Backfill issue -086 — 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   # 3 tools matched

AI & LLM Tooling

◆ AI Coding Agents

Cline

v3.85.0 NOTES

Autonomous coding agent as an SDK, IDE extension, or CLI assistant.

Cline v3.85.0 adds GPT-5.5, DeepSeek V4, Gemini 3.5 Flash model support and a new LG dashboard webhook integration.

└──▷ GET THIS VERSION

$ git clone --branch v3.85.0 https://github.com/cline/cline.git
# already have the repo? check out this version:
$ git checkout v3.85.0

›Adds GPT-5.5 model support via SAP AI Core provider.
›Adds DeepSeek V4 Flash and Pro models.
›Adds Gemini 3.5 Flash to Gemini and Vertex providers.
›Adds /lg-task URI webhook integration for LG dashboard flows.

Was this useful?

Charm Crush

v0.72.0 NOTES

Glamourous agentic coding for all

Crush v0.72.0 adds ctrl+y YOLO toggle, skill descriptions, session scrollbar, and auto-expanded TODO list.

└──▷ GET THIS VERSION

$ git clone --branch v0.72.0 https://github.com/charmbracelet/crush.git
# already have the repo? check out this version:
$ git checkout v0.72.0

›Adds ctrl+y keybinding to instantly toggle YOLO mode (with on-screen notification) without opening the command palette.
›Displays descriptions alongside user-invocable skill commands in the skill picker for easier discovery.
›Adds a scrollbar to the sessions list dialog for easier navigation of long session lists.
›Auto-expands the TODO list by default when terminal height is sufficient; toggle with ctrl+t.

Was this useful?

◆ Local LLM Runtimes

llama.cpp

b9319 2 RELEASES · 2026-05-25 NOTES STABLE

llama.cpp b9319 adds gguf_init_from_callback and gguf_init_from_buffer for flexible GGUF loading from memory and streaming sources.

└──▷ GET THIS VERSION

$ git clone --branch b9319 https://github.com/ggml-org/llama.cpp.git
# already have the repo? check out this version:
$ git checkout b9319

›Adds gguf_init_from_buffer to initialize a GGUF context directly from an in-memory buffer, enabling model loading without file I/O.
›Adds gguf_init_from_callback with a gguf_reader_callback_t callback type to stream GGUF data chunk-by-chunk, with max_chunk_read == 0 meaning SIZE_MAX (unlimited chunk size) and max_expected_size and offsets typed as uint64_t for large-model safety.

1 more release in this issue · 2026-05-25

b9310 NOTES STABLE

llama.cpp b9310 adds --checkpoint-min-step flag and autoparser message-barrier detection for smarter server checkpointing.

└──▷ GET THIS VERSION

$ git clone --branch b9310 https://github.com/ggml-org/llama.cpp.git
# already have the repo? check out this version:
$ git checkout b9310

└──▷ TRY IT

Prevent excessive checkpoint creation during long prompts by setting a minimum token step between checkpoints.

$ llama-server --checkpoint-min-step 256 -m model.gguf

›Adds --checkpoint-min-step CLI flag to control minimum spacing between server context checkpoints.
›Adds common_chat_split_by_role to split chat output by role, enabling message-span extraction from chat templates.
›Supports autoparser detection for message barriers, allowing the server to automatically identify prompt split points without manual configuration.
›Enables multimodal prompt support when mapping text/template positions to server prompt tokens during checkpoint creation.

Was this useful?

// END OF TRANSMISSION

The AI Toolchain · curated daily · May 25, 2026
Releases & features from the open-source and commercial AI tools that practitioners actually run.

The AI Toolchain — issue -086, May 25, 2026

Cline

Charm Crush

llama.cpp