Backfill issue -130 — 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

OpenAI Codex CLI

rust-v0.120.0 NOTES

Lightweight coding agent that runs in your terminal

Codex CLI v0.120.0 adds Realtime V2 background agent streaming, improved hook TUI, MCP outputSchema support, and richer SessionStart context.

└──▷ GET THIS VERSION

$ git clone --branch rust-v0.120.0 https://github.com/openai/codex.git
# already have the repo? check out this version:
$ git checkout rust-v0.120.0

›Streams Realtime V2 background agent progress live while work is still running, and queues follow-up responses until the active response completes.
›Improves TUI hook activity display: live running hooks shown separately, completed hook output retained only when useful.
›Adds thread title as a variable available in custom TUI status line configurations.
›Includes MCP outputSchema details in Code-mode tool declarations so structured tool results carry precise typing.
›Enables SessionStart hooks to distinguish sessions created by /clear from fresh startup or resume sessions.

Was this useful?

◆ AI Agent Frameworks

OpenClaw

v2026.4.10 NOTES

Your own personal AI assistant. Any OS.

OpenClaw v2026.4.10 adds Active Memory sub-agent, local MLX speech, exec-policy CLI, gateway command discovery, and expanded QA lanes.

└──▷ GET THIS VERSION

$ git clone --branch v2026.4.10 https://github.com/openclaw/openclaw.git
# already have the repo? check out this version:
$ git checkout v2026.4.10

└──▷ TRY IT

Inspect or override your local exec approval policy without editing config files by hand.

$ openclaw exec-policy show
openclaw exec-policy preset strict
openclaw exec-policy set tools.exec.shell allow

Run your full QA suite inside a disposable Linux VM to keep host state clean and capture VM logs alongside the normal report.

$ openclaw qa suite --runner multipass

›Adds Active Memory plugin that automatically injects relevant preferences, context, and past details into ongoing chats via a dedicated memory sub-agent before each reply, with configurable context modes and live /verbose inspection.
›Adds experimental local MLX speech provider for Talk Mode on macOS, with explicit provider selection, local utterance playback, interruption handling, and system-voice fallback.
›Adds bundled Codex provider so codex/gpt-* models use Codex-managed auth, native threads, model discovery, and compaction while openai/gpt-* stays on the standard OpenAI path.
›Adds Seedance 2.0 model support to the bundled fal provider, including duration, resolution, audio, and seed metadata fields for video generation.
›Adds Microsoft Teams message actions for pin, unpin, read, react, and listing reactions.

+10 moreshow less

›Adds openclaw exec-policy command with show, preset, and set subcommands for synchronizing tools.exec.* config with the local exec approvals file.
›Adds commands.list RPC to the gateway so remote clients can discover runtime-native, text, skill, and plugin commands with surface-aware naming and serialized argument metadata.
›Adds per-provider models.providers.*.request.allowPrivateNetwork setting to enable trusted self-hosted OpenAI-compatible endpoints.
›Adds openclaw qa matrix lane backed by a disposable Matrix homeserver covering threading, reactions, restart, and allowlist transport behavior.
›Adds openclaw qa telegram lane for private-group bot-to-bot checks with native Telegram command reply threading.
›Adds --runner multipass option to openclaw qa suite for running QA scenarios inside a disposable Linux VM with report and log write-back.
›Adds MSC4357 live markers to Matrix draft preview sends and edits, enabling typewriter animation in supporting clients.
›Adds opt-in strict-agentic embedded Pi execution contract for GPT-5-family runs so plan-only or filler turns continue acting until a real blocker is reached.
›Adds provider-owned OpenAI/Codex tool schema compatibility and surfaces embedded-run replay/liveness state for long-running agent runs.
›Adds QQBot per-account streaming mode configuration via streaming.mode ("partial" | "off") instead of hardcoding it off.

Was this useful?

◆ Local LLM Runtimes

llama.cpp

b8762 5 RELEASES · 2026-04-11 NOTES STABLE

llama.cpp b8762 adds MERaLiON-2 audio-language model support for speech transcription and spoken QA

└──▷ GET THIS VERSION

$ git clone --branch b8762 https://github.com/ggml-org/llama.cpp.git
# already have the repo? check out this version:
$ git checkout b8762

›Adds PROJECTOR_TYPE_MERALION projector type enabling MERaLiON-2 multimodal audio-language models (3B and 10B) via the --mmproj flag on convert_hf_to_gguf.py with architecture MERaLiON2ForConditionalGeneration.
›Supports speech transcription (EN/ZH/MS/TA), translation, and spoken QA tasks using a Whisper large-v2 encoder with a gated MLP adaptor and Gemma2 decoder.

4 more releases in this issue · 2026-04-11

b8761 NOTES STABLE

llama.cpp b8761 adds OpenCL support for Q5_K quantization format (matrix-vector and matrix-matrix ops).

└──▷ GET THIS VERSION

$ git clone --branch b8761 https://github.com/ggml-org/llama.cpp.git
# already have the repo? check out this version:
$ git checkout b8761

›Adds OpenCL backend support for Q5_K quantization, including general matrix-vector (mv) and flattened matrix-vector multiply, plus general matrix-matrix (mm) operations.

b8755 NOTES STABLE

llama.cpp b8755 adds Hexagon backend support for Linux on Snapdragon (Debian on ex2).

└──▷ GET THIS VERSION

$ git clone --branch b8755 https://github.com/ggml-org/llama.cpp.git
# already have the repo? check out this version:
$ git checkout b8755

›Adds Hexagon backend support for Linux on Snapdragon, including Debian on ex2 hardware, with -fvectorize enabled for C/C++ CMake builds.

b8754 NOTES STABLE

llama.cpp b8754 improves Hexagon NPU op batching, buffer management, and replaces GGML_HEXAGON_EXPERIMENTAL with GGML_HEXAGON_OPFILTER

└──▷ GET THIS VERSION

$ git clone --branch b8754 https://github.com/ggml-org/llama.cpp.git
# already have the repo? check out this version:
$ git checkout b8754

└──▷ TRY IT

Disable a specific Hexagon backend op by regex during debugging, replacing the removed GGML_HEXAGON_EXPERIMENTAL variable.

$ GGML_HEXAGON_OPFILTER='MUL_MAT' ./llama-cli -m model.gguf -p 'Hello'

›Replaces the GGML_HEXAGON_EXPERIMENTAL environment variable with GGML_HEXAGON_OPFILTER, a regex-based op filter for selectively disabling Hexagon backend ops during debugging or validation.
›Introduces op request batching on the Hexagon backend: the host now prepares batches of up to 256 requests and dispatches them via a single dspqueue message, reducing inter-op overhead.
›Adds configurable opbatch sizing (OB and OQ params) and a vmem limit for op batching on the Hexagon backend.
›Introduces pinned mmap-based shared buffers for packing op batches, with explicit per-tensor L2 cache management (flush/invalidate) replacing coarse global flushes.
›Enables Flash Attention during token generation (TG) on the Hexagon backend to reduce graph splits.

+1 moreshow less

›Improves VTCM acquisition on the Hexagon backend to remove inter-op overhead, with full compatibility with QNN-HTP coexistence.

└──▷ BREAKING ON UPGRADE

!The GGML_HEXAGON_EXPERIMENTAL environment variable is removed; use GGML_HEXAGON_OPFILTER instead to disable specific ops.

b8752 NOTES STABLE

llama.cpp b8752 adds a callback interface for download progress in the common library.

└──▷ GET THIS VERSION

$ git clone --branch b8752 https://github.com/ggml-org/llama.cpp.git
# already have the repo? check out this version:
$ git checkout b8752

›Adds a callback interface for download progress in the common library, enabling programmatic monitoring of model download state.

Was this useful?

Other / Uncategorized

◆ VECTOR DB RAG

LanceDB

v0.28.0-beta.2 2 RELEASES · 2026-04-11 NOTES STABLE

LanceDB v0.28.0-beta.2 adds user_id field to ClientConfig for user identification.

└──▷ GET THIS VERSION

$ git clone --branch v0.28.0-beta.2 https://github.com/lancedb/lancedb.git
# already have the repo? check out this version:
$ git checkout v0.28.0-beta.2

›Adds user_id field to ClientConfig for associating requests with a specific user identity.

1 more release in this issue · 2026-04-11

python-v0.31.0-beta.2 NOTES STABLE

LanceDB python-v0.31.0-beta.2 adds user_id field to ClientConfig for user identification.

└──▷ GET THIS VERSION

$ git clone --branch python-v0.31.0-beta.2 https://github.com/lancedb/lancedb.git
# already have the repo? check out this version:
$ git checkout python-v0.31.0-beta.2

└──▷ USE IT

Tag client connections with a user identifier to track or audit requests per user.

python

from lancedb import ClientConfig

config = ClientConfig(user_id="[email protected]")
db = lancedb.connect("db://my-lancedb", client_config=config)

›Adds user_id field to ClientConfig for attaching a user identifier to client connections.

Was this useful?

// END OF TRANSMISSION

The AI Toolchain · curated daily · April 11, 2026
Releases & features from the open-source and commercial AI tools that practitioners actually run.

The AI Toolchain — issue -130, April 11, 2026

OpenAI Codex CLI

OpenClaw

llama.cpp

LanceDB