Heads up This site is currently under heavy development.
Subscribe Get it delivered — the daily firehose, filtered to the tools you run, plus the documentation changes vendors never announce. Compare plans →

The AI Toolchain — issue -191, February 7, 2026

THE AI TOOLCHAIN NO. -191
Tail
THE DAILY RELEASE FIREHOSE
PUBLISHED FEBRUARY 7, 2026 · EVERY WEEKDAY
EDITIONS tail grep head diff uniq

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.

VIEW
ISSUE VIEW full issue
Do you prefer this view? 
$ tct list   # 7 tools matched
AI & LLM Tooling
◆  AI Coding Agents

GitHub Copilot CLI

Sources Release notes → v0.0.406 NOTES

GitHub Copilot CLI v0.0.406 adds Claude Opus 4.6 Fast, a /changelog command, --no-experimental flag, and richer MCP tool support.

└──▷ GET THIS VERSION
$ git clone --branch v0.0.406 https://github.com/github/copilot-cli.git
# already have the repo? check out this version:
$ git checkout v0.0.406
└──▷ TRY IT
Check which MCP tools are currently enabled or disabled without leaving the CLI.
$ /mcp show
Add a third-party plugin directly from a URL via the plugin marketplace.
$ gh copilot plugin marketplace add https://example.com/my-copilot-plugin
  • ›New --no-experimental flag disables all experimental features at invocation time.
  • ›New /changelog command lets users view release notes directly from the CLI.
  • ›New /mcp show command displays enabled/disabled status for MCP tools.
  • ›MCP tool responses now include structured content (images, resources) for richer UI display in VS Code.
  • ›plugin marketplace add now accepts URLs as sources when adding plugins.
+4 moreshow less
  • ›Commands from plugins are now translated into skills, expanding the skill surface automatically.
  • ›Adds support for Claude Opus 4.6 Fast (Preview) as an available model.
  • ›Markdown formatting now renders in non-interactive mode output.
  • ›Displays a warning when the authenticated user has no Copilot subscription.
Was this useful?

Earendil Works Pi

Sources Release notes → v0.52.8 NOTES

AI agent toolkit: unified LLM API, agent loop, TUI, coding agent CLI

Pi v0.52.8 adds Emacs kill-ring editing, OpenRouter auto-routing, and programmatic editor paste for extensions.

└──▷ GET THIS VERSION
$ git clone --branch v0.52.8 https://github.com/earendil-works/pi.git
# already have the repo? check out this version:
$ git checkout v0.52.8
└──▷ TRY IT
Inspect available subcommands for a package without triggering a silent failure.
$ pi <package> --help
  • ›Adds Emacs-style kill ring (ctrl+k/ctrl+y/alt+y) and undo (ctrl+z) keybindings in the editor input.
  • ›Adds openrouter:auto model alias for automatic OpenRouter model routing.
  • ›Enables extensions to programmatically paste content into the editor via pasteToEditor in the extension UI context.
  • ›Adds helpful output for pi <package> --help and invalid subcommands instead of silent failure.
└──▷ BREAKING ON UPGRADE
  • !The default model is changed from Claude Opus 4.5 to Opus 4.6; any workflow pinned to the implicit default will now use Opus 4.6.
Was this useful?

Alibaba Qwen Code

Sources Release notes → v0.10.0-nightly.20260207.36931e1e NOTES

Qwen Code v0.10.0 adds session resume, export to Markdown/HTML, Java SDK alpha, Agent Skills GA, and large-paste UI improvements.

└──▷ GET THIS VERSION
$ git clone --branch v0.10.0-nightly.20260207.36931e1e https://github.com/QwenLM/qwen-code.git
# already have the repo? check out this version:
$ git checkout v0.10.0-nightly.20260207.36931e1e
└──▷ TRY IT
Resume a previous conversation session in a scripted or long-running workflow without losing context.
$ qwen query --resume <sessionId> 'Continue the refactor we started'
  • ›Adds --resume <sessionId> support to the query command so practitioners can resume previous sessions by session ID.
  • ›Adds export command for session history with markdown and HTML output formats.
  • ›Adds resume and continue options and extends authType support in the SDK.
  • ›Adds FORK_MODE support to ProcessTransport for Electron IPC integration.
  • ›Adds Java SDK (alpha) for programmatic access to Qwen Code capabilities.
+5 moreshow less
  • ›Promotes Agent Skills from experimental to stable.
  • ›Adds a large-paste placeholder in the CLI UI, improving handling of large clipboard input on macOS.
  • ›Adds debug mode output routed logfile-first via debugLogger, replacing direct console calls.
  • ›Adds source information tracking in telemetry logs.
  • ›Adds a UI hint for installing external-source extensions.
└──▷ BREAKING ON UPGRADE
  • !Settings renamed from disable* to enable* (negative to positive naming) — any configuration or scripts referencing the old disable* setting keys will break.
  • !The Smart Edit tool and ClearcutLogger are removed.
  • !The read_many_files tool is removed; its functionality is replaced by the readManyFiles utility for user @-commands.
  • !Qwen OAuth free quota reduced from 2000 to 1000 requests per day.
Was this useful?
◆  Local LLM Runtimes

LocalAI

Sources Release notes → v3.11.0 NOTES

LocalAI v3.11.0 adds realtime audio conversations, four new ASR backends, TTS streaming, music generation UI, and vLLM Omni support.

└──▷ GET THIS VERSION
$ git clone --branch v3.11.0 https://github.com/mudler/LocalAI.git
# already have the repo? check out this version:
$ git checkout v3.11.0
└──▷ TRY IT
Transcribe a multi-speaker audio file and get speaker-labeled output using the new WhisperX backend with diarization.
$ curl http://localhost:8080/v1/audio/transcriptions \
  -F [email protected] \
  -F model=whisperx \
  -F response_format=json
  • ›Adds ace-step backend for music generation (MusicGen/Ace-Step), with a new Web UI for text-to-music generation directly in the browser.
  • ›Adds transcribe response format request parameter to the STT API endpoint, letting callers control transcription output format.
  • ›Adds whisperx backend for transcription with native speaker diarization (identifying who is speaking in multi-speaker audio).
  • ›Adds vllm-omni backend for high-performance inference with vLLM Omni models.
  • ›Adds VoxCPM TTS backend with streaming mode support, reducing time-to-first-audio for speech synthesis.
+7 moreshow less
  • ›Adds qwen-asr backend for Qwen speech recognition models.
  • ›Adds nemo backend for Nvidia NeMo ASR (speech-to-text).
  • ›Adds vibevoice ASR support alongside its existing TTS capability.
  • ›Adds qwen-tts (Qwen-TTS) model support for text-to-speech.
  • ›Introduces native realtime audio conversation support compatible with OpenAI's Realtime API, including STT/TTS pipelines, voice-to-voice models, and tool call support.
  • ›Extends MLX build support to CUDA 12, CUDA 13, L4T (Nvidia Jetson), SBSA, and macOS Metal for broader hardware coverage.
  • ›Adds most remaining Piper voices from Hugging Face to the model gallery.
└──▷ BREAKING ON UPGRADE
  • !The ExLlama backend has been removed; migrate to ExLlamaV2 or llama.cpp loaders.
  • !The Bark backend has been removed (upstream unmaintained); use the new TTS backends (VoxCPM, Qwen-TTS, Piper) instead.
Was this useful?

llama.cpp

Sources Release notes → b7964 NOTES

llama.cpp b7964 adds support for the Step3.5-Flash model architecture.

└──▷ GET THIS VERSION
$ git clone --branch b7964 https://github.com/ggml-org/llama.cpp.git
# already have the repo? check out this version:
$ git checkout b7964
  • ›Adds support for the Step3.5-Flash model architecture (LLM_ARCH_STEP35), including GGUF conversion, swiglu clamp KV entries, and KV shifting disabled for this architecture.
Was this useful?
◆  AI Model & Data Infrastructure

Ollama

Sources Release notes → v0.15.6 NOTES

Get up and running with Kimi-K2.6, GLM-5.2, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.

ollama launch now auto-downloads missing models instead of erroring out

└──▷ GET THIS VERSION
$ git clone --branch v0.15.6 https://github.com/ollama/ollama.git
# already have the repo? check out this version:
$ git checkout v0.15.6
  • ›Enables ollama launch to automatically download missing models on demand rather than returning an error.
Was this useful?
◆  AI Agent Frameworks

OpenClaw

Sources Release notes → v2026.2.6 NOTES

Your own personal AI assistant. Any OS.

OpenClaw v2026.2.6 adds xAI/Grok provider, Anthropic Opus 4.6 & GPT-5.3-Codex support, Voyage AI memory, and a token usage dashboard.

└──▷ GET THIS VERSION
$ git clone --branch v2026.2.6 https://github.com/openclaw/openclaw.git
# already have the repo? check out this version:
$ git checkout v2026.2.6
  • ›Adds xAI (Grok) as a supported provider.
  • ›Supports Anthropic Opus 4.6 and OpenAI Codex gpt-5.3-codex models with forward-compat fallbacks.
  • ›Adds native Voyage AI support for memory.
  • ›New token usage dashboard in the Web UI.
  • ›CLI help output now sorts commands alphabetically.
Was this useful?
// END OF TRANSMISSION

The AI Toolchain · curated daily · February 7, 2026
Releases & features from the open-source and commercial AI tools that practitioners actually run.

▷ Subscribe
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 →