Backfill issue -232 — The AI Toolchain

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   # 4 tools matched

AI & LLM Tooling

◆ AI Coding Agents

SST OpenCode

v1.0.205 NOTES

The open source coding agent.

OpenCode v1.0.205 adds bash completions, themes, thinking/tool-call visibility in /copy and /export, and line-number autocomplete.

└──▷ GET THIS VERSION

$ git clone --branch v1.0.205 https://github.com/sst/opencode.git
# already have the repo? check out this version:
$ git checkout v1.0.205

›Adds bash shell completions for OpenCode CLI commands.
›Adds thinking and tool call visibility settings to the /copy and /export commands.
›Supports line numbers and ranges in autocomplete.
›Introduces themes support.

Was this useful?

Alibaba Qwen Code

v0.6.0-nightly.20251228.2bc80795 NOTES

Qwen Code v0.6.0-nightly adds automatic LLM output language detection from the system locale.

└──▷ GET THIS VERSION

$ git clone --branch v0.6.0-nightly.20251228.2bc80795 https://github.com/QwenLM/qwen-code.git
# already have the repo? check out this version:
$ git checkout v0.6.0-nightly.20251228.2bc80795

›Automatically detects the system locale to set the LLM output language, so responses match the user's OS language without manual configuration.
›Expands Russian translation with new strings for broader i18n coverage.

Was this useful?

◆ AI Agent Frameworks

holmesgpt

0.18.1 NOTES

SRE Agent - CNCF Sandbox Project

HolmesGPT 0.18.1 adds memory usage limits for bash and yaml toolsets via ulimit.

└──▷ GET THIS VERSION

$ git clone --branch 0.18.1 https://github.com/HolmesGPT/holmesgpt.git
# already have the repo? check out this version:
$ git checkout 0.18.1

›Adds ulimit-based memory limiting for the bash and yaml toolsets to cap resource consumption during automated investigations.

Was this useful?

◆ Local LLM Runtimes

llama.cpp

b7563 2 RELEASES · 2025-12-28 NOTES STABLE

llama.cpp b7563 adds support for the Plamo3 model architecture.

└──▷ GET THIS VERSION

$ git clone --branch b7563 https://github.com/ggml-org/llama.cpp.git
# already have the repo? check out this version:
$ git checkout b7563

›Adds support for the Plamo3 model architecture, including chat template integration.

1 more release in this issue · 2025-12-28

b7557 NOTES STABLE

llama.cpp b7557 adds six new x86-64 CPU architecture targets when building with GGML_CPU_ALL_VARIANTS=On

└──▷ GET THIS VERSION

$ git clone --branch b7557 https://github.com/ggml-org/llama.cpp.git
# already have the repo? check out this version:
$ git checkout b7557

└──▷ TRY IT

Build llama.cpp with all x86-64 CPU variants — including the newly added zen4, cascadelake, and cooperlake targets — to produce optimized binaries for each micro-architecture.

$ cmake -B build -DGGML_CPU_ALL_VARIANTS=On && cmake --build build --config Release

›Adds ivybridge, piledriver, cannonlake, cascadelake, cooperlake, and zen4 as supported x86-64 CPU backends when building with GGML_CPU_ALL_VARIANTS=On

Was this useful?

// END OF TRANSMISSION

The AI Toolchain · curated daily · December 28, 2025
Releases & features from the open-source and commercial AI tools that practitioners actually run.

The AI Toolchain — issue -232, December 28, 2025

SST OpenCode

Alibaba Qwen Code

holmesgpt

llama.cpp