resolver conversations.
- ›Exposes the Automations menu item to all users.
- ›Routes unclaimed automation events to the default org on single-org installs.
- ›Moves existing users into the default org when first auto-added, and makes the first signed-in user the default org owner (tracked via
is_defaultflag). - ›Encodes agent harness in the conversation chip icon and surfaces the model name in chip text.
- ›Adds
- 1.8.0
OpenHands 1.8.0 adds LLM profiles, sub-agent delegation, sandbox grouping strategies, and a generic ACP agent UI.
└──▷ GET THIS VERSION$ git clone --branch 1.8.0 https://github.com/All-Hands-AI/OpenHands.git # already have the repo? check out this version: $ git checkout 1.8.0
- ›Adds LLM profiles, letting users save and switch between named LLM configurations.
- ›Enables sub-agent delegation, allowing the primary agent to hand off subtasks to specialised child agents.
- ›Adds user-selectable sandbox grouping strategy to control how sandbox environments are allocated and shared.
- ›Introduces a minimal generic ACP (Agent Communication Protocol) agent UI for interacting with ACP-compatible agents.
└──▷ BREAKING ON UPGRADE- !The App tab has been removed from the conversation view.
- 1.7.0
OpenHands 1.7.0 adds KVM-accelerated sandbox VMs, exposes SDK settings schema, and surfaces LLM model info in the UI.
└──▷ GET THIS VERSION$ git clone --branch 1.7.0 https://github.com/All-Hands-AI/OpenHands.git # already have the repo? check out this version: $ git checkout 1.7.0
- ›New
SANDBOX_KVM_ENABLEDenvironment variable lets sandbox containers pass through/dev/kvm, enabling KVM-accelerated virtual machines instead of slow emulation. - ›Exposes SDK settings schema to OpenHands, making programmatic configuration discovery available to integrations.
- ›Displays the active LLM model on conversation cards and the header for at-a-glance visibility.
- ›Tavily search key moved to MCP settings, centralising external tool credentials under the MCP configuration surface.
- ›New
- 1.6.0
OpenHands 1.6.0 adds hooks support,
/clearand/newchat commands, toggleable global skills, and Catalan UI localization.└──▷ GET THIS VERSION$ git clone --branch 1.6.0 https://github.com/All-Hands-AI/OpenHands.git # already have the repo? check out this version: $ git checkout 1.6.0
└──▷ HOW TO FIND ITReset chat context mid-session without losing your running sandbox state — useful when a conversation has drifted and you want a clean prompt history.📍In the chat input, type/clearand press Enter. A new conversation opens, inheriting the current sandbox and configuration.- ›Adds hooks support, enabling extensible event-driven integrations with the OpenHands runtime.
- ›New
/clearslash command starts a fresh conversation that inherits the current sandbox and configuration, preserving runtime state while resetting chat history. - ›New
/newslash command is now surfaced in the slash command menu for faster access to new conversations. - ›Adds ability to enable or disable default global skills, giving operators control over which built-in capabilities are active.
- ›Adds a copy button to code blocks in the chat UI for easier extraction of generated code.
+1 moreshow less
- ›Adds Catalan language support to the UI.
- 1.5.0
OpenHands 1.5.0 adds a planning agent, real-time Task List panel, slash command menu, Bitbucket Datacenter support, and six new models.
└──▷ GET THIS VERSION$ git clone --branch 1.5.0 https://github.com/All-Hands-AI/OpenHands.git # already have the repo? check out this version: $ git checkout 1.5.0
└──▷ HOW TO FIND ITSurface available agent skills mid-conversation without leaving the chat input.📍In the chat input, type/to open the slash command menu and select an available agent skill or command.Monitor the agent's progress across multi-step tasks in real time.📍In the right panel, click the Task List tab to view the agent's current tasks and their live status.- ›Adds a planning agent for structured, multi-step task execution.
- ›New Task List tab in the right panel shows the agent's current task list with real-time status updates.
- ›New slash command menu in the chat input surfaces available agent skills and commands when typing
/. - ›Enables attaching or changing the Git repository for existing conversations.
- ›Adds Bitbucket Datacenter as a supported Git provider.
+1 moreshow less
- ›Adds support for Claude Opus 4.6, Claude Sonnet 4.6, GLM-4.7, GLM-5, Kimi-K2.5, Qwen3-Coder-Next, and Gemini 3.1 Pro Preview models.
- 1.4.0
OpenHands 1.4.0 adds MiniMax-M2.5 model support.
└──▷ GET THIS VERSION$ git clone --branch 1.4.0 https://github.com/All-Hands-AI/OpenHands.git # already have the repo? check out this version: $ git checkout 1.4.0
- ›Adds MiniMax-M2.5 as a supported LLM backend.
- 1.3.0
OpenHands 1.3.0 adds CORS support for remote browser access and host networking mode for reverse proxy setups.
└──▷ GET THIS VERSION$ git clone --branch 1.3.0 https://github.com/All-Hands-AI/OpenHands.git # already have the repo? check out this version: $ git checkout 1.3.0
- ›Adds CORS support to the Docker sandbox service, enabling remote browser access by setting
WEB_HOSTandSANDBOX_CONTAINER_URL_PATTERN. - ›Adds host networking mode via
OH_SANDBOX_USE_HOST_NETWORK=true, allowing reverse proxies to reach user-launched applications on any port beyond the predefined worker ports.
- ›Adds CORS support to the Docker sandbox service, enabling remote browser access by setting
- 1.2.0
OpenHands 1.2.0 adds a chat readiness status indicator and doubles the condenser context window default.
└──▷ GET THIS VERSION$ git clone --branch 1.2.0 https://github.com/All-Hands-AI/OpenHands.git # already have the repo? check out this version: $ git checkout 1.2.0
- ›Adds a status indicator above the chat UI that shows when a conversation is ready to receive input.
- ›Doubles the condenser default
max_sizefrom 120 to 240, allowing larger context to be retained before summarization.
- 1.1.0
OpenHands 1.1.0 adds OAuth 2.0 Device Flow for CLI auth, Forgejo integration, and conversation export.
└──▷ GET THIS VERSION$ git clone --branch 1.1.0 https://github.com/All-Hands-AI/OpenHands.git # already have the repo? check out this version: $ git checkout 1.1.0
└──▷ HOW TO FIND ITAuthenticate the OpenHands CLI from a headless server or remote shell without needing a browser on the same machine.📍In the OpenHands CLI, select 'Login' and follow the Device Flow prompt: visit the displayed URL on any device and enter the code to authorize the session.Save a full agent conversation for audit, review, or sharing — useful after a complex remediation session.📍In the OpenHands UI, open the conversation panel, locate the session, and click 'Export Conversation' to download the conversation as a file.- ›Adds OAuth 2.0 Device Flow for CLI authentication, enabling headless and browser-less login workflows.
- ›Adds Forgejo integration, extending repository provider support to the self-hosted Forgejo platform.
- ›Adds an Export Conversation button in the conversation panel to save full conversation history.
- ›Adds a Refresh button on the Changes tab for on-demand file-diff updates without reloading.
- 1.0.0
OpenHands 1.0.0 adds Azure DevOps integration, a new task tracker UI, and native tool calling for Gemini 2.5 Pro.
└──▷ GET THIS VERSION$ git clone --branch 1.0.0 https://github.com/All-Hands-AI/OpenHands.git # already have the repo? check out this version: $ git checkout 1.0.0
- ›Adds Azure DevOps integration support for repository and pipeline connectivity.
- ›New task tracker interface provides structured visibility into agent task progress.
- ›Chat messages are now queued during runtime connection, enabling smoother interaction during agent startup.
- 0.62.0
OpenHands 0.62.0 adds conversation tab pinning and a Documentation link in the profile menu.
└──▷ GET THIS VERSION$ git clone --branch 0.62.0 https://github.com/All-Hands-AI/OpenHands.git # already have the repo? check out this version: $ git checkout 0.62.0
└──▷ HOW TO FIND ITKeep a frequently referenced conversation always accessible by pinning it.📍In the OpenHands UI, right-click or use the tab options on a conversation tab and select 'Pin' to pin it; select 'Unpin' to remove the pin.- ›Enables pinning and unpinning of conversation tabs for quick access to important sessions.
- ›Adds a Documentation link directly in the profile menu for faster access to reference material.
- 0.61.0
OpenHands 0.61.0 makes the terminal tab read-only and removes the Jupyter tab from the UI.
└──▷ GET THIS VERSION$ git clone --branch 0.61.0 https://github.com/All-Hands-AI/OpenHands.git # already have the repo? check out this version: $ git checkout 0.61.0
- ›Terminal tab is now read-only, preventing direct user input into the agent's terminal session.
- ›Jupyter tab has been removed from the UI.
└──▷ BREAKING ON UPGRADE- !The Jupyter tab has been removed from the UI; any workflows relying on it will no longer have access to it.
- 0.60.0
OpenHands 0.60.0 adds Clarifai provider support and automatic sandbox lifecycle management to curb resource exhaustion.
└──▷ GET THIS VERSION$ git clone --branch 0.60.0 https://github.com/All-Hands-AI/OpenHands.git # already have the repo? check out this version: $ git checkout 0.60.0
- ›Adds Clarifai as a supported LLM provider.
- ›Adds automatic sandbox lifecycle management that limits the number of concurrently running sandboxes to prevent resource exhaustion.
- ›Simplifies the security analyzer confirmation UI by replacing two reject options with a single 'Reject' option that prompts for an optional reason.
└──▷ BREAKING ON UPGRADE- !The V0 CLI has been removed and is officially unsupported; any setup relying on the V0 CLI will break on upgrade.
- 0.59.0
OpenHands 0.59.0 adds Lemonade as a supported LLM provider.
└──▷ GET THIS VERSION$ git clone --branch 0.59.0 https://github.com/All-Hands-AI/OpenHands.git # already have the repo? check out this version: $ git checkout 0.59.0
- ›Adds Lemonade Provider as a supported LLM backend option.
- 1.0.0-cli
OpenHands 1.0.0-cli ships standalone binaries, faster startup, a refreshed UI, and MCP OAuth support.
└──▷ GET THIS VERSION$ git clone --branch 1.0.0-cli https://github.com/All-Hands-AI/OpenHands.git # already have the repo? check out this version: $ git checkout 1.0.0-cli
- ›Adds multi-platform standalone executable binaries so the CLI runs without any additional setup or runtime install.
- ›Faster CLI startup when running via
uv,pip, and similar tools. - ›New and refreshed UI for the CLI experience.
- ›Simplified JSON MCP configuration with added MCP OAuth support.
- 0.58.0
OpenHands 0.58.0 adds configurable SHTTP MCP server timeouts and claude-sonnet-4-5 model support.
└──▷ GET THIS VERSION$ git clone --branch 0.58.0 https://github.com/All-Hands-AI/OpenHands.git # already have the repo? check out this version: $ git checkout 0.58.0
- ›Adds configurable timeout settings for SHTTP MCP servers, preventing tool calls from hanging indefinitely.
- ›Adds support for the claude-sonnet-4-5 model.
- ›Converts the settings panel to a vertical sidebar layout.
- 0.57.0
OpenHands 0.57.0 adds a redesigned UI and Bring Your Own Key (BYOK) support on Cloud.
└──▷ GET THIS VERSION$ git clone --branch 0.57.0 https://github.com/All-Hands-AI/OpenHands.git # already have the repo? check out this version: $ git checkout 0.57.0
└──▷ HOW TO FIND ITUse your own LLM API key on OpenHands Cloud instead of the platform's default billing.📍In the OpenHands Cloud console, go to Settings and enter your own API key under the Bring Your Own Key (BYOK) section.- ›New UI for landing and conversation pages improves the agent interaction experience.
- ›Adds Bring Your Own Key (BYOK) support on OpenHands Cloud, letting users supply their own LLM API keys.
- 0.56.0
OpenHands 0.56.0 adds AGENTS.md support, microagent management, and multi-LLM routing within agent trajectories.
└──▷ GET THIS VERSION$ git clone --branch 0.56.0 https://github.com/All-Hands-AI/OpenHands.git # already have the repo? check out this version: $ git checkout 0.56.0
- ›Supports AGENTS.md files in microagents, enabling repo-level agent behavior configuration via a standardized file.
- ›New microagent management feature for organizing and controlling microagents.
- ›Enables routing between different LLMs within a single agent trajectory, allowing dynamic model selection per task step.
- 0.55.0
OpenHands 0.55.0 adds an LLM risk analyzer and configurable condenser history size limit.
└──▷ GET THIS VERSION$ git clone --branch 0.55.0 https://github.com/All-Hands-AI/OpenHands.git # already have the repo? check out this version: $ git checkout 0.55.0
- ›Adds a configurable max history size setting for the condenser, giving operators control over context window usage.
- ›Improves performance and UX when working with repositories containing many branches.
- 0.54.0
OpenHands 0.54 adds task tracking with planning mode, MCP on Cloud, and an improved MCP config UI.
└──▷ GET THIS VERSION$ git clone --branch 0.54.0 https://github.com/All-Hands-AI/OpenHands.git # already have the repo? check out this version: $ git checkout 0.54.0
└──▷ HOW TO FIND ITConnect an MCP server on OpenHands Cloud to extend the agent with custom tools.📍In the OpenHands Cloud console, go to Settings › MCP and use the Add, Edit, or Delete controls to manage your MCP server configurations.- ›Adds a task tracking tool and planning mode to help agents manage long-horizon, multi-step tasks.
- ›Enables Model Context Protocol (MCP) support on OpenHands Cloud.
- ›Improves the MCP configuration UI with add, edit, and delete functionality.
- ›Adds a new user feedback reason: 'The agent didn't finish the job'.
- 0.53.0
OpenHands 0.53.0 adds named Docker volume binding, configurable git commit identity, and partial CLI settings updates.
└──▷ GET THIS VERSION$ git clone --branch 0.53.0 https://github.com/All-Hands-AI/OpenHands.git # already have the repo? check out this version: $ git checkout 0.53.0
- ›Supports binding named Docker volumes into the runtime for persistent or shared storage across agent sessions.
- ›Enables specifying the user identity (name/email) OpenHands commits as when pushing code changes.
- ›Allows partial modification of CLI settings without needing to restate the full configuration.
- 0.52.0
OpenHands 0.52.0 adds GPT-5, Claude Opus 4.1, Qwen-3-Coder-480B, CLI UI launch, and overlay mount support.
└──▷ GET THIS VERSION$ git clone --branch 0.52.0 https://github.com/All-Hands-AI/OpenHands.git # already have the repo? check out this version: $ git checkout 0.52.0
└──▷ HOW TO FIND ITToggle solvability analysis on or off for the GitHub issue resolver in OpenHands Cloud to control triage depth.📍In OpenHands Cloud, go to the Resolver settings and use the solvability analysis switch to enable or disable additional solvability analysis.- ›Adds
qwen-3-coder-480bto the OpenHands provider model roster. - ›Adds
gpt-5-2025-08-07to the OpenHands provider model roster. - ›Adds
claude-opus-4-1-20250805as a supported model. - ›Adds search API key settings configuration to the CLI.
- ›Supports launching the full OpenHands UI directly from the CLI.
+6 moreshow less
- ›Supports overlay mounts in the Docker runtime for more flexible workspace setups.
- ›Adds a toggle to enable or disable solvability analysis in the resolver on OpenHands Cloud.
- ›Includes branch information in repository context provided to agents.
- ›Adds auto-pagination with infinite scroll for the conversation list.
- ›Expands conversation history limit from 20 to 100 entries.
- ›Adds proper markdown rendering for agent messages and final thoughts in the CLI interface.
- ›Adds
- 0.51.0
OpenHands 0.51 adds MCP support for the CLI, multi-repo git change detection, and smarter resolver summaries.
└──▷ GET THIS VERSION$ git clone --branch 0.51.0 https://github.com/All-Hands-AI/OpenHands.git # already have the repo? check out this version: $ git checkout 0.51.0
- ›Adds MCP (Model Context Protocol) support to the CLI, enabling tool-server integrations previously only available in the UI.
- ›Optimizes git change detection in the Changes tab with performance improvements and multi-repository support.
- ›Improves resolver summary generation by focusing each summary only on new changes since the last one, reducing repetition across consecutive summaries.
- 0.50.0
OpenHands 0.50 adds Moonshot AI Kimi-K2 model support and new CLI confirmation dialog options
└──▷ GET THIS VERSION$ git clone --branch 0.50.0 https://github.com/All-Hands-AI/OpenHands.git # already have the repo? check out this version: $ git checkout 0.50.0
- ›Adds Moonshot AI Kimi-K2 (kimi-k2-0711-preview) as a recommended and natively supported model via the OpenHands provider.
- ›Adds new options to CLI confirmation dialogs, giving practitioners more control over interactive approval flows.
- ›Persists alias choices in the CLI across sessions, reducing repetitive configuration.
- ›Improves MCP settings UI layout and clarity for easier Model Context Protocol configuration.
- 0.49.0
OpenHands 0.49 adds CLI/VSCode integration, a new Memory UI, OpenHands Cloud LLM provider, and conversation management improvements.
└──▷ GET THIS VERSION$ git clone --branch 0.49.0 https://github.com/All-Hands-AI/OpenHands.git # already have the repo? check out this version: $ git checkout 0.49.0
└──▷ TRY ITCheck which config file OpenHands is loading without digging through docs — useful when managing multiple environments.$ /settings- ›Adds CLI/VSCode integration, enabling OpenHands to be used directly from the command line and VS Code.
- ›Introduces an OpenHands Cloud LLM provider, letting users route model calls through OpenHands Cloud.
- ›New Memory UI feature surfaces agent memory state in the interface.
- ›Conversation cards now display branch name and git provider at a glance.
- ›Suggested tasks are now split and organized by git provider.
+3 moreshow less
- ›Users can edit a conversation's title directly in the UI.
- ›CLI alias setup for first-time users: on first run, users are offered the option to create
openhandsandohshell aliases for faster launch. - ›CLI
/settingscommand now displays the active configuration file path.
- 0.48.0
OpenHands 0.48 adds user-directory microagents, .cursorrules support, conversation stop control, and setup.sh event visibility.
└──▷ GET THIS VERSION$ git clone --branch 0.48.0 https://github.com/All-Hands-AI/OpenHands.git # already have the repo? check out this version: $ git checkout 0.48.0
- ›Supports loading microagents from the user directory (
~/.openhands/microagents/) for per-user agent customization without touching project repos. - ›Supports
.cursorrulesfiles placed in the project root directory, letting teams reuse existing Cursor editor rule sets. - ›Adds ability to stop in-progress conversations from the UI.
- ›Surfaces
setup.shscript execution in the event stream so users can observe when and how the setup script runs.
└──▷ BREAKING ON UPGRADE- !The Jupyter plugin is now disabled by default in the CLI runtime; setups that relied on Jupyter being active without explicit configuration will no longer have it enabled.
- ›Supports loading microagents from the user directory (
- 0.47.0
OpenHands 0.47 adds GitLab microagent config directory support and smarter terminal output truncation.
└──▷ GET THIS VERSION$ git clone --branch 0.47.0 https://github.com/All-Hands-AI/OpenHands.git # already have the repo? check out this version: $ git checkout 0.47.0
└──▷ HOW TO FIND ITStore org-level microagents in a GitLab repo using the supported alternative directory path so OpenHands can discover them.📍In your GitLab group, create a repository namedopenhands-configand place your microagent.mdfiles under themicroagents/folder — OpenHands will automatically load them per the updated org microagent discovery logic.- ›Adds new feedback options for users within the UI.
- ›Supports
openhands-configas an alternative GitLab directory for hosting org-level microagents. - ›Changes terminal truncation to trim the middle of long outputs instead of the suffix, preserving both start and end context.
- 0.46.0
OpenHands 0.46 adds custom model names, vi-mode CLI keybindings, configurable safety settings, and system prompt overrides.
└──▷ GET THIS VERSION$ git clone --branch 0.46.0 https://github.com/All-Hands-AI/OpenHands.git # already have the repo? check out this version: $ git checkout 0.46.0
└──▷ TRY ITEnable vi-style j/k navigation in CLI confirmation menus for keyboard-driven workflows.$ CLI_VI_MODE=true python -m openhands.core.cli
- ›Supports custom/arbitrary model names during CLI model selection, beyond the preset list.
- ›Adds optional vi-style keybindings (j/k navigation) for CLI confirmation prompts, enabled via the
CLI_VI_MODEenvironment variable. - ›Adds customizable safety settings for Mistral AI and Gemini models.
- ›Enables overriding the hardcoded system prompt for full prompt control.
- ›Allows users to submit feedback on agent performance even when the agent hit an error or is awaiting user input.
- 0.45.0
OpenHands 0.45 adds Kubernetes runtime, Bitbucket integration, file/image uploads, per-conversation budgets, and Japanese UI.
└──▷ GET THIS VERSION$ git clone --branch 0.45.0 https://github.com/All-Hands-AI/OpenHands.git # already have the repo? check out this version: $ git checkout 0.45.0
- ›Adds Kubernetes Runtime support as a new sandbox execution backend.
- ›Supports file and image uploads directly within conversations.
- ›Adds Bitbucket integration for local usage alongside existing GitHub support.
- ›Enables per-conversation budget configuration to cap LLM spending.
- ›Adds Japanese language support to the UI.
+1 moreshow less
- ›Increases max iterations per task from 250 to 500, enabling more complex autonomous workflows.
└──▷ BREAKING ON UPGRADE- !The local configuration directory has moved from
~/.openhands-stateto~/.openhands; existing state stored in the old path will not be picked up automatically after upgrading.
- 0.44.0
OpenHands 0.44 adds draft PR/MR control via Git MCP, Slack integration in settings, and SWE-bench-Live evaluation support.
└──▷ GET THIS VERSION$ git clone --branch 0.44.0 https://github.com/All-Hands-AI/OpenHands.git # already have the repo? check out this version: $ git checkout 0.44.0
└──▷ HOW TO FIND ITInstall the Slack integration for your Cloud OpenHands workspace without leaving the product.📍In the Cloud OpenHands console, go to Settings › Integrations and follow the prompts to install the Slack integration.- ›Agents can now control whether PRs/MRs opened via Git MCP are created as drafts or ready-for-review.
- ›Adds Slack integration installable directly from the Integrations tab in the Cloud OpenHands Settings page.
- ›Supports evaluation runs on SWE-bench-Live for more realistic, up-to-date issue-resolving benchmarks.
- ›Dev container networking now works without host network mode, improving security and portability of the dev setup.
- 0.43.0
OpenHands 0.43 adds Slack integration (beta), a Microagents UI, GitLab lower-scoped token support, and a code review microagent example.
└──▷ GET THIS VERSION$ git clone --branch 0.43.0 https://github.com/All-Hands-AI/OpenHands.git # already have the repo? check out this version: $ git checkout 0.43.0
└──▷ HOW TO FIND ITBrowse available microagents mid-conversation to understand what specialized knowledge is loaded before asking a domain-specific question.📍In the conversation UI, open the context menu and select 'Microagents' to view the list of active specialized microagents for the current session.- ›New Slack integration (beta) with Cloud OpenHands for triggering and interacting with agents via Slack.
- ›New Microagents UI in the conversation context menu lets users see what specialized knowledge microagents are available in their current conversation.
- ›New example code review microagent provides a ready-made template for automated code review workflows.
- ›Supports lower-scoped GitLab tokens, enabling more granular permission control when connecting GitLab repositories.
- ›Adds JSON serialization for array and object parameters when converting tools, broadening tool-call compatibility.
└──▷ BREAKING ON UPGRADE- !The CLI default provider is changed from
openaitoanthropic; existing CLI users relying on the default will now target Anthropic instead of OpenAI. - !CLI settings are now saved directly under
~/.openhandsinstead of the previous location; existing CLI config files stored elsewhere will no longer be read automatically.
- 0.42.0
OpenHands 0.42.0 adds API endpoints to control conversation lifecycle and lets users update their email address.
└──▷ GET THIS VERSION$ git clone --branch 0.42.0 https://github.com/All-Hands-AI/OpenHands.git # already have the repo? check out this version: $ git checkout 0.42.0
- ›New API endpoints to explicitly start and stop conversations programmatically.
- ›New
VSCODE_IN_NEW_TABfeature flag to open the VS Code editor in a new browser tab.
- 0.41.0
OpenHands 0.41.0 adds Cloud GitLab Resolver, streamable HTTP MCP support, and native Windows runtime.
└──▷ GET THIS VERSION$ git clone --branch 0.41.0 https://github.com/All-Hands-AI/OpenHands.git # already have the repo? check out this version: $ git checkout 0.41.0
- ›Adds Cloud GitLab Resolver, enabling automated issue/PR resolution against cloud-hosted GitLab repositories.
- ›Implements streamable HTTP MCP transport, supporting MCP servers served over HTTP streams.
- ›Adds native Windows support without requiring WSL, broadening local deployment options.
- ›Improves CLI mode setup flow to guide users through configuration when settings are missing.
- 0.40.0
OpenHands 0.40.0 adds native PR/MR creation via MCP, LocAgent integration, and a first-class search API.
└──▷ GET THIS VERSION$ git clone --branch 0.40.0 https://github.com/All-Hands-AI/OpenHands.git # already have the repo? check out this version: $ git checkout 0.40.0
- ›Enables native PR/MR opening on GitHub and GitLab via in-house MCP integration.
- ›Incorporates LocAgent into OpenHands for improved code localization capabilities.
- ›Adds first-class search API support to OpenHands.
- ›Adds Interactive SWE-Bench benchmark for evaluating agent performance.
- ›Improves MCP tool usage visualization in the UI.
- 0.39.0
OpenHands 0.39.0 adds UI-based custom secret management and nested runtime API support for scalable agent deployments.
└──▷ GET THIS VERSION$ git clone --branch 0.39.0 https://github.com/All-Hands-AI/OpenHands.git # already have the repo? check out this version: $ git checkout 0.39.0
└──▷ HOW TO FIND ITStore a custom API key or credential so the agent can securely access it during task execution — no code change required.📍In the console, go to Settings › Secrets and add a new custom secret (name + value) to make it available to the agent at runtime.- ›Adds ability to save custom secrets for agents directly through the UI settings panel.
- ›Adds API support for nested runtimes, enabling more flexible and scalable agent deployments.
└──▷ BREAKING ON UPGRADE- !Only volumes explicitly mounted to
/workspacewill be treated as workspace mounts; other volume mounts no longer receive workspace treatment on upgrade.
- 0.38.0
OpenHands 0.38.0 adds Windows runtime, MCP config UI, self-hosted Git support, and user/org microagents.
└──▷ GET THIS VERSION$ git clone --branch 0.38.0 https://github.com/All-Hands-AI/OpenHands.git # already have the repo? check out this version: $ git checkout 0.38.0
└──▷ HOW TO FIND ITConfigure MCP servers for the agent via the settings UI.📍In the OpenHands UI, go to Settings › MCP and add your MCP server configurations.- ›Adds self-hosted GitLab and enterprise GitHub host settings for local installations.
- ›Supports user-defined runners for the resolver, enabling custom execution environments.
- ›Adds Windows local runtime support with PowerShell.
- ›Enables the agent to save browser screenshots as image files during sessions.
- ›Supports loading custom Agent implementations from arbitrary Python packages via config.toml.
+3 moreshow less
- ›Adds MCP (Model Context Protocol) configuration directly in the settings UI.
- ›Supports user- and org-level microagents for shared, reusable agent configurations.
- ›Simplifies workspace mounting via the
SANDBOX_VOLUMESconfiguration.
- 0.37.0
OpenHands 0.37.0 adds branch picker for repositories and per-user configurable conversation starters.
└──▷ GET THIS VERSION$ git clone --branch 0.37.0 https://github.com/All-Hands-AI/OpenHands.git # already have the repo? check out this version: $ git checkout 0.37.0
└──▷ HOW TO FIND ITTarget a specific branch when starting work on a repository from the homepage, without manually switching branches later.📍In the console, go to the Homepage, select your repository, then use the branch picker to choose the desired branch before starting a conversation.Disable proactive conversation starters for Cloud Resolver if you prefer a quieter, prompt-only experience.📍In the console, go to Account Settings and toggle 'Proactive conversation starters' off.- ›Adds a branch picker for repository selection on the homepage.
- ›Enables per-user configuration of proactive conversation starters for Cloud Resolver, togglable in account settings (enabled by default).
- ›Adds helpful tips to the Changes tab zero state.
- 0.36.0
OpenHands 0.36.0 adds CLI agent pause/resume, documentation search, and raises the conversation panel limit to 20.
└──▷ GET THIS VERSION$ git clone --branch 0.36.0 https://github.com/All-Hands-AI/OpenHands.git # already have the repo? check out this version: $ git checkout 0.36.0
- ›Adds pause and resume functionality for agents running in the CLI.
- ›Adds search support for documentation within the product.
- ›Separates settings into multiple distinct sections in the UI.
- ›Increases the conversation panel limit from 9 to 20.
- 0.35.0
OpenHands 0.35 adds API key management UI, GitLab suggested tasks, a VS Code tab, and new CLI commands.
└──▷ GET THIS VERSION$ git clone --branch 0.35.0 https://github.com/All-Hands-AI/OpenHands.git # already have the repo? check out this version: $ git checkout 0.35.0
└──▷ TRY ITQuickly start a new session, check status, or open settings without leaving the CLI.$ /new /status /settingsManage API keys for programmatic access to OpenHands Cloud from the settings page.📍In the OpenHands Cloud console, go to Settings › API Keys to create or revoke keys.- ›Supports viewing and launching suggested tasks for GitLab repositories directly from the homepage.
- ›Replaces the Workspace tab with a VS Code tab for in-browser code editing.
- ›Enables
/new,/status, and/settingscommands in the CLI. - ›Sorts GitHub repos in OpenHands Cloud by most recently pushed, making active repos easier to find.
- ›Simplifies microagent authoring: names in frontmatter are no longer required — only triggers matter for dynamically loaded microagents.
- 0.34.0
OpenHands 0.34 adds a Changes tab for reviewing agent modifications, custom sandboxes for the resolver, and tool disabling controls.
└──▷ GET THIS VERSION$ git clone --branch 0.34.0 https://github.com/All-Hands-AI/OpenHands.git # already have the repo? check out this version: $ git checkout 0.34.0
└──▷ HOW TO FIND ITWhen reviewing what an agent changed in a session, open the Changes tab to see a diff of all modified files before accepting or rolling back.📍In the OpenHands UI, open an active or completed session and click the Changes tab to view a diff of all files modified by the agent.- ›New Changes tab in the UI surfaces all file modifications made by OpenHands during a session, making agent-driven diffs reviewable at a glance.
- ›Adds ability to disable specific default tools, giving operators fine-grained control over which capabilities the agent can invoke.
- ›Supports custom sandbox images for the resolver, enabling reproducible, project-specific environments when resolving GitHub issues.
- ›Resolver now names branches with the
openhands/prefix, establishing a consistent convention for identifying agent-created branches. - ›Updated home screen layout improves navigation and workspace entry points.
└──▷ BREAKING ON UPGRADE- !Resolver branches are now created with the
openhands/prefix — any automation or filters matching previous branch name patterns must be updated.
- 0.33.0
OpenHands 0.33 adds native MCP server support, GitLab OAuth/PAT integration, GitHub Enterprise resolver, and interactive CLI commands.
└──▷ GET THIS VERSION$ git clone --branch 0.33.0 https://github.com/All-Hands-AI/OpenHands.git # already have the repo? check out this version: $ git checkout 0.33.0
- ›Supports MCP servers natively via CodeActAgent, enabling model context protocol tool use within agents.
- ›Adds GitLab API integration with both OAuth and PAT token authentication.
- ›Enables PR type specification when using the GitHub Action resolver.
- ›Supports GitHub Enterprise and on-premises GitLab in the GitHub Action resolver.
- ›Adds interactive CLI commands
/init,/help, and/exitwith an enhanced startup experience.
+2 moreshow less
- ›Displays agent 'think' actions as collapsible elements in the conversation view.
- ›Improves SWE-bench_Verified single-pass baseline results to 59.6%.
- 0.32.0
OpenHands 0.32 adds microagent context visibility, PR template awareness, and enables context condensation by default.
└──▷ GET THIS VERSION$ git clone --branch 0.32.0 https://github.com/All-Hands-AI/OpenHands.git # already have the repo? check out this version: $ git checkout 0.32.0
- ›Displays microagent context directly in the UI so practitioners can see which microagent knowledge is active during a session.
- ›Shows edited file paths in the conversation headline for at-a-glance change tracking.
- ›Enables context condensation by default, automatically compressing long conversation histories to stay within model context limits.
- ›Expands GitLab repository listing to include repos where the user has membership but is not the owner.
- ›Supports microagent files without a required header, reducing friction when authoring custom microagents.
+3 moreshow less
- ›Adds a user-friendly UI message for content policy violation errors.
- ›Prompts the agent to follow existing PR templates when creating new pull requests.
- ›Improves event retrieval performance for conversations with a large number of events.
└──▷ BREAKING ON UPGRADE- !Condensation is now enabled by default; existing deployments that relied on full, uncompressed conversation history will have condensation applied automatically on upgrade.
- 0.31.0
OpenHands 0.31.0 adds vision-based browsing with PDF/image support, OpenHands LM integration, and multi-provider Git configuration.
└──▷ GET THIS VERSION$ git clone --branch 0.31.0 https://github.com/All-Hands-AI/OpenHands.git # already have the repo? check out this version: $ git checkout 0.31.0
└──▷ HOW TO FIND ITConfigure both GitHub and GitLab as Git providers at the same time for local OpenHands, so agents can operate across repositories on either platform.📍In the OpenHands settings UI, go to Settings › Git Providers and add credentials for both GitHub and GitLab simultaneously.- ›Enables vision-based browsing by default, allowing OpenHands to see and interpret PDFs and images rendered in the browser.
- ›Adds support for OpenHands LM as a new LLM provider option.
- ›Supports configuring multiple Git providers simultaneously (e.g., GitHub + GitLab) in local OpenHands deployments.
- ›Generates LLM-based natural-language titles for conversations automatically.
- 0.30.1
OpenHands 0.30.1 adds trajectory replay in the web app and raises the default max iterations to 250.
└──▷ GET THIS VERSION$ git clone --branch 0.30.1 https://github.com/All-Hands-AI/OpenHands.git # already have the repo? check out this version: $ git checkout 0.30.1
- ›Adds trajectory replay support in the web app, enabled via the
FEATURE_TRAJECTORY_REPLAYfeature flag. - ›Tracks accumulated token usage across a session instead of per-request token usage, giving a running total.
- ›Raises the default max iterations from the previous limit to 250, allowing agents to tackle longer tasks out of the box.
- ›Improves the startup experience for the VSCode extension integration.
- ›Adds trajectory replay support in the web app, enabled via the
- 0.30.0
OpenHands 0.30.0 adds live API cost/token display, web screenshots in headless trajectories, and auto-generated conversation titles.
└──▷ GET THIS VERSION$ git clone --branch 0.30.0 https://github.com/All-Hands-AI/OpenHands.git # already have the repo? check out this version: $ git checkout 0.30.0
- ›Displays API cost and token usage live in the frontend during agent sessions.
- ›Adds a headless-mode config option to include web screenshots in trajectories for richer audit trails.
- ›Auto-generates conversation titles from the first user message.
- ›Improved UI for interactive browser action view.
- ›Updated file explorer styles for a cleaner workspace experience.
└──▷ BREAKING ON UPGRADE- !Download workspace and download files buttons are removed; users are redirected to VS Code instead.
- !File upload functionality is removed from the UI; users are redirected to VS Code instead.
- !The continue button is removed from the UI.
- !Bash SOFT timeout is reduced from 30 to 10 seconds, which may cause previously passing long-running bash commands to time out.
- 0.29.1
OpenHands 0.29.1 adds a dedicated security microagent for security-focused autonomous tasks.
└──▷ GET THIS VERSION$ git clone --branch 0.29.1 https://github.com/All-Hands-AI/OpenHands.git # already have the repo? check out this version: $ git checkout 0.29.1
- ›Adds a security microagent, enabling OpenHands to apply security-specific reasoning and guidance during autonomous coding sessions.
- 0.29.0
OpenHands 0.29.0 adds Swift Linux microagent support and exposes microagent recall observations to the UI and LLM.
└──▷ GET THIS VERSION$ git clone --branch 0.29.0 https://github.com/All-Hands-AI/OpenHands.git # already have the repo? check out this version: $ git checkout 0.29.0
- ›Adds a Swift Linux Installation Microagent for automated Swift environment setup on Linux.
- ›Makes microagents available in the event stream as recall observations, accessible from both the UI and the LLM.
- ›Adds TestGenEval benchmark support for evaluating test generation capabilities.
- 0.28.0
OpenHands 0.28 adds Docker-in-runtime, Kubernetes cluster support, a CodeAct thinking tool, microagent templates, and JSON structured logging.
└──▷ GET THIS VERSION$ git clone --branch 0.28.0 https://github.com/All-Hands-AI/OpenHands.git # already have the repo? check out this version: $ git checkout 0.28.0
└──▷ TRY ITEnable structured JSON logs so your SIEM or log aggregator can parse OpenHands output without custom parsers.$ LOG_JSON=true docker run --rm -e LOG_JSON=true ghcr.io/all-hands-ai/openhands:0.28.0
- ›Adds sound and browser notifications for agent state changes, so practitioners are alerted when long-running tasks complete.
- ›New microagent template system lets users create properly structured domain-specific agents.
- ›Adds a 'thinking' tool to the CodeAct agent, enabling explicit reasoning steps during task execution.
- ›Enables OpenHands to run Docker inside its own runtime, unlocking containerized workflows within the agent sandbox.
- ›Enables OpenHands to start a Kubernetes cluster from within its runtime, supporting cluster-level automation tasks.
+1 moreshow less
- ›Adds structured JSON logging via the
LOG_JSONenvironment variable for improved observability and log ingestion.
└──▷ BREAKING ON UPGRADE- !The default Claude model is now
claude-3-7-sonnet-20250219(previously an older version), which may affect costs, behavior, or rate-limit quotas for deployments that rely on the default.
- 0.27.0
OpenHands 0.27 adds custom runtime support, an extended config section, and Claude 3.7 model selection.
└──▷ GET THIS VERSION$ git clone --branch 0.27.0 https://github.com/All-Hands-AI/OpenHands.git # already have the repo? check out this version: $ git checkout 0.27.0
└──▷ USE ITInject arbitrary key-value config into an OpenHands deployment without waiting for first-class support for those keys.[extended] my_custom_flag = "value" another_setting = 42
Switch the agent to Claude 3.7 when you need its extended thinking or latest capabilities.📍In the console, go to Settings › Model and select the Anthropic provider, then choose Claude 3.7 from the model list.- ›Adds an
[extended]section inconfig.tomlfor arbitrary user-defined configuration keys set on the fly. - ›Supports selecting Claude 3.7 via the Anthropic provider in model settings.
- ›Enables advanced users to define and use their own custom runtimes.
- ›Adds an
- 0.26.0
OpenHands 0.26.0 adds Daytona sandbox runtime, CLI task automation, and UI-configurable memory condensation.
└──▷ GET THIS VERSION$ git clone --branch 0.26.0 https://github.com/All-Hands-AI/OpenHands.git # already have the repo? check out this version: $ git checkout 0.26.0
└──▷ HOW TO FIND ITEnable memory condensation to keep long sessions within LLM context limits without manual intervention.📍In the console, go to Settings and enable memory condensation.- ›Adds Daytona runtime support for managing sandboxes as an alternative execution environment.
- ›Enables memory condensation configuration directly from the settings page.
- ›Supports running the CLI with a task argument for fully automated, non-interactive execution.
- ›Truncates conversation history by half (instead of failing) when the LLM context limit is reached, enabling longer sessions.
- 0.25.0
OpenHands 0.25.0 adds GitLab resolver support, multi-conversation navigation, and a redesigned Settings screen.
└──▷ GET THIS VERSION$ git clone --branch 0.25.0 https://github.com/All-Hands-AI/OpenHands.git # already have the repo? check out this version: $ git checkout 0.25.0
- ›Adds GitLab support for the OpenHands resolver, enabling automated issue and PR resolution on GitLab repositories.
- ›New multi-conversation navigation lets users switch between different conversations without losing context.
- ›Redesigned Settings screen provides an updated UI for managing configuration.
- ›Improves filtering of sensitive data from logs, reducing credential and secret exposure in log output.
- 0.24.0
OpenHands 0.24.0 adds dockerless runtime support and success/failure indicators for file operations.
└──▷ GET THIS VERSION$ git clone --branch 0.24.0 https://github.com/All-Hands-AI/OpenHands.git # already have the repo? check out this version: $ git checkout 0.24.0
- ›Adds preliminary/experimental support for running OpenHands without Docker, broadening deployment flexibility.
- ›Adds success/failure indicators for file read and edit operations, giving agents clearer feedback on action outcomes.
- ›Adds comprehensive error logging to PostHog for improved observability of agent failures.
- 0.23.0
OpenHands 0.23.0 adds o3-mini support and live LLM retry visibility with rate-limit resume.
└──▷ GET THIS VERSION$ git clone --branch 0.23.0 https://github.com/All-Hands-AI/OpenHands.git # already have the repo? check out this version: $ git checkout 0.23.0
- ›Supports OpenAI o3-mini as a selectable LLM.
- ›Shows LLM retries in real time and enables resuming sessions from a Rate-Limited state.
- 0.22.0
OpenHands 0.22.0 adds VisualWebArena evaluation support and drops the Redis dependency.
└──▷ GET THIS VERSION$ git clone --branch 0.22.0 https://github.com/All-Hands-AI/OpenHands.git # already have the repo? check out this version: $ git checkout 0.22.0
- ›Adds VisualWebArena evaluation support, enabling visual web-navigation benchmark testing within OpenHands.
- ›Removes the Redis dependency, simplifying self-hosted deployments with fewer infrastructure requirements.
- 0.21.0
OpenHands 0.21 adds trajectory replay, downloadable trajectories, multi-language UI, and a dedicated draft-editor LLM config.
└──▷ GET THIS VERSION$ git clone --branch 0.21.0 https://github.com/All-Hands-AI/OpenHands.git # already have the repo? check out this version: $ git checkout 0.21.0
└──▷ HOW TO FIND ITRoute edit-draft generation to a cheaper or faster model while keeping your primary LLM for reasoning — set thedraft_editorcustom LLM config and enable the LLM editor in agent options.📍In Settings, add a custom LLM configuration nameddraft_editorpointing to your preferred model, then enablecodeact_enable_llm_editorin the agent options.Cap compute cost on o1-family models by settingreasoning_effortto a lower tier for less complex tasks.📍In Settings › LLM, select an o1-family model and setreasoning_efforttolow(ormedium/high) to trade off reasoning depth against token cost.- ›Adds multi-language UI support, broadening accessibility for non-English practitioners.
- ›Supports the
reasoning_effortparameter for OpenAI o1-family models, giving control over model reasoning depth. - ›Introduces a
draft_editornamed custom LLM config so a separate, dedicated model can handle edit drafts independently of the primary LLM. - ›Adds trajectory replay in headless mode, enabling automated re-execution of recorded agent sessions.
- ›Adds a chat-panel button to download the current agent trajectory for offline review or auditing.
+1 moreshow less
- ›Agent now explicitly receives the cloned repo name and path when connecting to a GitHub repository, improving context awareness.
└──▷ BREAKING ON UPGRADE- !The
trajectories_pathconfig key is renamed tosave_trajectory_path; existing configurations usingtrajectories_pathwill break on upgrade.
- 0.20.0
OpenHands 0.20.0 adds a live App tab for interacting with web apps and a conversation info display.
└──▷ GET THIS VERSION$ git clone --branch 0.20.0 https://github.com/All-Hands-AI/OpenHands.git # already have the repo? check out this version: $ git checkout 0.20.0
└──▷ HOW TO FIND ITPreview and interact with a web app your agent is building without leaving the OpenHands UI.📍In the OpenHands UI, open your conversation and click the App tab (bottom panel) to view and interact with the running web app in real time.- ›Adds a new App tab (Beta) that lets users interact directly with the web app running inside OpenHands.
- ›Displays current conversation info in the bottom-right corner of the UI.
- 0.19.0
OpenHands 0.19.0 adds custom microagents in headless/CLI modes, toggleable function calling, multi-conversation support, and runtime size configuration.
└──▷ GET THIS VERSION$ git clone --branch 0.19.0 https://github.com/All-Hands-AI/OpenHands.git # already have the repo? check out this version: $ git checkout 0.19.0
- ›Supports custom microagents in headless and CLI modes, extending agent customization beyond the UI.
- ›Enables or disables function calling via user configuration, giving practitioners control over LLM tool-use behavior.
- ›Adds rate-limit error visibility in the UI and agent state, surfacing provider throttling in real time.
- ›Introduces multi-conversation feature (behind a feature flag), allowing parallel conversation management.
- ›Adds runtime size configuration, letting users tune the sandbox compute footprint per session.
└──▷ BREAKING ON UPGRADE- !Developer mode now defaults to storing data on the filesystem instead of in-memory, which changes persistence behavior for existing developer-mode deployments.
- 0.18.0
OpenHands 0.18.0 adds per-repo prompt customization, resizable panels, and server-side settings storage.
└──▷ GET THIS VERSION$ git clone --branch 0.18.0 https://github.com/All-Hands-AI/OpenHands.git # already have the repo? check out this version: $ git checkout 0.18.0
└──▷ HOW TO FIND ITCustomize the agent's system prompt for a specific repository so it follows project-specific conventions on every run.📍In your repository root, create a.openhandsdirectory and add your prompt customization files there. OpenHands will automatically detect and apply them when operating on that repo.- ›Adds
.openhandsdirectory support for customizing agent prompts on a per-repository basis. - ›Introduces a resizable and collapsible panel layout in the UI for a more flexible workspace.
- ›Enables workspace downloads on mobile and browsers lacking the Directory API.
- ›Migrates settings storage from browser localStorage to the server API, enabling persistent settings across devices and browsers.
- ›Adds navbar tooltips for improved UI discoverability.
└──▷ BREAKING ON UPGRADE- !File editing functionality has been removed from the OpenHands UI — workflows that relied on in-UI file editing must use an alternative method.
- ›Adds
- 0.17.0
OpenHands 0.17 adds custom PR titles, per-conversation URLs, and a homepage recent-conversation view.
└──▷ GET THIS VERSION$ git clone --branch 0.17.0 https://github.com/All-Hands-AI/OpenHands.git # already have the repo? check out this version: $ git checkout 0.17.0
- ›Supports custom pull request titles when using the GitHub issue resolver.
- ›Each conversation now gets its own unique URL, enabling direct linking and bookmarking.
- ›Shows the most recent conversation on the homepage for quick resumption.
- ›Adds TheAgentCompany evaluation harness for benchmarking agent performance.
- ›Settings store type is now defined in
openhands_configinstead of the main config.
└──▷ BREAKING ON UPGRADE- !Settings store type is now defined in
openhands_configrather than the main config — configurations relying on the main config for this setting will need to be updated.
- 0.16.1
OpenHands 0.16.1 adds file-by-file download with progress and backend config saving infrastructure.
└──▷ GET THIS VERSION$ git clone --branch 0.16.1 https://github.com/All-Hands-AI/OpenHands.git # already have the repo? check out this version: $ git checkout 0.16.1
- ›Adds file-by-file download with progress tracking for workspace files.
- ›Introduces infrastructure for saving configuration on the backend rather than the frontend.
- 0.16.0
OpenHands 0.16.0 updates GitHub Authentication flow.
└──▷ GET THIS VERSION$ git clone --branch 0.16.0 https://github.com/All-Hands-AI/OpenHands.git # already have the repo? check out this version: $ git checkout 0.16.0
- ›Updates GitHub Authentication integration.
- 0.15.3
OpenHands 0.15.3 raises default max_iterations to 500 and resets turn budget per user interaction
└──▷ GET THIS VERSION$ git clone --branch 0.15.3 https://github.com/All-Hands-AI/OpenHands.git # already have the repo? check out this version: $ git checkout 0.15.3
- ›Adds color coding to the 'Ran a Command' UI indicator based on command return value, making pass/fail status immediately visible.
- ›Increases default max_iterations to 500, enabling agents to tackle longer, more complex tasks before hitting the iteration limit.
- ›Measures the turn limit from the last user interaction rather than session start, giving agents a full budget after each user message.
- ›Persists jwt_secret in the config file so the secret survives service restarts without manual reconfiguration.
- 0.15.2
OpenHands 0.15.2 adds workspace-level custom MicroAgents, resolver code-review requests, and browser observations in chat.
└──▷ GET THIS VERSION$ git clone --branch 0.15.2 https://github.com/All-Hands-AI/OpenHands.git # already have the repo? check out this version: $ git checkout 0.15.2
- ›Adds support for Custom MicroAgents placed directly in the connected workspace, enabling project-specific agent behavior without global configuration.
- ›Enables the resolver to automatically request a code review from the person who initiated it after completing a PR.
- ›Surfaces browser observations (what the agent sees while web browsing) directly in the chat interface for real-time visibility.
- 0.15.1
OpenHands 0.15.1 adds command-run notifications and multiline message support in headless mode.
└──▷ GET THIS VERSION$ git clone --branch 0.15.1 https://github.com/All-Hands-AI/OpenHands.git # already have the repo? check out this version: $ git checkout 0.15.1
- ›Shows a status message in the UI each time the agent executes a command, giving real-time visibility into agent actions.
- ›Supports multiline user messages, and provides a default user message when running in headless mode.
- 0.15.0
OpenHands 0.15.0 adds SocketIO comms, BrowseURLAction in CodeAct, custom resolver sandboxes, and multi-tab session sharing.
└──▷ GET THIS VERSION$ git clone --branch 0.15.0 https://github.com/All-Hands-AI/OpenHands.git # already have the repo? check out this version: $ git checkout 0.15.0
- ›Switches underlying client-server communication to SocketIO for more robust real-time messaging.
- ›Adds
BrowseURLActionto the CodeAct agent, enabling it to navigate URLs as part of agentic workflows. - ›Adds an alignment checker for the browsing agent to verify page-interaction accuracy.
- ›Supports custom sandbox images for the GitHub issue resolver.
- ›Adds a microagent to automatically handle npm timeout issues during code execution.
+2 moreshow less
- ›Allows multiple browser tabs to connect to and share the same agent session simultaneously.
- ›Runtimes are no longer kept alive by default, reducing idle resource consumption.
└──▷ BREAKING ON UPGRADE- !Runtimes are no longer kept alive by default — existing deployments that relied on persistent runtimes between sessions will need to reconfigure this behavior explicitly.
- 0.14.3
OpenHands 0.14.3 adds a Push & Create PR button and the commit0 benchmark.
└──▷ GET THIS VERSION$ git clone --branch 0.14.3 https://github.com/All-Hands-AI/OpenHands.git # already have the repo? check out this version: $ git checkout 0.14.3
└──▷ HOW TO FIND ITAfter an agent completes its work, push the branch and open a PR without leaving the UI.📍In the OpenHands UI, after a session completes, click the Push & Create PR button to push the current branch and create a pull request in your connected repository.- ›New Push & Create PR UI button lets users push changes and open a pull request directly from the OpenHands interface.
- ›Adds the commit0 benchmark for evaluating agent performance.
- ›Server process now runs at highest system priority, improving responsiveness under load.
- 0.14.1
OpenHands 0.14.1 adds a push-to-GitHub button directly in the chat interface.
└──▷ GET THIS VERSION$ git clone --branch 0.14.1 https://github.com/All-Hands-AI/OpenHands.git # already have the repo? check out this version: $ git checkout 0.14.1
└──▷ HOW TO FIND ITAfter completing a coding task in a session, push your changes to GitHub without leaving the chat interface.📍In the chat interface, click the 'Push to GitHub' button to push your current changes to the configured GitHub repository.- ›Adds a 'Push to GitHub' action button in the chat interface for pushing changes directly from a session.
- 0.14.0
OpenHands 0.14.0 adds an embedded VSCode editor, GitHub issue resolver integration, and universal function-calling shim for non-native LLMs.
└──▷ GET THIS VERSION$ git clone --branch 0.14.0 https://github.com/All-Hands-AI/OpenHands.git # already have the repo? check out this version: $ git checkout 0.14.0
└──▷ HOW TO FIND ITOpen the embedded VSCode editor from within the OpenHands UI to inspect and edit agent-modified files without leaving the interface.📍In the OpenHands UI, open an active session and click the VSCode panel to launch the integrated editor against the running runtime.- ›Adds a full VSCode editor directly inside the OpenHands runtime and UI, giving agents and users an integrated code editing experience.
- ›Integrates the OpenHands resolver into the main repository, enabling automated GitHub issue resolution workflows natively.
- ›Adds a utility that automatically converts function-calling LLM requests to non-function-calling format, broadening compatible model support.
- 0.13.1
OpenHands 0.13.1 adds workspace media previews and improved GitHub push support.
└──▷ GET THIS VERSION$ git clone --branch 0.13.1 https://github.com/All-Hands-AI/OpenHands.git # already have the repo? check out this version: $ git checkout 0.13.1
- ›Supports displaying images, videos, and PDFs directly in the workspace UI.
- ›Improves pushing changes to GitHub from within a session.
- 0.13.0
OpenHands 0.13.0 adds drag-and-drop image input to chat and a loading indicator for ZIP downloads.
└──▷ GET THIS VERSION$ git clone --branch 0.13.0 https://github.com/All-Hands-AI/OpenHands.git # already have the repo? check out this version: $ git checkout 0.13.0
- ›Supports dragging images directly into the chat input for multimodal interactions.
- ›Shows a loading indicator when downloading a workspace ZIP file.
- ›New empty-state design for the chat interface.
- 0.12.2
OpenHands 0.12.2 gives CodeAct native web browsing, adds PostHog analytics, and integrates DiscoveryBench.
└──▷ GET THIS VERSION$ git clone --branch 0.12.2 https://github.com/All-Hands-AI/OpenHands.git # already have the repo? check out this version: $ git checkout 0.12.2
- ›Adds PostHog analytics integration for tracking usage and agent behavior.
- ›Enables CodeAct agent to perform web browsing natively — no longer delegates to a separate BrowsingAgent.
- ›Adds DiscoveryBench integration for benchmarking OpenHands agents on data-discovery tasks.
- 0.12.0
OpenHands 0.12.0 adds function calling to CodeAct 2.1 and prompt caching for Claude 3.5 Sonnet, hitting 53% on SWE-Bench Verified.
└──▷ GET THIS VERSION$ git clone --branch 0.12.0 https://github.com/All-Hands-AI/OpenHands.git # already have the repo? check out this version: $ git checkout 0.12.0
- ›Adds function calling support to the CodeAct 2.1 agent, boosting benchmark performance to 53% on SWE-Bench Verified and 41.7% on SWE-Bench Lite — the highest score among open-source AI software engineering systems.
- ›Supports prompt caching for
claude-3-5-sonnet-20241022, reducing latency and cost on repeated context. - ›Surfaces backend error messages directly in the chat UI so practitioners see failure details without digging through logs.
- 0.11.0
OpenHands 0.11.0 improves LLM-powered agent file editing.
└──▷ GET THIS VERSION$ git clone --branch 0.11.0 https://github.com/All-Hands-AI/OpenHands.git # already have the repo? check out this version: $ git checkout 0.11.0
- ›Improves agent file editing quality using LLM-based refinements.
- 0.10.0
OpenHands 0.10.0 ships a redesigned UI and adds Modal as a new sandbox runtime.
└──▷ GET THIS VERSION$ git clone --branch 0.10.0 https://github.com/All-Hands-AI/OpenHands.git # already have the repo? check out this version: $ git checkout 0.10.0
- ›New OpenHands UI with a redesigned interface for interacting with agents.
- ›Adds Modal sandbox support as an alternative runtime backend for agent execution.
- 0.9.8
OpenHands 0.9.8 lets you specify a custom config.toml path via command-line arguments.
└──▷ GET THIS VERSION$ git clone --branch 0.9.8 https://github.com/All-Hands-AI/OpenHands.git # already have the repo? check out this version: $ git checkout 0.9.8
- ›Supports specifying the
config.tomllocation via command-line arguments, enabling flexible multi-environment deployments.
- ›Supports specifying the
- 0.9.5
OpenHands 0.9.5 adds more granular startup status messages in the UI.
└──▷ GET THIS VERSION$ git clone --branch 0.9.5 https://github.com/All-Hands-AI/OpenHands.git # already have the repo? check out this version: $ git checkout 0.9.5
- ›Displays more granular status messages in the UI during agent startup, giving practitioners better visibility into initialization progress.
- 0.9.4
OpenHands 0.9.4 adds a
--versionflag to the CLI and reduces Gemini safety thresholds.└──▷ GET THIS VERSION$ git clone --branch 0.9.4 https://github.com/All-Hands-AI/OpenHands.git # already have the repo? check out this version: $ git checkout 0.9.4
- ›Adds
--versionflag to the OpenHands CLI for quick version inspection. - ›Reduces safety thresholds for Gemini models, enabling broader task execution with Gemini backends.
- ›Adds
- 0.9.3
OpenHands 0.9.3 adds interactive command support and a redesigned settings modal.
└──▷ GET THIS VERSION$ git clone --branch 0.9.3 https://github.com/All-Hands-AI/OpenHands.git # already have the repo? check out this version: $ git checkout 0.9.3
- ›Supports interactive terminal commands, enabling agents to handle prompts that require user input mid-execution.
- ›Redesigned settings modal with an updated UI for configuring the service.
- ›Makes prompt caching opt-in rather than enabled by default, giving users explicit control over caching behavior.
└──▷ BREAKING ON UPGRADE- !Prompt caching is no longer enabled by default; users who relied on it must explicitly opt in after upgrading.
- 0.9.1
OpenHands 0.9.1 adds a CLI mode, prompt caching for Sonnet/Haiku, and specialized micro agents for CodeAct.
└──▷ GET THIS VERSION$ git clone --branch 0.9.1 https://github.com/All-Hands-AI/OpenHands.git # already have the repo? check out this version: $ git checkout 0.9.1
- ›Adds CLI mode, enabling OpenHands to be driven from the command line without the web UI.
- ›Adds prompt caching to CodeActAgent for Anthropic Sonnet and Haiku models, reducing latency and token costs on repeated context.
- ›Introduces micro agents as specializations of CodeAct, allowing targeted agent behaviors for specific tasks.
- ›Improves model selection UI in settings for easier LLM configuration.
- 0.9.0
OpenHands 0.9.0 adds vision LLM support, a Security Analyzer, async LLM calls, and switches to EventStream Runtime by default.
└──▷ GET THIS VERSION$ git clone --branch 0.9.0 https://github.com/All-Hands-AI/OpenHands.git # already have the repo? check out this version: $ git checkout 0.9.0
- ›Adds vision input support for LLMs with vision capabilities, enabling image-aware agent interactions.
- ›Adds a Security Analyzer functionality for automated security review workflows.
- ›Enhances the LLM class with async support for non-blocking model calls.
- ›Implements
copy_tofor Runtime, allowing files to be pushed directly into the agent's runtime environment. - ›Supports injecting additional dependencies into the OpenHands runtime Docker image at launch.
+7 moreshow less
- ›Switches the default runtime to EventStream Runtime.
- ›Clears conversation history at the start of each new task to avoid context bleed between sessions.
- ›Adds collapsible resizers in the UI for a more flexible workspace layout.
- ›Integrates the Aider Benchmark for agent evaluation.
- ›Agents can now accept per-agent configuration via agent config, enabling fine-grained control.
- ›Adds warning messages when a config file contains unknown keys, helping catch misconfiguration early.
- ›Adds error observations to the CodeAct SWE agent so it can recover from execution failures.
└──▷ BREAKING ON UPGRADE- !The project is renamed from OpenDevin to OpenHands — any references to the old name in configs, Docker images, or scripts will need updating.
- !The default runtime is now EventStream Runtime instead of the previous default — existing setups relying on the old default runtime behavior may behave differently without explicit configuration.
- 0.8.3
OpenHands 0.8.3 adds a UI toggle for agent selection and Dev Container support for GitHub Codespaces.
└──▷ GET THIS VERSION$ git clone --branch 0.8.3 https://github.com/All-Hands-AI/OpenHands.git # already have the repo? check out this version: $ git checkout 0.8.3
- ›Adds a UI toggle to enable or disable agent selection (defaults to off, hiding agent selection from end users).
- ›Adds Dev Container configuration for GitHub Codespaces, enabling one-click cloud development environments.
- 0.8.2
OpenHands 0.8.2 adds headless controller mode and SWE-Bench custom Docker namespace support for eval workflows.
└──▷ GET THIS VERSION$ git clone --branch 0.8.2 https://github.com/All-Hands-AI/OpenHands.git # already have the repo? check out this version: $ git checkout 0.8.2
- ›Adds
headless_modefor the Controller, enabling programmatic agent runs without a UI session. - ›Supports pulling SWE-Bench evaluation environments from a custom Docker namespace.
- ›Shrinks the runtime image size, reducing pull times and storage overhead.
└──▷ BREAKING ON UPGRADE- !The Monologue agent has been removed and is no longer available as an agent type.
- !Global config has been removed from the sandbox, agent controller, and related components — configurations previously set globally must now be passed explicitly.
- ›Adds
- 0.8.0
OpenHands 0.8.0 adds user confirmation mode, per-agent LLM config, EventStream runtime with browser and Jupyter support, and restores
append_file.└──▷ GET THIS VERSION$ git clone --branch 0.8.0 https://github.com/All-Hands-AI/OpenHands.git # already have the repo? check out this version: $ git checkout 0.8.0
- ›Adds
append_fileaction back to the agent's file-editing toolkit, enabling agents to append content to files without overwriting them. - ›Implements user confirmation mode: when enabled, OpenHands requests explicit user confirmation before executing bash or Python code.
- ›Enables per-agent LLM configuration, allowing each delegated agent to use a distinct LLM config set from the UI.
- ›Introduces
EventStreamRuntimewith an agnostic sandbox, adding Jupyter notebook support and browser interaction to the runtime client. - ›Adds a WebSocket runtime (
od-client-runtime) as a new runtime backend option.
+3 moreshow less
- ›Displays real-time build logs for the agnostic sandbox image during construction.
- ›Deprecates the
recallaction andsearch_memorycapability, removing them from the agent action surface. - ›Removes support for Background Commands from the runtime architecture.
└──▷ BREAKING ON UPGRADE- !Background Commands are no longer supported — any working setup relying on background command execution will break on upgrade.
- !The
recallaction andsearch_memoryare deprecated and removed — agents or configurations invoking these will break on upgrade.
- ›Adds
- 0.7.1
OpenHands 0.7.1 adds local Ollama model support, CLI session restore, config templates, and DEBUG logging control.
└──▷ GET THIS VERSION$ git clone --branch 0.7.1 https://github.com/All-Hands-AI/OpenHands.git # already have the repo? check out this version: $ git checkout 0.7.1
- ›Adds
make run-wsltarget for running OpenHands under Windows Subsystem for Linux. - ›Enables DEBUG-level logging via a config setting, giving operators fine-grained log control without code changes.
- ›Adds a config template feature to bootstrap new configuration files.
- ›Adds support for local Ollama models, letting teams run inference entirely on-premises without an external LLM provider.
- ›Adds optional CLI session restore, allowing interrupted CLI sessions to be resumed.
+7 moreshow less
- ›Enables concurrent CLI operation, improving throughput for command-line workflows.
- ›Removes the
MAX_CHARStraffic-control limit, lifting a cap on observation size. - ›Allows
MAX_ITERATIONSandMAX_BUDGET_PER_TASKto be overridden directly from the web GUI. - ›Improves code editing in the CodeAct agent by using
diff-basedpatching for more reliable file edits. - ›Removes the Docker exec sandbox backend, consolidating on the SSH-based sandbox.
- ›Adds automatic LLM retry on internal server errors, improving resilience against transient upstream failures.
- ›Docker builds for stable releases now also publish a
latesttag, simplifying image pulls.
└──▷ BREAKING ON UPGRADE- !The Docker exec sandbox box has been removed; deployments relying on it must migrate to the SSH-based sandbox.
- !The
MAX_CHARStraffic-control setting has been removed; any configuration referencing it will no longer have effect. - !Global CLI arguments have been removed; workflows depending on those global args must be updated.
- ›Adds
- 0.7.0
OpenHands 0.7.0 adds WebArena, MiniWoB++, GPQA, ToolQA, Gorilla APIBench, and BioCoder benchmarks plus CodeActAgent browser delegation.
└──▷ GET THIS VERSION$ git clone --branch 0.7.0 https://github.com/All-Hands-AI/OpenHands.git # already have the repo? check out this version: $ git checkout 0.7.0
- ›Renames the
OPENDEVIN_WORKSPACEenvironment variable toWORKSPACE_BASEacross the codebase. - ›Adds
append_fileskill to agentskills, enabling agents to append content to files. - ›Adds WebArena and MiniWoB++ benchmark support with related architecture changes for browser-based evaluation.
- ›Adds GPQA benchmark evaluation support.
- ›Adds ToolQA benchmark support.
+8 moreshow less
- ›Adds Gorilla APIBench benchmark support.
- ›Adds BioCoder benchmark integration.
- ›Adds SWE-Bench Docker-based evaluation (SWEBench-docker eval).
- ›Enables
CodeActAgentto delegate browser tasks toBrowsingAgent, allowing the code agent to hand off web interactions to a specialized sub-agent. - ›Revamps
AgentRejectActionand enablesManagerAgentto handle task rejections gracefully. - ›Adds evaluation time-travel capability, allowing benchmark evaluation to target a specific historical version of the codebase.
- ›Makes plugin sandbox Dockerfile sandbox-agnostic, broadening deployment flexibility.
- ›Adjusts the stuck-step detection threshold to 3 consecutive identical steps before halting.
└──▷ BREAKING ON UPGRADE- !The
OPENDEVIN_WORKSPACEenvironment variable is renamed toWORKSPACE_BASE; existing configurations referencingOPENDEVIN_WORKSPACEwill no longer be recognized. - !The
github-tokenconfig key is removed; configurations using it will no longer work.
- ›Renames the