Backfill issue -087 — 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   # 2 tools matched

AI & LLM Tooling

◆ Local LLM Runtimes

LocalAI

v4.3.0 NOTES

LocalAI v4.3.0 adds keyless cosign backend verification, prompt cache on by default, per-API-key usage tracking, and distributed mode v3.

└──▷ GET THIS VERSION

$ git clone --branch v4.3.0 https://github.com/mudler/LocalAI.git
# already have the repo? check out this version:
$ git checkout v4.3.0

└──▷ USE IT

Pin a gallery's backend images to signatures issued after a specific date, revoking all earlier keyless Fulcio certs for that gallery.

yaml

verification:
  issuer_regex: "^https://token\.actions\.githubusercontent\.com$"
  identity_regex: "^https://github\.com/mudler/LocalAI/\.github/workflows/backend_merge\.yml@.*$"
  not_before: "2026-05-22T00:00:00Z"

Identify which API keys and users are consuming the most GPU tokens — useful for chargeback or quota enforcement.

$ curl -s -H 'Authorization: Bearer <admin-token>' 'http://localhost:8080/api/auth/admin/usage/sources?user_id=<uid>&api_key_id=<kid>'

›Adds --require-backend-integrity flag (or LOCALAI_REQUIRE_BACKEND_INTEGRITY=true) to enforce strict mode: missing verification: policy or empty SHA256 in gallery YAML becomes a hard-fail instead of a warning.
›Adds verification: block to gallery YAML supporting issuer_regex, identity_regex, and not_before fields for keyless cosign/sigstore-go signature verification of backend OCI images with digest pinning and TUF root caching.
›Adds LOCALAI_TRACING_MAX_BODY_BYTES environment variable (default 64 KiB) to cap captured request/response body size in trace middleware, recording body_truncated and original body_bytes fields when truncation occurs.
›Adds LOCALAI_NATS_BACKEND_INSTALL_TIMEOUT and LOCALAI_NATS_BACKEND_UPGRADE_TIMEOUT environment variables (default 15 minutes, previously hardcoded 3 minutes) to control distributed backend install timeouts.
›Adds new API endpoints GET /api/auth/usage/sources (self) and GET /api/auth/admin/usage/sources (admin, with user_id / api_key_id filters and 200-key truncation) for per-API-key and per-user token attribution.

+9 moreshow less

›Changes kv_unified default to true in grpc-server.cpp and prompt_cache_all default to true at the YAML layer, enabling llama-cpp server-side prompt cache out of the box — collapsing repeated system-prompt prefill from minutes to seconds.
›Adds cache_idle_slots and checkpoint_every_nt as new model-config option keys for tuning llama-cpp KV cache behavior.
›Changes POST /api/nodes/:id/backends/install to return HTTP 202 plus a jobID immediately instead of blocking up to 3 minutes, with per-node scoped opcache and async streaming progress events on nodes.<nodeID>.backend.install.<opID>.progress NATS subjects.
›Adds unified /app/backend-logs/:modelId route that is mode-aware: routes to local WebSocket view in standalone mode, or to a per-node picker in distributed mode, with ?from= deep-link timestamp support.
›Adds a Sources tab to the React Usage page with a source-mix ribbon, top-7 + Other time chart, and searchable/sortable table; admin view rolls up (source, user_id, user_name) and shows owning account per named key.
›Adds usage_records fields Source (apikey / web / legacy), APIKeyID, and APIKeyName with idempotent backfill of pre-feature rows on InitDB; revoked keys remain visible in history as (revoked).
›Adds flake.nix and flake.lock for a reproducible, dockerless LocalAI setup on NixOS plus a dev shell.
›Adds a distributed test harness under tests/distributed/ for regression testing of multi-node routing behavior.
›Implements per-request replica routing in SmartRouter.Route using PickBestReplica with in_flight ASC, last_used ASC, available_vram DESC ordering, and memoizes probeHealth per (nodeID, addr) with a 30-second TTL and singleflight coalescing.

Was this useful?

◆ AI Agent Frameworks

OpenClaw

v2026.5.22 NOTES

Your own personal AI assistant. Any OS.

OpenClaw v2026.5.22 adds meeting-notes capture, 4,100× faster model listing, poll sender SDK, embedding provider API, and chat session search.

└──▷ GET THIS VERSION

$ git clone --branch v2026.5.22 https://github.com/openclaw/openclaw.git
# already have the repo? check out this version:
$ git checkout v2026.5.22

└──▷ TRY IT

Access read-only meeting notes captured from Discord voice or manual transcript imports.

$ openclaw meeting-notes

›Adds openclaw meeting-notes CLI with auto-start capture, manual transcript imports, and Discord voice as the first live source via a new external meeting-notes plugin.
›Pre-warms provider auth-state at gateway startup, dropping /models and model-listing call cost from ~20 s to ~5 ms (~4,100× speedup).
›Adds search and Load More pagination to the Control UI chat session picker so older conversations remain reachable.
›Enables configurable agentComponents.ttlMs callback registry lifetime for Discord long-running component workflows, with per-account overrides and a 24-hour cap.
›Adds a generic channel-message poll sender to the Plugin SDK so channel plugins can deliver polls without depending on channel-specific SDK facades.

+10 moreshow less

›Adds a general embeddingProviders capability contract and registration API so embeddings become a reusable provider surface outside memory-specific adapters.
›Adds row-level session workflow helpers to the Plugin SDK and deprecates loadSessionStore so plugins can read and patch sessions without the legacy whole-store shape.
›Extends the OpenTelemetry smoke harness to prove trace, metric, and log export, and adds first-class Prometheus and observability smoke aliases.
›Adds curated mock JSONL replay fixtures and first-drift reporting to QA-Lab for runtime-parity audits.
›Reuses xAI OAuth auth profiles for Grok web_search, threads active-agent auth through web search, and adds Grok model aliases.
›Starts classic onboarding when bare openclaw runs before an authored config exists, keeping configured installs on Crestodian.
›Lazy-loads startup-idle plugin work and the embedded ACPX runtime so Gateway health and ready signals no longer wait on unused handler trees.
›Ships the root npm package and OpenClaw-owned plugins with generated shrinkwrap and bundled plugin runtime dependencies, requiring review for lockfile changes.
›Limits default sub-agent bootstrap context to AGENTS.md and TOOLS.md, excluding persona, identity, user, memory, heartbeat, and setup files from delegated workers by default.
›Adds openclaw-landable-bug-sweep maintainer skill for producing small, reviewed, CI-green bugfix PRs from issue/PR sweeps.

└──▷ BREAKING ON UPGRADE

!Default sub-agent bootstrap context is now limited to AGENTS.md and TOOLS.md; persona, identity, user, memory, heartbeat, and setup files are no longer passed to delegated workers by default.
!Gemini CLI is no longer auto-probed for media understanding; Antigravity CLI is used only as a lower-priority image/video fallback after configured provider APIs.
!The old sender-owner tool gating path is removed; configured tools are now always visible for trusted sessions while command and channel-action auth still carry real sender identity.

Was this useful?

// END OF TRANSMISSION

The AI Toolchain · curated daily · May 24, 2026
Releases & features from the open-source and commercial AI tools that practitioners actually run.

The AI Toolchain — issue -087, May 24, 2026

LocalAI

OpenClaw