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 -204, January 25, 2026

THE AI TOOLCHAIN NO. -204
Tail
THE DAILY RELEASE FIREHOSE
PUBLISHED JANUARY 25, 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   # 5 tools matched
AI & LLM Tooling
◆  AI Coding Agents

OpenAI Codex CLI

Sources Release notes → rust-v0.90.0 NOTES

Lightweight coding agent that runs in your terminal

Codex CLI gains a network sandbox proxy, connectors/MCP support, and a beta collaboration mode with ephemeral threads.

└──▷ GET THIS VERSION
$ git clone --branch rust-v0.90.0 https://github.com/openai/codex.git
# already have the repo? check out this version:
$ git checkout rust-v0.90.0
  • ›Adds a network sandbox proxy with policy enforcement to control outbound network access.
  • ›Introduces connectors support (phase 1) via an app server and MCP integration, with new config surface.
  • ›Ships collaboration mode as beta in the TUI, featuring a clearer plan → execute handoff and simplified Coding vs Plan mode selection.
  • ›Supports ephemeral threads and improved provenance metadata for spawned collaboration threads.
  • ›Adds proxy configuration support for WebSocket connections.
+1 moreshow less
  • ›Enforces stricter limits on the number of concurrent multi-agents.
Was this useful?

SST OpenCode

Sources Release notes → v1.1.36 2 RELEASES · 2026-01-25 NOTES STABLE

The open source coding agent.

OpenCode v1.1.36 enables extended thinking for Google Vertex Anthropic models.

└──▷ GET THIS VERSION
$ git clone --branch v1.1.36 https://github.com/sst/opencode.git
# already have the repo? check out this version:
$ git checkout v1.1.36
  • ›Enables thinking mode for Google Vertex Anthropic models.
1 more release in this issue · 2026-01-25
v1.1.35 NOTES STABLE

OpenCode v1.1.35 adds model identity in prompts, xhigh Copilot reasoning, server management UI, subagent back button, and more.

└──▷ GET THIS VERSION
$ git clone --branch v1.1.35 https://github.com/sst/opencode.git
# already have the repo? check out this version:
$ git checkout v1.1.35
  • ›Tells the model what model it is via the environment section of the prompt.
  • ›Adds model information as part of task metadata.
  • ›Adds xhigh reasoning effort support for GitHub Copilot GPT-5 models.
  • ›Supports GPT-5.1-Codex model in the Codex auth plugin.
  • ›Implements new server management UI for web and desktop.
+9 moreshow less
  • ›Adds a back button in subagent sessions in the desktop app.
  • ›Auto-opens OAuth links for Codex and Copilot.
  • ›Adds Iosevka as a font choice in the desktop app.
  • ›Always centers the selected item in selection dialogs.
  • ›Retries web fetch with a simple user agent on 403 errors.
  • ›Adds an active state to comment cards in the prompt input.
  • ›Adds a link icon for copy-to-clipboard buttons in the UI.
  • ›New workspace now appears expanded and at the top of the list.
  • ›Adds onFilter callback to the List component and hides the add-server row during search.
Was this useful?

Alibaba Qwen Code

Sources Release notes → v0.8.0-nightly.20260125.829ba9c4 NOTES

Qwen Code v0.8.0 adds an extension system with detail command, /bug in non-interactive mode, and a redesigned CLI welcome screen.

└──▷ GET THIS VERSION
$ git clone --branch v0.8.0-nightly.20260125.829ba9c4 https://github.com/QwenLM/qwen-code.git
# already have the repo? check out this version:
$ git checkout v0.8.0-nightly.20260125.829ba9c4
  • ›Adds /bug command availability in non-interactive mode.
  • ›Adds a new extensions subsystem (Feat/extension) with a detail command and improved extension validation.
  • ›Redesigns the CLI welcome screen and settings dialog.
  • ›Adds runtime-aware fetch options for Anthropic and OpenAI providers.
  • ›Uses dim colors for YOLO/auto-accept mode borders to visually distinguish that mode in the terminal UI.
Was this useful?
◆  AI Agent Frameworks

OpenClaw

Sources Release notes → v2026.1.24 NOTES

Your own personal AI assistant. Any OS.

OpenClaw v2026.1.24 adds LINE channel support, Edge TTS fallback, in-chat exec approvals via /approve, Brave freshness filtering, and gateway config.patch.

└──▷ GET THIS VERSION
$ git clone --branch v2026.1.24 https://github.com/openclaw/openclaw.git
# already have the repo? check out this version:
$ git checkout v2026.1.24
└──▷ TRY IT
Approve a pending exec command directly in chat instead of switching to another interface.
$ /approve
Set TTS to activate only for inbound messages in a session, then override per-session.
$ /tts inbound
  • ›Adds LINE channel plugin (Messaging API) with rich replies, quick replies, and plugin HTTP registry.
  • ›Adds Edge TTS provider as a keyless fallback with MP3 retry on format failures.
  • ›Adds TTS auto mode enum (off/always/inbound/tagged) with per-session /tts override.
  • ›Adds in-chat exec approval via /approve slash command across all channels including plugins.
  • ›Adds channels.telegram.linkPreview config key to toggle outbound link previews on Telegram.
+4 moreshow less
  • ›Adds Telegram DM topics as separate sessions with stable history limits via thread suffixes.
  • ›Adds Brave freshness filter parameter for time-scoped web search results.
  • ›Adds diagnostic flags for targeted debug logging, configurable via config and env override.
  • ›Refreshes Control UI dashboard design system (typography, colors, spacing).
Was this useful?
◆  Local LLM Runtimes

llama.cpp

Sources Release notes → b7833 2 RELEASES · 2026-01-25 NOTES STABLE

llama.cpp b7833 adds tiled flash attention for CPU prompt processing, improving long-context performance.

└──▷ GET THIS VERSION
$ git clone --branch b7833 https://github.com/ggml-org/llama.cpp.git
# already have the repo? check out this version:
$ git checkout b7833
  • ›Adds tiled flash attention (FA) kernel for CPU prompt-processing, replacing the prior vector kernel that degraded performance on long contexts — tile sizes tuned on AMD EPYC 64-core hardware.
1 more release in this issue · 2026-01-25
b7832 NOTES STABLE

llama.cpp b7832 adds V-less KV-cache support, reducing memory overhead for compatible model architectures.

└──▷ GET THIS VERSION
$ git clone --branch b7832 https://github.com/ggml-org/llama.cpp.git
# already have the repo? check out this version:
$ git checkout b7832
  • ›Adds V-less KV-cache mode, allowing the value cache to be omitted for model architectures that share V with K, reducing memory usage during inference.
Was this useful?
// END OF TRANSMISSION

The AI Toolchain · curated daily · January 25, 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 →