The daily firehose — everything the toolchain shipped today, already filtered.
// HOW THIS ISSUE IS MADE
We read every release from the 174 tools on our watchlist at the source — GitHub and GitLab release notes, vendor release pages and changelogs, project blogs and feeds, vendor press releases, and the source code behind the tag. Bug-fix-only releases and non-product newsroom noise are dropped; what's left is summarized down to the new capability, how to try it, and any screenshots or videos the release itself published. Every entry links to the sources it was built from.
Continue openai-adapters 1.34.0 adds Sonnet 4.5 model support and deprecates Sonnet 3.5.
└──▷ GET THIS VERSION
$ git clone --branch @continuedev/[email protected] https://github.com/continuedev/continue.git
# already have the repo? check out this version:$ git checkout @continuedev/[email protected]
›Adds support for Claude Sonnet 4.5 and marks Sonnet 3.5 as deprecated.
Continue adds grep/find/findstr search fallback, Supabase OAuth scopes for MCP, and org profile selection at sign-in.
└──▷ GET THIS VERSION
$ git clone --branch @continuedev/[email protected] https://github.com/continuedev/continue.git
# already have the repo? check out this version:$ git checkout @continuedev/[email protected]
›Adds grep, find, and findstr as alternative search strategies in the CLI for code search operations.
›Adds Supabase-specific OAuth scopes to the mcp-remote fallback for MCP integrations.
›Supports selecting an org profile at sign-in.
›Adds support for Claude Opus 4/5 and Sonnet 4/5 model updates.
Continue CLI gains grep/find/findstr search fallback, Supabase OAuth scopes for MCP, and org profile selection on sign-in.
└──▷ GET THIS VERSION
$ git clone --branch @continuedev/[email protected] https://github.com/continuedev/continue.git
# already have the repo? check out this version:$ git checkout @continuedev/[email protected]
›Adds grep, find, and findstr as alternative search strategies in the Continue CLI for codebase search.
›Adds Supabase-specific OAuth scopes to the mcp-remote fallback in the MCP integration.
›Enables organization profile selection at sign-in time.
›Adds support for Claude Sonnet 4.5 model and marks Sonnet 3.5 as deprecated.
Pi v0.12.4 adds a /debug slash command that logs terminal rendering diagnostics to disk.
└──▷ GET THIS VERSION
$ git clone --branch v0.12.4 https://github.com/earendil-works/pi.git
# already have the repo? check out this version:$ git checkout v0.12.4
└──▷ TRY IT
Capture a rendering diagnostic snapshot when lines appear misaligned or truncated in your terminal.
$ /debug
›New /debug slash command writes terminal width and all rendered lines with their visible widths to ~/.pi/agent/pi-debug.log for diagnosing rendering issues.
Pi v0.12.0 ships pre-built standalone binaries for macOS, Linux, and Windows — no Node/Bun runtime required.
└──▷ GET THIS VERSION
$ git clone --branch v0.12.0 https://github.com/earendil-works/pi.git
# already have the repo? check out this version:$ git checkout v0.12.0
›Adds standalone self-contained binary builds via npm run build:binary, with pre-built releases for macOS (arm64/x64), Linux (x64/arm64), and Windows (x64) on GitHub Releases.
An open-source AI agent that brings the power of Gemini directly into your terminal.
gemini-cli v0.19.0 adds Databricks auth, a session browser, hooks infrastructure, custom model aliases, and automatic Flash fallback on quota errors.
└──▷ GET THIS VERSION
$ git clone --branch v0.19.0 https://github.com/google-gemini/gemini-cli.git
# already have the repo? check out this version:$ git checkout v0.19.0
└──▷ TRY IT
Browse and resume a previous chat session interactively without leaving the CLI.
$ /resume
›Adds Databricks authentication support and a custom header option for connecting to Databricks-hosted Gemini endpoints.
›Adds interactive session browser component with a new /resume slash command to browse and reopen past chat sessions.
›Introduces hooks infrastructure (telemetry, event handling, agent lifecycle, and system orchestration) enabling extensible automation around agent actions.
›Adds model availability service (modelAvailabilityService) with ModelPolicy and PolicyCatalog for tracking and managing model health.
›Adds isModelAvailabilityServiceEnabled setting to toggle the model availability service.
+5 moreshow less
›Supports custom aliases for model configs, letting users define shorthand names for specific model configurations.
›Automatic fallback to Gemini Flash on TerminalQuota errors so sessions continue without manual intervention.
›Adds session subtask display in the /stats command output.
›Displays a custom loading phrase when an interactive shell tool requires user input.
›Removes the useModelRouter experimental flag, graduating model routing to standard behavior.
└──▷ BREAKING ON UPGRADE
!Alternate buffer mode is now off by default; terminals that relied on the previous default alternate-buffer behavior will see a changed display mode on upgrade.
gemini-cli v0.20.0-nightly adds auto-executing slash commands, a holiday theme, and enhanced model availability routing.
└──▷ GET THIS VERSION
$ git clone --branch v0.20.0-nightly.20251202.29920b16d https://github.com/google-gemini/gemini-cli.git
# already have the repo? check out this version:$ git checkout v0.20.0-nightly.20251202.29920b16d
›Auto-executes simple slash commands on Enter, removing the need for an extra confirmation keystroke.
›Adds a built-in holiday theme () selectable via the themes system.
›Enhances availability routing with wrapped fallback and single-model policies for more resilient model selection.
›Adds a startup profiler to measure and record application initialization phases.
›Always applies MCP server instructions when MCP tools are in use.
LangGraph SDK 0.2.12 adds pagination to assistants search and a sentinel to skip auto-loading API keys.
└──▷ GET THIS VERSION
$ git clone --branch sdk==0.2.12 https://github.com/langchain-ai/langgraph.git
# already have the repo? check out this version:$ git checkout sdk==0.2.12
└──▷ USE IT
Instantiate the SDK client without auto-loading the API key from the environment, supplying credentials explicitly instead.
python
from langgraph_sdk import get_client, SKIP_LOAD_API_KEY
client = get_client(url="http://localhost:8123", api_key=SKIP_LOAD_API_KEY)
›Adds pagination metadata to the assistants search response, enabling clients to page through large assistant lists.
›Introduces a sentinel value to skip automatic API key loading when instantiating the SDK client, allowing explicit credential control.
warelay v1.3.0 adds pluggable AI agents, safety stop words, same-phone mode, and IPC relay coordination.
└──▷ GET THIS VERSION
$ git clone --branch v1.3.0 https://github.com/openclaw/openclaw.git
# already have the repo? check out this version:$ git checkout v1.3.0
└──▷ USE IT
Switch from Claude to Codex as the reply agent without changing prompt templates.
yaml
# In your warelay config:
inbound:
reply:
agent: codex
Customize the same-phone prefix so bot replies are visually distinct when chatting with yourself.
yaml
# In your warelay config:
inbound:
samePhoneMarker: "[🦞 same-phone]"
Send a message through the running relay's IPC socket instead of opening a second WhatsApp connection.
$ warelay send --provider web
›Adds pluggable agent support via a new inbound.reply.agent config block, enabling Claude, Pi, Codex, and Opencode as swappable CLI backends with per-agent argv builders and NDJSON stream parsing.
›Adds safety stop words: sending stop, esc, abort, wait, or exit immediately kills the active agent run and marks the session with an aborted-run reminder.
›Adds same-phone mode, allowing warelay to run on the same number it messages from; echo detection via a bounded Set prevents infinite reply loops.
›Adds a new inbound.samePhoneMarker config option to customize the prefix on same-phone messages (default: [same-phone]).
›Adds an IPC Unix socket server at ~/.warelay/relay.sock so warelay send and warelay heartbeat reuse the running relay's WhatsApp connection instead of opening a second socket.
+4 moreshow less
›Adds batched inbound messaging: multiple queued WhatsApp messages are delivered to the agent in one timestamped batch to preserve ordering and context.
›Adds a watchdog timer that auto-restarts the WhatsApp connection after 30 minutes of no message activity; heartbeat logs now include minutesSinceLastMessage.
›Adds early allowFrom filtering in inbound.ts to block unauthorized senders before any encryption/decryption attempt, preventing Bad MAC errors from silently killing the event emitter.
›Adds typing indicator after IPC-sent messages to signal that more replies may be coming.
LanceDB v0.22.4-beta.3 adds head() for remote tables and stable row IDs via storage_options.
└──▷ GET THIS VERSION
$ git clone --branch v0.22.4-beta.3 https://github.com/lancedb/lancedb.git
# already have the repo? check out this version:$ git checkout v0.22.4-beta.3
›Supports stable row IDs configurable via storage_options when creating or opening tables.
›Implements head() method for remote tables, enabling fast row-count-limited retrieval without a full scan.
›Updates Codex URL key configuration for remote connectivity.
LanceDB python-v0.25.4-beta.3 adds head() for remote tables and stable row ID support via storage_options.
└──▷ GET THIS VERSION
$ git clone --branch python-v0.25.4-beta.3 https://github.com/lancedb/lancedb.git
# already have the repo? check out this version:$ git checkout python-v0.25.4-beta.3
›Supports stable row IDs on tables via storage_options, enabling consistent row addressing across compaction and updates.
›Implements head() for remote tables, allowing callers to fetch the first N rows from a remote LanceDB table.
›Updates the Codex URL key, enabling connectivity to the updated Codex endpoint.
THE AI TOOLCHAIN