Heads up This site is currently under heavy development.
← all tools
◆ Local LLM Runtimes

Jan

v0.8.4 open-source

Jan is an open source alternative to ChatGPT that runs 100% offline on your computer.

source ↗ website ↗ rss ↗ last repo push Aug 20, 2026

Summary

Jan is an open-source desktop application that allows running local large language models with full control and privacy. It is available across major platforms, requiring only a direct download or store installation for setup. It is aimed at users interested in local-inference llm cyber tool(s), positioning itself as an accessible alternative to services like ChatGPT. The project maintains continuous presence with clear download links available.

Jan is an open source alternative to ChatGPT that runs 100% offline on your computer.

What Jan answers

What platforms does it support for setup?

direct download or store installation

What types of models can it run?

local large language models

What control does it offer over running LLMs?

full control and privacy

What is the primary way to start using it?

direct download or store installation

How is the setup process described?

through official platform badges or specific downloads

What is the general availability of the tool?

open-source and accessible via clear download links

Release history

  1. v0.8.4 Jul 23, 2026 · issue -027

    Jan v0.8.4 adds an OpenAI-compatible gateway, Responses API, native web search, and migrates credentials to the OS keyring.

    └──▷ GET THIS VERSION
    $ git clone --branch v0.8.4 https://github.com/janhq/jan.git
# already have the repo? check out this version:
$ git checkout v0.8.4
    • ›Adds an OpenAI-compatible translating gateway, OpenAI Responses API support, and unified reasoning across providers.
    • ›Moves provider settings and API keys from localStorage to a backend-managed store, with secrets written to the OS keyring — existing data is migrated automatically on first launch.
    • ›Adds native web_search/web_fetch capability via tauri-plugin-websearch.
    • ›Adds per-model chat template kwargs for llama.cpp models.
    • ›Adds a toggle for folding interim text into the reasoning trace in chat.
    +3 moreshow less
    • ›Adds API key rotation support for Gemini.
    • ›Adds a token counter for remote and MLX providers.
    • ›Bundles built-in extensions into the app binary.
    └──▷ BREAKING ON UPGRADE
    • !Settings and credentials are now read from and written to the backend store (OS keyring for secrets) instead of the webview localStorage. Downgrading to a pre-0.8.4 build will revert to the older localStorage snapshot, not any settings changed in 0.8.4+.
  2. v0.8.4 Jul 23, 2026 · issue 002

    Jan v0.8.4 adds an OpenAI-compatible translating gateway, Responses API, native web search, per-model chat template kwargs, and migrates credentials to the OS keyring.

    └──▷ GET THIS VERSION
    $ git clone --branch v0.8.4 https://github.com/janhq/jan.git
# already have the repo? check out this version:
$ git checkout v0.8.4
    • ›Adds an OpenAI-compatible translating gateway, Responses API support, and unified reasoning — enabling Jan to front-end any OpenAI-compatible backend with response translation.
    • ›Adds native web_search / web_fetch capabilities via tauri-plugin-websearch, bringing built-in web search to the desktop app without external tooling.
    • ›Adds per-model chat template kwargs for llama.cpp models, allowing fine-grained control over how prompts are formatted per model.
    • ›Adds API key rotation for Gemini, so Gemini provider credentials can now be cycled without reconfiguring the full provider.
    • ›Adds a token counter for remote and MLX providers, surfacing token usage in chat for non-local inference backends.
    +3 moreshow less
    • ›Adds a toggle for folding interim text into the reasoning trace in chat, letting users collapse chain-of-thought output into the reasoning block.
    • ›Moves provider settings and credentials from the webview's localStorage to a backend-managed store, with secrets persisted to the OS keyring — existing settings and API keys are migrated automatically on first launch.
    • ›Bundles built-in extensions directly into the app binary, removing the need to fetch them separately at runtime.
    └──▷ BREAKING ON UPGRADE
    • !Provider settings and credentials are now read from and written to the backend store (secrets in the OS keyring) instead of localStorage. After upgrading to v0.8.4, any new changes are saved only to the backend store; downgrading to a pre-0.8.4 build will show the older localStorage snapshot, not settings changed in v0.8.4+.
  3. v0.8.2 Jun 1, 2026 · issue -079

    Jan v0.8.2 adds AMD ROCm/HIP backend, pauseable downloads, and an automatic-update toggle

    └──▷ GET THIS VERSION
    $ git clone --branch v0.8.2 https://github.com/janhq/jan.git
# already have the repo? check out this version:
$ git checkout v0.8.2
    • ›Adds HIP (AMD ROCm) backend support for llamacpp, enabling GPU-accelerated local inference on AMD hardware.
    • ›Adds a toggle in Settings to enable or disable the automatic app update check.
    • ›Adds copy and reveal buttons to API key input fields in the Providers settings.
    • ›Adds pause and resume controls for model downloads from the hub panel.
    • ›Adds a branded startup loader with phased status messages; defers MCP initialization until after first paint.
  4. v0.8.1 May 29, 2026 · issue -082

    Jan v0.8.1 adds Italian localization to the desktop UI.

    └──▷ GET THIS VERSION
    $ git clone --branch v0.8.1 https://github.com/janhq/jan.git
# already have the repo? check out this version:
$ git checkout v0.8.1
    • ›Adds Italian language translation to the Jan desktop interface.
  5. v0.8.0 May 22, 2026 · issue -089

    Jan v0.8.0 adds MiniMax cloud provider, /v1/orchestrations MCP API, Chain of Thought, API key rotation, and a Rust-native inference backend.

    └──▷ GET THIS VERSION
    $ git clone --branch v0.8.0 https://github.com/janhq/jan.git
# already have the repo? check out this version:
$ git checkout v0.8.0
    └──▷ TRY IT
    Trigger server-side MCP tool orchestration without relying on the client — useful for headless or API-only deployments.
    $ curl -X POST http://localhost:1337/v1/orchestrations \
  -H 'Content-Type: application/json' \
  -d '{"model": "gpt-4o", "messages": [{"role": "user", "content": "Search the web for the latest CVEs in OpenSSL."}]}'
    Enable server-side tool execution for /chat/completions via the Jan GUI so MCP tools run on the server rather than requiring client approval each call.
    📍In the Jan GUI, go to Settings › Connectors, select your MCP server, and toggle 'Server-side tool execution' on.
    • ›Adds /v1/orchestrations API endpoint for server-side MCP tool execution.
    • ›Adds GUI toggle for server-side tool execution on /chat/completions.
    • ›Adds optional lightweight router model for MCP tool routing, with routing telemetry.
    • ›Adds feat(llamacpp): expands llama.cpp server flags and wires llama.cpp-only sampling parameters.
    • ›Adds MiniMax as a predefined cloud provider with M2.7 as the default model.
    +18 moreshow less
    • ›Adds configurable token limits and auto-compact for remote model providers.
    • ›Adds API key fallbacks with automatic rotation across remote model providers.
    • ›Adds options to preserve user data during a factory reset.
    • ›Moves backend download and management logic to a Rust plugin with dependency verification.
    • ›Implements initial Chain of Thought (CoT) display for reasoning-capable models.
    • ›Adds paragraph-level 'Edit with AI' for assistant markdown responses.
    • ›Adds auto-summarize of thread titles after the first response, with cancellable background inference.
    • ›Adds message queuing during streaming with auto-send, two-stage stop, and editable pending chips in the input area.
    • ›Stores all user settings in local files instead of browser localStorage.
    • ›Splits the provider list into local and remote sections in the UI.
    • ›Adds an assistant chat button to start conversations directly from an assistant.
    • ›Adds optional health-check auto-restart for crashed model sessions.
    • ›Adds a regenerate button on failed message responses.
    • ›Adds a file attachment progress bar.
    • ›Expands supported file types for document attachments to include many additional extensions.
    • ›Adds Korean, Catalan, Hindi language localizations.
    • ›Renames MCP to 'Connectors' in the Settings sidebar.
    • ›Allows retrieving the last typed message by pressing the up arrow key.
  6. v0.7.9 Mar 23, 2026 · issue -149

    Jan v0.7.9 adds NVIDIA NIM cloud provider, Spanish locale, expanded file attachments, and auto-scaling context length

    └──▷ GET THIS VERSION
    $ git clone --branch v0.7.9 https://github.com/janhq/jan.git
# already have the repo? check out this version:
$ git checkout v0.7.9
    • ›Adds setting to auto-increase ctx_len when the context window fills up, preventing truncation without manual tuning.
    • ›Removes the 32k ctx_len enforcement that was previously applied on API server start, allowing models to use their native context limits.
    • ›Adds NVIDIA NIM as a predefined cloud provider in the model hub.
    • ›Adds a configurable default model for the local API server.
    • ›Adds a default assistant setting, letting users pin a preferred assistant across sessions.
    +4 moreshow less
    • ›Expands supported file types for document attachments in chat.
    • ›Adds Spanish (Español) locale to the UI.
    • ›Adds safer directory scoping during factory reset to protect user data outside Jan's managed folders.
    • ›Enables remote model updates so model metadata can be refreshed without a full app update.
  7. v0.7.8 Mar 11, 2026 · issue -160

    Jan v0.7.8 adds xAI provider, OpenClaw agent integration, a Jan CLI, and dynamic context allocation.

    └──▷ GET THIS VERSION
    $ git clone --branch v0.7.8 https://github.com/janhq/jan.git
# already have the repo? check out this version:
$ git checkout v0.7.8
    • ›Adds xAI as a new model provider, expanding the roster of supported remote inference backends.
    • ›Integrates OpenClaw, an agent framework, including sandbox config isolation, an agent mode toggle, quality-of-life keyboard shortcuts, Docker validation on Windows and Linux, and a pre-installed Bun runtime replacing all Node/npm dependencies.
    • ›Introduces a Jan CLI (jan-cli) shipped alongside the desktop app, including in the Windows NSIS installer as jan-cli.exe.
    • ›Jan now manages context allocation dynamically, automatically sizing context windows based on available resources rather than requiring manual configuration.
    • ›Adds a refreshed starter screen and updated download management UI for the initial model setup flow.
    +1 moreshow less
    • ›Improves the settings panel with better organization and expanded model provider options.
  8. v0.7.7 Feb 11, 2026 · issue -187

    Jan v0.7.7 adds MLX backend for Apple Silicon, Exa MCP search, vision model prompts, and local API server improvements.

    └──▷ GET THIS VERSION
    $ git clone --branch v0.7.7 https://github.com/janhq/jan.git
# already have the repo? check out this version:
$ git checkout v0.7.7
    • ›Adds new MLX backend for running inference natively on Apple Silicon Macs.
    • ›Adds streamable HTTP Exa default search MCP integration.
    • ›Adds prompt to download the Jan VL model when vision capability is needed.
    • ›Adds 'delete all threads' action inside projects.
    • ›Implements auto-fit settings in the llama.cpp extension to automatically size models to available resources, replacing the previous model planner.
    +3 moreshow less
    • ›Improves local API server with a revamped UI and stream transform support.
    • ›Revamps the overall application layout.
    • ›Displays embedding models in settings with visual distinction from generative models.
  9. v0.7.6 Jan 27, 2026 · issue -202

    Jan v0.7.6 adds message editing, Anthropic Messages API proxy, search dialog, token usage persistence, and a portable Windows build.

    └──▷ GET THIS VERSION
    $ git clone --branch v0.7.6 https://github.com/janhq/jan.git
# already have the repo? check out this version:
$ git checkout v0.7.6
    • ›Enables proxy to llama.cpp for Anthropic Messages API support, allowing local inference to be addressed via the Anthropic Messages API format.
    • ›Persists token usage into message metadata so per-message token counts are retained across sessions.
    • ›Adds a search dialog for quickly navigating conversations and content within the app.
    • ›Adds a portable Windows build for running Jan without installation.
    • ›Adds the ability to edit and delete chat messages directly in the conversation UI.
    +6 moreshow less
    • ›Improves sidebar UI with distinct sections and better empty states.
    • ›Improves toast messages and error notifications for clearer in-app feedback.
    • ›Adds Polish metainfo translation and completes Czech translations, extending localization coverage.
    • ›Combines attachments into a unified icon for a cleaner chat input UI.
    • ›Disables auto-updater in the Flatpak distribution.
    • ›Easier installation on ARM platforms.
  10. v0.7.4 Dec 5, 2025 · issue -255

    Jan v0.7.4 adds CUDA 13 support, a browser MCP tool, desktop file attachments, and a quick-start model flow.

    └──▷ GET THIS VERSION
    $ git clone --branch v0.7.4 https://github.com/janhq/jan.git
# already have the repo? check out this version:
$ git checkout v0.7.4
    • ›Adds an embedding flag to model metadata with automatic detection, allowing Jan to identify and handle embedding models without manual classification.
    • ›Adds CUDA 13 backend support, with CUDA 13 set as a priority backend for GPU inference.
    • ›Adds an official Jan browser MCP (Model Context Protocol) integration, accessible as a chat input shortcut, enabling web browsing capabilities directly from the chat interface.
    • ›Moves proactive mode configuration into MCP settings for centralised control of agentic behaviour.
    • ›Adds a lockfile mechanism to kill conflicting MCP server port usage, preventing port collision errors.
    +10 moreshow less
    • ›Adds a cancellation mechanism during MCP connectivity checks, allowing users to abort hung connection attempts.
    • ›Enables desktop file attachments, letting users attach local files directly in conversations.
    • ›Adds a quick-start flow to begin chatting with a Jan model immediately without manual setup.
    • ›Adds a dialog to install the Jan browser extension from within the app, with an updated link to the Chrome Web Store.
    • ›Migrates the assistant configuration screen into the Settings panel.
    • ›Adds Czech locale support and completes missing translations across all supported locales.
    • ›Updates the Flatpak build for Linux distribution via Flathub.
    • ›Adds backend migration mapping to handle transitions between inference backends.
    • ›Closes the app to the background instead of quitting on window close.
    • ›Adds search instructions to the system prompt to guide the assistant on when to invoke web search.
  11. v0.7.3 Nov 13, 2025 · issue -277

    Jan v0.7.3 adds mobile MVP, file attachments, proactive mode, browser MCP, and new localization support.

    └──▷ GET THIS VERSION
    $ git clone --branch v0.7.3 https://github.com/janhq/jan.git
# already have the repo? check out this version:
$ git checkout v0.7.3
    • ›Adds llamacpp MoE (Mixture-of-Experts) offloading setting, enabling larger MoE models to be partially offloaded to GPU.
    • ›Adds configurable timeout for llamacpp connections.
    • ›Adds official Jan browser MCP integration.
    • ›Adds backend migration mapping and updated backend handling.
    • ›Adds file attachment support in chat input.
    +11 moreshow less
    • ›Adds 'Proactive mode' for AI interactions.
    • ›Adds ability to continue an AI response after interrupting it.
    • ›Enables typing a new prompt while waiting for an AI response.
    • ›Adds support for multimodal tool results and improved tool message handling.
    • ›Adds a loader screen before the frontend loads.
    • ›Adds web temporary chat mode.
    • ›Adds search button for extensions in the web interface.
    • ›Adds Japanese, Brazilian Portuguese, French, and Russian localizations.
    • ›Delivers Jan mobile MVP with persistence store, backend integration, and platform-specific build configurations.
    • ›Shows supported file types in the file picker UI.
    • ›Supports two configurable scroll behaviors in chat.
  12. v0.7.0 Oct 2, 2025 · issue -318

    Jan v0.7.0 adds MCP support for web, Azure as a first-class provider, Swagger UI for the API server, thread folders, and an MSI installer.

    └──▷ GET THIS VERSION
    $ git clone --branch v0.7.0 https://github.com/janhq/jan.git
# already have the repo? check out this version:
$ git checkout v0.7.0
    • ›Adds configurable model response timeout for the local API server.
    • ›Adds Swagger UI for the Jan local API server, making the OpenAPI spec browsable and testable in-browser.
    • ›Adds getTokensCount method to compute token usage.
    • ›Adds .zip archive support for manual llama.cpp backend installation.
    • ›Adds Azure as a first-class provider alongside existing remote providers.
    +13 moreshow less
    • ›Adds MCP (Model Context Protocol) support for the Jan web interface.
    • ›Adds Exa MCP server as a built-in MCP integration.
    • ›Adds authentication with Google Auth provider for Jan web.
    • ›Adds thread organization into folders for managing conversation history.
    • ›Adds MSI installer option for Windows.
    • ›Adds model selector that fetches available models from v1/models when configuring a provider.
    • ›Adds custom downloaded model naming.
    • ›Adds prompt-progress indicator during streaming responses.
    • ›Enables vision capability for remote providers.
    • ›Adds LaTeX fragment normalization in markdown rendering.
    • ›Adds system tray icon build flag for desktop builds.
    • ›Adjusts RAM/VRAM calculation for unified memory systems (Apple Silicon and similar).
    • ›Adds web remote conversation support, syncing threads across devices on Jan web.
  13. v0.6.10 Sep 18, 2025 · issue -332

    Jan v0.6.10 ships a web UI, smart model management, mmproj import, API key visibility, and CDN fallback for llama.cpp.

    └──▷ GET THIS VERSION
    $ git clone --branch v0.6.10 https://github.com/janhq/jan.git
# already have the repo? check out this version:
$ git checkout v0.6.10
    • ›Adds Jan Web — a browser-based version of Jan that reuses the Jan Desktop UI and can load Jan models directly.
    • ›Adds the ability to view the API key in the UI while the local server is running.
    • ›Allows importing models that include an mmproj file (multimodal projection), enabling vision-capable local model workflows.
    • ›Introduces smart model management to automatically handle model selection and compatibility.
    • ›Adds CDN fallback for llama.cpp backend downloads when the primary source fails.
    +3 moreshow less
    • ›Enhances llama.cpp backend management and installation, including better memory suitability checks and out-of-memory error detection.
    • ›Adds copy-to-clipboard for MCP (Model Control Plane) permissions in the UI.
    • ›Labels the 'optimize' setting as experimental in the UI.
  14. v0.6.9 Aug 28, 2025 · issue -353

    Jan v0.6.9 adds mmproj/vision model support, MCP enhancements, GGUF validation, model favorites, and Polish localization.

    └──▷ GET THIS VERSION
    $ git clone --branch v0.6.9 https://github.com/janhq/jan.git
# already have the repo? check out this version:
$ git checkout v0.6.9
    └──▷ HOW TO FIND IT
    Cap MCP tool-call retries to avoid infinite loops when an MCP server misbehaves.
    📍In Jan, go to Settings › MCP Servers, open a server entry, and set 'Max Attempt' to your desired limit (e.g. 3) before saving.
    Start the local API server automatically every time Jan launches, without manual intervention.
    📍In Jan, go to Settings › Local API Server and enable the 'Run on startup' toggle.
    Load a vision-capable local model by pairing it with its mmproj file so image inputs are processed correctly.
    📍In Jan, open the Hub, select a model that shows the vision icon, and import the corresponding mmproj model file when prompted during setup.
    • ›Adds support for passing the API key via environment variable instead of as a command-line argument for llama.cpp.
    • ›Adds support for custom environment variables for llama.cpp, enabling fine-grained runtime configuration.
    • ›Adds max_attempt setting for MCP to cap tool-call loops and prevent runaway execution.
    • ›Adds a 'run on startup' setting for the local API server so it launches automatically with the app.
    • ›Adds support for mmproj (multimodal projection) models, enabling vision/image capabilities in local inference.
    +13 moreshow less
    • ›Adds GGUF metadata reading, file-size validation, and SHA-256 hash validation before loading models.
    • ›Adds model compatibility check and memory estimation so users know before loading whether a model will fit in available RAM/VRAM.
    • ›Adds reasoning field support for OpenRouter-connected models.
    • ›Adds MCP server error handling with structured feedback in the UI.
    • ›Adds tool-call cancellation, letting users stop an in-flight MCP tool call mid-run.
    • ›Adds auto-detection of model tool-use capability so users no longer need to configure it manually.
    • ›Adds support for inserting the current date into the assistant system prompt.
    • ›Adds CPU architecture detection at runtime to select the correct backend binary automatically.
    • ›Adds an attachment UI for including files in conversations.
    • ›Adds a vision indicator icon in the Hub model list so multimodal models are visually identified.
    • ›Adds the ability for users to mark models as favorites.
    • ›Adds Polish language translation.
    • ›Adds Flatpak packaging, making Jan distributable via Flathub on Linux.
  15. v0.6.8 Aug 14, 2025 · issue -363

    Jan v0.6.8 adds per-model Jinja templates, tensor buffer type overrides, and AVX2 checks for Intel Mac MCP support.

    └──▷ GET THIS VERSION
    $ git clone --branch v0.6.8 https://github.com/janhq/jan.git
# already have the repo? check out this version:
$ git checkout v0.6.8
    • ›Adds per-model Jinja template customization, allowing chat templates to be set at the model level rather than only at the provider level.
    • ›Adds support for overriding tensor buffer type in llama.cpp settings.
    • ›Adds AVX2 instruction support check for MCP on macOS with Intel CPUs, blocking unsupported configurations before they fail.
    • ›Adds 'recommended' labels to llama.cpp settings to guide users toward optimal configuration choices.
    • ›Introduces structured error handling for the llama.cpp extension, surfacing more actionable error messages.
    +1 moreshow less
    • ›Improves llama.cpp argument handling with device parsing, including conditional Vulkan support checks for better GPU compatibility.
  16. v0.6.6 Jul 31, 2025 · issue -364

    Jan v0.6.6 adds Hugging Face as a provider, Claude 4 models, per-model llama.cpp overrides, and backend device querying.

    └──▷ GET THIS VERSION
    $ git clone --branch v0.6.6 https://github.com/janhq/jan.git
# already have the repo? check out this version:
$ git checkout v0.6.6
    • ›Adds RunEvent::Exit event in Tauri to handle macOS context-menu exit.
    • ›Adds support for querying available backend devices.
    • ›Adds per-model overrides in llama.cpp load().
    • ›Adds Hugging Face as a built-in, non-deletable provider.
    • ›Adds Claude 4 model support.
    +7 moreshow less
    • ›Adds proxy support for the new downloader.
    • ›Enhances port selection with availability check before binding.
    • ›Enhances llama.cpp backend management with persistence (settings survive restarts).
    • ›Adds vcruntime to the Windows installer to satisfy runtime dependencies.
    • ›Migrates cortex models to the llama.cpp extension.
    • ›Moves the thinking toggle to runtime settings for dynamic control without reloading.
    • ›Improves model load error handling with a dedicated error dialog triggered from the provider screen.
  17. v0.6.5 Jul 17, 2025 · issue -364

    Jan v0.6.5 adds responsive UI layouts and bumps llama.cpp to b5857.

    └──▷ GET THIS VERSION
    $ git clone --branch v0.6.5 https://github.com/janhq/jan.git
# already have the repo? check out this version:
$ git checkout v0.6.5
    • ›Bumps the bundled llama.cpp engine to version b5857.
    • ›Adds responsive layout support to the base UI.
    • ›Adds responsive layout support to the Settings panel.
  18. v0.6.2 Jun 26, 2025 · issue -365

    Jan v0.6.2 removes the production gate on MCP and tool use, and improves local provider connectivity with a CORS bypass.

    └──▷ GET THIS VERSION
    $ git clone --branch v0.6.2 https://github.com/janhq/jan.git
# already have the repo? check out this version:
$ git checkout v0.6.2
    • ›Removes the production gate on MCP and tool use, making both capabilities available without a feature flag.
    • ›Adds an experimental feature toggle to the UI, letting users opt into early-access capabilities.
    • ›Improves local provider connectivity by bypassing CORS restrictions when connecting to local model endpoints.
  19. v0.6.0 Jun 19, 2025 · issue -365

    Jan v0.6.0 adds MCP server support, multi-assistant management, API key auth, Vulkan toggle, download resume, fuzzy search, and a Tauri build option.

    └──▷ GET THIS VERSION
    $ git clone --branch v0.6.0 https://github.com/janhq/jan.git
# already have the repo? check out this version:
$ git checkout v0.6.0
    • ›Adds API Key setting to the Jan local API server, enabling authenticated access to the built-in OpenAI-compatible endpoint.
    • ›Adds a Vulkan toggle in settings to enable GPU acceleration on supported hardware.
    • ›Adds support for resuming interrupted model downloads via a new download manager for the llama.cpp extension.
    • ›Adds fuzzy search integration into the model dropdown for faster model selection.
    • ›Adds a refresh button to reload the model list for remote providers.
    +25 moreshow less
    • ›Adds predefined parameter presets for model configuration.
    • ›Adds a filter for downloaded models on the Hub screen.
    • ›Adds quick-access model settings directly from the model selector dropdown.
    • ›Adds a custom OpenAI-compatible provider configuration option.
    • ›Adds support for multiple assistants, each with custom emoji picker and metadata.
    • ›Adds MCP (Model Context Protocol) server connection status display and tool-call permission dialog.
    • ›Adds MCP content rendering and error handling for server activation responses.
    • ›Adds hardware info display (CPU/GPU) as a replacement for the previous cortex hardware readout.
    • ›Adds Cortex server auto-restart with in-app webview notification on failure.
    • ›Adds an 'Open API Documentation' button inside the local API server panel.
    • ›Adds token speed display per message in the chat interface.
    • ›Adds out-of-context troubleshooting guidance when a model runs out of context window.
    • ›Adds masking of sensitive values in the environment variables settings panel.
    • ›Adds file upload thumbnail preview in the chat input.
    • ›Adds initial in-app log viewer with access to the log folder and data folder relocation dialog.
    • ›Adds Tauri as an alternative build option alongside the existing Electron build.
    • ›Adds legacy local storage data migration to the new app data format.
    • ›Adds chat container width setting for adjustable chat layout.
    • ›Adds assistant info display on individual chat messages.
    • ›Adds product analytics (PostHog) opt-in.
    • ›Adds 'About' section entries in General settings.
    • ›Adds built-in custom emoji support and message metadata display in chat.
    • ›Persists the last-used model when creating a new thread.
    • ›Adds support for opening Jan directly from a Hugging Face GGUF repository page.
    • ›The /models local API endpoint now filters results to show only downloaded models.
  20. v0.5.16 Mar 24, 2025 · issue -368

    Jan v0.5.16 adds API token rotation, Cortex API authorization, Model Hub filters, and preserves token speed in threads.

    └──▷ GET THIS VERSION
    $ git clone --branch v0.5.16 https://github.com/janhq/jan.git
# already have the repo? check out this version:
$ git checkout v0.5.16
    • ›Adds Cortex API Authorization, rotating the API token on each run for improved credential hygiene.
    • ›Adds filter options and responsive layout to the Jan Model Hub, with a sticky filter panel and tooltip filters for max model size and search results.
    • ›Adds a manual refresh control so users can pull an updated list of cloud models on demand.
    • ›Preserves and displays token generation speed within chat threads.
    • ›Adds OpenAI GPT-4.5 preview and Anthropic Claude 3.7 Sonnet to the built-in model list.
    +5 moreshow less
    • ›Adds a checkmark indicator on the currently selected model in the model list.
    • ›Adds a 'recommended' label to highlight engine variants in the engine selection UI.
    • ›Keeps the Jan Model Hub model list automatically up to date without requiring a manual refresh.
    • ›Adds scrollbar visibility/style options in Settings.
    • ›Integrates PostHog analytics into Jan Web.
  21. v0.5.15 Feb 18, 2025 · issue -369

    Jan v0.5.15 adds HTTP proxy auth, remote model management, Google Gemini and DeepSeek support, and removes Umami telemetry.

    └──▷ GET THIS VERSION
    $ git clone --branch v0.5.15 https://github.com/janhq/jan.git
# already have the repo? check out this version:
$ git checkout v0.5.15
    • ›Adds HTTP proxy authentication input fields, enabling Jan to route traffic through authenticated proxies.
    • ›Adds the ability to add and manage custom remote models, with automatic model list population when configuring a new remote engine.
    • ›Adds Google Gemini and DeepSeek as supported remote engine providers out of the box.
    • ›Adds DeepSeek R1 distill models to the model hub.
    • ›Expands the system monitor panel with an updated app layout giving hardware stats more screen space.
    +5 moreshow less
    • ›Improves the hardware settings screen with better GPU and device information display.
    • ›Removes Umami analytics, eliminating telemetry data collection from the app.
    • ›Adds inline standardized error messages across the UI for remote engine and thread errors.
    • ›New threads now open with the last chosen model pre-selected.
    • ›Updates the file and image upload UI.
  22. v0.5.12 Dec 30, 2024 · issue -371

    Jan v0.5.12 adds chat width settings, product analytics UI, and routes all thread/message requests through the cortex.cpp backend.

    └──▷ GET THIS VERSION
    $ git clone --branch v0.5.12 https://github.com/janhq/jan.git
# already have the repo? check out this version:
$ git checkout v0.5.12
    • ›Adds a chat width setting option for threads, letting users adjust the thumbnail/input box width from the thread settings panel.
    • ›Reroutes all threads and messages API requests to the cortex.cpp backend, deprecating Jan core's REST module.
    • ›Adds a product analytics UI for usage insights.
    • ›Updates the macOS app download to a universal binary supporting both Apple Silicon and Intel.
    • ›Improves error handling for remote models when there is no internet connection.
    +4 moreshow less
    • ›Defaults the Jan Input Box Settings and Right panel to open on launch.
    • ›Adds OpenAI gpt-4o-mini and o1 models to the remote model roster.
    • ›Moves token speed display to the bottom of the chat interface.
    • ›Sets the recommended model to undefined when no model is available, preventing stale model references.
  23. v0.5.11 Dec 5, 2024 · issue -371

    Jan v0.5.11 adds a universal macOS build supporting both Apple Silicon and Intel in a single binary.

    └──▷ GET THIS VERSION
    $ git clone --branch v0.5.11 https://github.com/janhq/jan.git
# already have the repo? check out this version:
$ git checkout v0.5.11
    • ›Adds a universal macOS binary that runs natively on both Apple Silicon and Intel Macs without Rosetta translation.
  24. v0.5.10 Dec 3, 2024 · issue -371

    Jan v0.5.10 adds stop word model settings, more Groq models, Anthropic model updates, and an increased Claude 3.5 max-token limit.

    └──▷ GET THIS VERSION
    $ git clone --branch v0.5.10 https://github.com/janhq/jan.git
# already have the repo? check out this version:
$ git checkout v0.5.10
    • ›Adds stop word model setting, letting users define stop sequences directly in model configuration.
    • ›Increases the max-token limit for Claude 3.5 models.
    • ›Adds more Groq models to the model selection.
    • ›Adds updated Anthropic model options including newer Claude variants.
    • ›Updates Jan's client request handling to adapt to API changes from Cortex.
  25. v0.5.9 Nov 22, 2024 · issue -372

    Jan v0.5.9 adds HTTP proxy and HuggingFace token configuration, cortex.cpp engine variants, and a new code-block UI with mid-stream copy.

    └──▷ GET THIS VERSION
    $ git clone --branch v0.5.9 https://github.com/janhq/jan.git
# already have the repo? check out this version:
$ git checkout v0.5.9
    • ›Adds HTTP proxy configuration via cortex.cpp, enabling Jan to route model traffic through a proxy.
    • ›Adds HuggingFace API token configuration via cortex.cpp for authenticated model access.
    • ›Supports cortex.cpp engine variants, allowing selection among different backend engine builds.
    • ›New code-block UI with the ability to copy code blocks or plain text mid-stream during model responses.
    • ›Enhances the local server page UX.
  26. v0.5.8 Nov 13, 2024 · issue -372

    Jan v0.5.8 integrates Cortex.cpp as a backend provider and adds a new nightly app channel.

    └──▷ GET THIS VERSION
    $ git clone --branch v0.5.8 https://github.com/janhq/jan.git
# already have the repo? check out this version:
$ git checkout v0.5.8
    • ›Integrates Cortex.cpp as a backend provider, with Jan APIs proxied to Cortex.cpp.
    • ›Adds a new nightly app release channel for early access builds.
    • ›Displays model ID on the local API server page.
    • ›Expands clickable areas in the ribbon panel for easier navigation.
    • ›Adds Qwen2.5-Coder 14B and 32B models to the model hub.
  27. v0.5.7 Oct 24, 2024 · issue -373

    Jan v0.5.7 adds markdown rendering in user messages and promotes persistent thread instructions to a stable feature.

    └──▷ GET THIS VERSION
    $ git clone --branch v0.5.7 https://github.com/janhq/jan.git
# already have the repo? check out this version:
$ git checkout v0.5.7
    • ›Adds markdown rendering support for user messages in chat threads.
    • ›Promotes saved instructions for new threads from experimental to a stable feature.
    • ›Introduces a Jan beta version channel.
  28. v0.5.5 Oct 2, 2024 · issue -373

    Jan v0.5.5 adds textarea auto-resize and an enhanced tabbed model-selection UI.

    └──▷ GET THIS VERSION
    $ git clone --branch v0.5.5 https://github.com/janhq/jan.git
# already have the repo? check out this version:
$ git checkout v0.5.5
    • ›Adds auto-resizing textarea in the chat input area, expanding as content grows.
    • ›Enhances the model selection UI with a new tabs component for browsing models.
  29. v0.5.4 Sep 17, 2024 · issue -374

    Jan v0.5.4 adds model search in the dropdown and new setting options in the dropdown menu.

    └──▷ GET THIS VERSION
    $ git clone --branch v0.5.4 https://github.com/janhq/jan.git
# already have the repo? check out this version:
$ git checkout v0.5.4
    • ›Enables search functionality within the model dropdown to quickly filter configured models.
    • ›Adds setting options directly accessible from the dropdown menu.
  30. v0.5.3 Aug 29, 2024 · issue -375

    Jan v0.5.3 adds GGUF metadata extraction on import, NVIDIA engine support, OpenRouter model settings, and a configurable data folder.

    └──▷ GET THIS VERSION
    $ git clone --branch v0.5.3 https://github.com/janhq/jan.git
# already have the repo? check out this version:
$ git checkout v0.5.3
    • ›Adds GGUF metadata extraction when importing models, surfacing model details automatically during the import flow.
    • ›Adds an NVIDIA engine option for running local models via the new add nvidia engine capability.
    • ›Adds OpenRouter model settings panel, allowing per-model configuration of OpenRouter-specific parameters.
    • ›Adds the ability to change the Jan data folder path from the UI, with the default now set to the app's userData directory.
    • ›Adds OpenRouter request endpoint setting back into configuration.
    +8 moreshow less
    • ›Adds chunk count display in the retrieval UI.
    • ›Embeds Cortex into Jan as a JS module, replacing the prior separate process integration.
    • ›Enables managing and configuring cloud/remote models directly from the 'My Models' screen and the threads screen.
    • ›Adds keyboard shortcut to delete and clean a thread.
    • ›Enables copying model instructions from the UI.
    • ›Adds a new starter screen for first-run experience.
    • ›Preserves model settings across sessions so per-model configuration is not lost on restart.
    • ›Adds a model assistant tab to the assistant panel.
    └──▷ BREAKING ON UPGRADE
    • !The default Jan data folder path has changed to the app's userData directory; existing data at the previous location will require migration.
    • !Docker and Kubernetes deployment support is deprecated and removed.
    • !Internal REST endpoints have been disabled due to a vulnerability issue; integrations relying on those endpoints will break.
  31. v0.5.2 Jul 15, 2024 · issue -376

    Jan v0.5.2 adds Claude 3.5 Sonnet, spell-check config for chat input, and right-click thread settings.

    └──▷ GET THIS VERSION
    $ git clone --branch v0.5.2 https://github.com/janhq/jan.git
# already have the repo? check out this version:
$ git checkout v0.5.2
    • ›Adds spell-check options config for the chat input field.
    • ›Adds Claude 3.5 Sonnet as a selectable model.
    • ›Adds a shortcut to open app logs directly from the System Monitor.
    • ›Enables right-click on thread items to open their settings.
  32. v0.5.1 Jun 21, 2024 · issue -377

    Jan v0.5.1 adds NVIDIA API integration and a hotkey to collapse the right panel.

    └──▷ GET THIS VERSION
    $ git clone --branch v0.5.1 https://github.com/janhq/jan.git
# already have the repo? check out this version:
$ git checkout v0.5.1
    • ›Adds NVIDIA API as a supported provider in the Jan application.
    • ›Adds a hotkey to collapse the right panel in the UI.
  33. v0.5.0 Jun 3, 2024 · issue -377

    Jan v0.5.0 revamps the desktop UI and adds access token registration for Hugging Face model downloads.

    └──▷ GET THIS VERSION
    $ git clone --branch v0.5.0 https://github.com/janhq/jan.git
# already have the repo? check out this version:
$ git checkout v0.5.0
    • ›Adds user access token registration, enabling authentication for gated Hugging Face model downloads.
    • ›Delivers a full desktop UI revamp with updated layout and visual design.
    • ›Adds input actions for settings items and updated tooltip explainers throughout the settings panel.
  34. v0.4.13 May 20, 2024 · issue -378

    Jan v0.4.13 adds Anthropic, OpenRouter, and Martian inference extensions plus deeplink support and new remote models.

    └──▷ GET THIS VERSION
    $ git clone --branch v0.4.13 https://github.com/janhq/jan.git
# already have the repo? check out this version:
$ git checkout v0.4.13
    • ›Adds Anthropic inference extension, enabling Claude models as a remote provider directly within Jan.
    • ›Adds OpenRouter integration as a remote inference provider.
    • ›Adds Martian inference extension for routing requests through the Martian model router.
    • ›Adds deeplink support, allowing Jan to be opened and targeted via URL schemes.
    • ›Adds remote model command-r (Cohere) to the list of available remote models.
    +3 moreshow less
    • ›Adds remote model gpt-4 turbo to the list of available remote models.
    • ›Adds gpt-4o API configuration for use as a remote model.
    • ›Adds phi3 model to the model hub.
  35. v0.4.12 Apr 25, 2024 · issue -379

    Jan v0.4.12 adds LaTeX rendering in chat, Windows NSIS installer, and new Llama 3 models on the Groq Extension.

    └──▷ GET THIS VERSION
    $ git clone --branch v0.4.12 https://github.com/janhq/jan.git
# already have the repo? check out this version:
$ git checkout v0.4.12
    • ›Adds LaTeX rendering in chat via the Marked extension (feat: add LaTeX extension support via Marked).
    • ›Adds new Llama 3 and additional models to the Groq Extension.
    • ›Adds a Windows NSIS installer package for easier Windows deployment.
    • ›Updates featured models available in the model hub.
  36. v0.4.11 Apr 15, 2024 · issue -379

    Jan v0.4.11 adds a Mistral inference engine extension, API prefix settings, and moves logs into a monitoring extension.

    └──▷ GET THIS VERSION
    $ git clone --branch v0.4.11 https://github.com/janhq/jan.git
# already have the repo? check out this version:
$ git checkout v0.4.11
    • ›Adds API prefix settings, letting users configure a custom URL prefix for the local API server.
    • ›Adds a Mistral inference engine extension for remote Mistral model inference.
    • ›Moves log output into the monitoring extension for centralized observability.
    • ›Adds GPU driver and toolkit status display in the UI.
    • ›Adds an 'open log directory' shortcut to the troubleshooting modal.
    +3 moreshow less
    • ›Adds markdown rendering support for extension descriptions.
    • ›Rearranges model positions on the Hub page for improved discoverability.
    • ›Adds support for CJK (Chinese/Japanese/Korean) input method Enter key handling in chat.
  37. v0.4.10 Apr 2, 2024 · issue -379

    Jan v0.4.10 adds a Groq Inference Extension for cloud-accelerated inference alongside homepage and download page redesigns.

    └──▷ GET THIS VERSION
    $ git clone --branch v0.4.10 https://github.com/janhq/jan.git
# already have the repo? check out this version:
$ git checkout v0.4.10
    • ›Adds Groq Inference Extension, enabling Groq-hosted cloud inference as a backend alongside local engines.
    • ›Revamps the Jan homepage with a new design.
    • ›Adds a dedicated download page to the Jan website.
  38. v0.4.9 Mar 19, 2024 · issue -380

    Jan v0.4.9 adds a Nitro-TensorRT-LLM extension and dark mode support for the Quick Ask feature.

    └──▷ GET THIS VERSION
    $ git clone --branch v0.4.9 https://github.com/janhq/jan.git
# already have the repo? check out this version:
$ git checkout v0.4.9
    • ›Adds the Nitro-TensorRT-LLM Extension for accelerated local inference using NVIDIA TensorRT-LLM.
    • ›Quick Ask interface now supports dark mode.
  39. v0.4.8 Mar 11, 2024 · issue -380

    Jan v0.4.8 adds vision (image input), model import, and an experimental Hugging Face to GGUF converter

    └──▷ GET THIS VERSION
    $ git clone --branch v0.4.8 https://github.com/janhq/jan.git
# already have the repo? check out this version:
$ git checkout v0.4.8
    • ›Adds vision capability ('Jan can see') enabling image input to supported models, including drag-and-drop image upload.
    • ›Adds an import model feature so users can bring local models into Jan directly from the UI.
    • ›Adds an experimental one-step conversion of Hugging Face models to GGUF format.
    • ›Prompts users to download updates manually when automatic update is not possible.
  40. v0.4.7 Feb 26, 2024 · issue -381

    Jan v0.4.7 adds AMD/Intel GPU support via Vulkan, user-selectable GPUs, editable messages, and a Helm chart for server deployments.

    └──▷ GET THIS VERSION
    $ git clone --branch v0.4.7 https://github.com/janhq/jan.git
# already have the repo? check out this version:
$ git checkout v0.4.7
    • ›Adds Nitro Vulkan backend to support AMD GPU/APU and Intel Arc GPU acceleration.
    • ›Adds user-selectable GPU controls with GPU-based model recommendations in the UI.
    • ›Adds the ability to edit sent user messages in a thread.
    • ›Adds a troubleshooting guideline modal to surface diagnostic help in-app.
    • ›Revamps the GPU acceleration settings UI with improved controls.
    +3 moreshow less
    • ›Revamps the model option dropdown list UI.
    • ›Adds a Helm chart and CI pipeline for Jan server deployments.
    • ›Thread titles now auto-summarize the conversation topic.
  41. v0.4.6 Feb 5, 2024 · issue -381

    Jan v0.4.6 adds HTTP API model control, factory reset, and a default NGL value for easier local model management.

    └──▷ GET THIS VERSION
    $ git clone --branch v0.4.6 https://github.com/janhq/jan.git
# already have the repo? check out this version:
$ git checkout v0.4.6
    • ›Adds start/stop model via HTTP API, enabling programmatic control of local model lifecycle.
    • ›Adds a factory reset feature to restore Jan to a clean default state.
    • ›Adds a default value for ngl (GPU layers), reducing manual configuration for new models.
    • ›Marks the Jan Data Folder setting as no longer experimental, making it a stable configuration option.
    • ›Marks RAG (retrieval-augmented generation) as an experimental feature, surfacing its status in the UI.
    +1 moreshow less
    • ›Adds timestamps displayed under thread names in the left panel for easier conversation tracking.
  42. v0.4.5 Jan 29, 2024 · issue -382

    Jan v0.4.5 adds HTTP proxy support, movable data folder, local API server dashboard, and low-RAM warnings.

    └──▷ GET THIS VERSION
    $ git clone --branch v0.4.5 https://github.com/janhq/jan.git
# already have the repo? check out this version:
$ git checkout v0.4.5
    • ›Adds HTTP proxy support, enabling Jan to route model traffic through a proxy.
    • ›Adds a new UI page serving as a local API server dashboard for monitoring and managing the built-in API server.
    • ›Adds UX improvements to the local API server settings panel.
    • ›Adds the ability for users to move the Jan data folder to a custom location via the UI.
    • ›Adds an error message when the system does not have enough RAM to run a selected model.
    +1 moreshow less
    • ›Redesigns the left panel settings page layout.
  43. v0.4.4 Jan 16, 2024 · issue -382

    Jan v0.4.4 adds GPU detection, Linux AppImage support, Swagger docs, model-switching mid-thread, and a collapsible sidebar with hotkey.

    └──▷ GET THIS VERSION
    $ git clone --branch v0.4.4 https://github.com/janhq/jan.git
# already have the repo? check out this version:
$ git checkout v0.4.4
    └──▷ TRY IT
    Explore and test Jan's local inference API interactively without writing any code.
    $ open http://localhost:1337/docs
    • ›Adds Swagger API documentation at localhost:1337/docs, giving practitioners a live, interactive reference for Jan's local API.
    • ›Adds engine settings panel in the UI, exposing inference engine parameters directly to users.
    • ›Adds a keyboard shortcut list in the Settings page so users can discover and reference all hotkeys.
    • ›Makes left sidebar collapsible via hotkey, improving screen real-estate during active sessions.
    • ›Enables switching models mid-thread without starting a new conversation.
    +5 moreshow less
    • ›Adds GPU detection for Windows and Linux, including CUDA version detection, so the app can surface hardware compatibility information.
    • ›Adds Linux AppImage format support, broadening the supported distribution packaging options.
    • ›Adds compatibility and recommendation labels (with color coding) to model cards in the Hub, based on total system RAM.
    • ›Makes model.json optional for model loading, reducing friction when importing models without metadata.
    • ›Deprecates the model.json ready state in favor of a .download file extension to track download status.
    └──▷ BREAKING ON UPGRADE
    • !The model.json ready state is deprecated in favor of the .download file extension; existing tooling or scripts that rely on the ready-state field in model.json will need to be updated.
  44. v0.4.3 Dec 21, 2023 · issue -383

    Jan v0.4.3 adds a copy button for code blocks, an autoupdater for nightly builds, and per-thread model setting state.

    └──▷ GET THIS VERSION
    $ git clone --branch v0.4.3 https://github.com/janhq/jan.git
# already have the repo? check out this version:
$ git checkout v0.4.3
    • ›Adds a copy button to code blocks in the chat UI for one-click copying of generated code.
    • ›Introduces an autoupdater for nightly builds, enabling automatic in-app updates without manual reinstallation.
    • ›Persists model settings state independently per thread, so switching threads no longer resets model configuration.
  45. v0.4.2 Dec 15, 2023 · issue -383

    Jan v0.4.2 adds theme persistence, a combined stop/send button, and a model-loading indicator.

    └──▷ GET THIS VERSION
    $ git clone --branch v0.4.2 https://github.com/janhq/jan.git
# already have the repo? check out this version:
$ git checkout v0.4.2
    • ›App theme now persists via local storage instead of following the native Electron system theme, so user theme choices survive restarts.
    • ›Adds a loading indicator while a model is starting up, giving visual feedback before inference begins.
  46. v0.4.1 Dec 14, 2023 · issue -383

    Jan v0.4.1 adds NVIDIA Triton TRT-LLM extension, prompt template inference, multiple engine support, and model parameter controls

    └──▷ GET THIS VERSION
    $ git clone --branch v0.4.1 https://github.com/janhq/jan.git
# already have the repo? check out this version:
$ git checkout v0.4.1
    • ›Adds NVIDIA Triton TRT-LLM extension for accelerated inference via @vuonghoainam's new engine integration.
    • ›Supports multiple inference engines for Nitro and OpenAI, enabling engine selection per model.
    • ›Adds model parameters configuration for inference extensions.
    • ›Adds JSON schema definitions for engine and model parameters.
    • ›Enables inference with prompt templates in Nitro.
    +2 moreshow less
    • ›Adds CPU hyper-threading support for Nitro model loading.
    • ›Enables killing the Nitro process via API (Nitro 0.1.27).
  47. v0.4.0 Dec 6, 2023 · issue -383

    Jan v0.4.0 revamps the thread and hub screens and boots a local Express server on localhost:1337

    └──▷ GET THIS VERSION
    $ git clone --branch v0.4.0 https://github.com/janhq/jan.git
# already have the repo? check out this version:
$ git checkout v0.4.0
    • ›Adds a boilerplate Express server running on localhost 1337 for local API access
    • ›Pre-populates Jan's /models folder with model.json files so models are available without manual setup
    • ›Revamps the Model Hub screen with a new cover image and updated layout
    • ›Revamps the thread screen UI
    • ›Revamps the landing page
  48. v0.3.3 Nov 28, 2023 · issue -384

    Jan v0.3.3 adds experimental per-conversation system instructions and a restyled message action toolbar.

    └──▷ GET THIS VERSION
    $ git clone --branch v0.3.3 https://github.com/janhq/jan.git
# already have the repo? check out this version:
$ git checkout v0.3.3
    • ›Adds experimental ability to give custom instructions for individual conversations, letting users steer model behavior per thread.
    • ›Improves styling of the message action toolbar for easier in-chat interactions.
    • ›Adds Windows code signing to the CI pipeline for distributed builds.
  49. v0.3.1 Nov 10, 2023 · issue -384

    Jan v0.3.1 adds an experimental feature toggle, a new conversation button, and a revamped plugin architecture.

    └──▷ GET THIS VERSION
    $ git clone --branch v0.3.1 https://github.com/janhq/jan.git
# already have the repo? check out this version:
$ git checkout v0.3.1
    • ›Adds an Experimental Feature Toggle, making opt-in unstable features accessible without separate builds.
    • ›Adds a 'New Conversation' button to the conversation sidebar for faster session creation.
    • ›Revamps the plugin architecture, including refactoring the plugin manager and execution layer to TypeScript.
    • ›Reads plugin manifests from a CDN, enabling dynamic plugin discovery without local manifest files.
    • ›Adds appDataPath to the plugin SDK for plugins that need access to the application data directory.
    +3 moreshow less
    • ›Allows users to cancel an in-progress model download.
    • ›Changes the download button label based on the user's operating system.
    • ›Bumps Nitro inference engine from v0.1.4 to v0.1.6.
  50. v0.2.1 Oct 25, 2023 · issue -385

    Jan v0.2.1 adds bot creation, document chat, remote plugin browsing, and a UI revamp.

    └──▷ GET THIS VERSION
    $ git clone --branch v0.2.1 https://github.com/janhq/jan.git
# already have the repo? check out this version:
$ git checkout v0.2.1
    • ›Adds create-bot functionality, letting users define and launch custom bot personas within the app.
    • ›New 'chat with documents' plugin enables retrieval-augmented conversation against local documents.
    • ›Enables browsing and installing plugins directly from the npm repository without manual file handling.
    • ›Plugins and the app can now subscribe to and emit events via the @janhq/plugin-core events module.
    • ›Adds the @janhq/plugin-core module with a defined usage API for plugin developers.
    +2 moreshow less
    • ›Updates Nitro inference backend to release 0.1.2 on Windows and Linux.
    • ›Interface revamp with updated home UI and landing page.
  51. v0.2.0 Oct 13, 2023 · issue -385

    Jan v0.2.0 lets users fetch models directly from GitHub and improves the chat UI.

    └──▷ GET THIS VERSION
    $ git clone --branch v0.2.0 https://github.com/janhq/jan.git
# already have the repo? check out this version:
$ git checkout v0.2.0
    • ›Enables fetching models from GitHub directly within the app.
    • ›Improved chat box UI for a cleaner conversation experience.
my-toolchain — 0 tools
paste an install list to detect your tools

A brew list, a Brewfile, requirements.txt, a Dockerfile — or just the product names, free-form. Nothing leaves your browser.

    browse all tools →