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.
Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflows - all through natural language commands.
Claude Code v2.1.152 adds auto-fix code review, hook-driven skill reloading, a MessageDisplay hook, and live thinking indicators.
└──▷ GET THIS VERSION
$ git clone --branch v2.1.152 https://github.com/anthropics/claude-code.git
# already have the repo? check out this version:$ git checkout v2.1.152
└──▷ TRY IT
Run a code review and immediately apply all suggestions to your working tree in one step.
$ claude /code-review --fix
Restrict which tools are available when a skill is active — useful for locked-down review or planning skills.
yaml
# In a skill's frontmatter (e.g., .claude/skills/review.md)
---
disallowed-tools:
- Bash
- Edit
---
Reload skills installed by a SessionStart hook without restarting the session.
$ claude /reload-skills
›Adds --fix flag to /code-review: automatically applies review findings (reuse, simplification, efficiency suggestions) to the working tree after review; /simplify now invokes /code-review --fix.
›Skills and slash commands can now set disallowed-tools in frontmatter to restrict which tools the model can use while that skill is active.
›Adds /reload-skills command to re-scan skill directories mid-session without restarting.
›SessionStart hooks can now return reloadSkills: true to make newly installed skills available in the same session.
›SessionStart hooks can now set the session title via hookSpecificOutput.sessionTitle on startup and resume.
+11 moreshow less
›Adds MessageDisplay hook event, enabling hooks to transform or hide assistant message text as it is rendered.
›Adds pluginSuggestionMarketplaces managed setting, allowing admins to allowlist org marketplaces whose plugins may be suggested via context-aware tips.
›claude plugin marketplace remove now accepts --scope user|project|local for symmetry with marketplace add, install, and uninstall.
›Automatically switches to the configured --fallback-model for the rest of the session when the primary model is not found, instead of failing every request.
›Auto mode no longer requires opt-in consent.
›Vim mode: / in NORMAL mode now opens reverse history search (like Ctrl+R), matching bash/zsh vi-mode behavior.
›The /usage breakdown now includes large session files, scanned with a streaming read to keep memory usage flat.
›Thinking summaries in collapsed groups now render as markdown, stay readable for at least 3 seconds, and cap at 10 lines; Ctrl+O shows the full thinking.
›In fullscreen mode, the 'Thinking for Ns' indicator now counts up live while the model thinks and retains its value if interrupted mid-thought.
›Post-response timer now shows 'Waiting for N background agents/workflows to finish' and reports cumulative time once results are processed.
›Adds session entrypoint as an OpenTelemetry metric attribute (app.entrypoint), opt-in via OTEL_METRICS_INCLUDE_ENTRYPOINT=true.
ChatPerplexity gains a use_responses_api flag to opt into Perplexity's Responses API.
└──▷ GET THIS VERSION
$ git clone --branch langchain-perplexity==1.3.0 https://github.com/langchain-ai/langchain.git
# already have the repo? check out this version:$ git checkout langchain-perplexity==1.3.0
└──▷ USE IT
Opt into the Perplexity Responses API when initializing ChatPerplexity for access to Responses-API-specific capabilities.
python
from langchain_perplexity import ChatPerplexity
llm = ChatPerplexity(use_responses_api=True)
response = llm.invoke('Summarize the latest AI research.')
print(response.content)
›Adds use_responses_api flag to ChatPerplexity to enable use of the Perplexity Responses API.
OpenClaw v2026.5.26 adds transcript capture, named auth profiles, reaction approvals, QA coverage matching, and a live Activity tab.
└──▷ GET THIS VERSION
$ git clone --branch v2026.5.26 https://github.com/openclaw/openclaw.git
# already have the repo? check out this version:$ git checkout v2026.5.26
└──▷ TRY IT
Discover matching QA scenarios from existing metadata before committing to a full live or remote run — useful for scoping a proof lane to a specific feature area.
›Adds core transcript capture and source-provider support for transcript-backed meeting summaries, with a new CLI surface and cleaned user-turn persistence.
›Adds named model login profiles with credential migration for Hermes, OpenCode, and Codex auth profiles, including explicit opt-out and non-interactive controls.
›Adds qa coverage --match <query> subcommand for focused proof selection against existing scenario metadata before running live or remote lanes.
›Adds Signal, iMessage, and WhatsApp thumb/reaction approval support so mobile approval flows work without textual /approve commands.
›Adds Android pair-new-gateway action and iOS direct realtime Talk mode with compact toolbar status and responsive voice waveform feedback.
+10 moreshow less
›Adds an alpha-bucket model picker for Discord when provider or model lists exceed 25 items, grouping entries by first-letter ranges instead of prev/next pagination.
›Adds an ephemeral Activity tab in Control UI for sanitized live tool activity summaries without persisting raw telemetry.
›Adds OpenTelemetry LLM content spans and alertable telemetry signals for blocked tools, failover, stale sessions, liveness, oversized payloads, and webhook ingress.
›Adds gateway secret-preparation tracing, skill/tool usage classification, and model stream progress surfacing for improved observability.
›Forwards OpenAI sampling parameters through the Gateway and exposes estimated context-budget status for active agent runs.
›Queues prompts submitted while an agent is busy and shows explicit fast-mode state plus richer systemd Gateway hygiene in status output.
›Defaults cron.maxConcurrentRuns to 8 so scheduled automations run in parallel without explicit configuration.
›Replaces the Sharp image backend with Rastermill for metadata, resizing, EXIF orientation, and PNG alpha-preserving optimization, removing the Sharp and WhatsApp Jimp dependencies.
›Exposes shared realtime voice SDK surface for turn-context tracking, output activity tracking, consult question matching, and activation-name matching, reused across Discord, browser voice, and meeting surfaces.
›Adds Plugin SDK reaction approval helpers and makes diagnostic event root exports discoverable across function-name and alias-bound module graphs.
└──▷ BREAKING ON UPGRADE
!The Sharp image backend and the WhatsApp Jimp fallback are removed; image processing now uses Rastermill, so any environment relying on Sharp being installed by OpenClaw will no longer have it.
$ git clone --branch v1.103.0 https://github.com/pydantic/pydantic-ai.git
# already have the repo? check out this version:$ git checkout v1.103.0
└──▷ USE IT
Enable eager input streaming when using Anthropic-compatible models via OpenRouter to reduce time-to-first-token.
python
from pydantic_ai.models.openrouter import OpenRouterModel
model = OpenRouterModel(
'anthropic/claude-3-5-sonnet',
anthropic_eager_input_streaming=True,
)
›Adds list_prompts and get_prompt methods to McpServer, enabling MCP clients to discover and retrieve prompts from a server.
›Supports anthropic_eager_input_streaming in OpenRouterModel, bringing eager input streaming parity with the native Anthropic model.
›Round-trips message timestamps through VercelAIAdapter's UIMessage.metadata, preserving original message timing across the adapter boundary.
LocalAI v4.3.2 adds model routing, PII filtering, cloud proxies, LTX-2 video generation, and a native object detection backend.
└──▷ GET THIS VERSION
$ git clone --branch v4.3.2 https://github.com/mudler/LocalAI.git
# already have the repo? check out this version:$ git checkout v4.3.2
›Adds X-LocalAI-Node response header (gated) in distributed/middleware mode to expose which node served a request.
›Adds middleware-layer model routing, PII filtering, and cloud model proxy support for request pipelines.
›Adds rfdetr-cpp native backend enabling object detection and segmentation without external dependencies.
›Adds LTX-2 and LTX-2.3 GGUF support to the stablediffusion-ggml backend, including gallery entries for image-to-video and first-last-frame-to-video variants.
›Adds 'Fits in my GPU' toggle filter on the Install Models UI screen to surface only models that fit available VRAM.
llama.cpp b9370 adds Q4_1 quantization support for Hexagon MUL_MAT and MUL_MAT_ID operations via HVX and HMX.
└──▷ GET THIS VERSION
$ git clone --branch b9370 https://github.com/ggml-org/llama.cpp.git
# already have the repo? check out this version:$ git checkout b9370
›Adds Q4_1 quantization support to Hexagon MUL_MAT and MUL_MAT_ID operations, with both HVX-only and HMX paths, enabling the Hexagon backend to offload nearly the entire compute graph.
›Adds early-wake support and op-batch completion polling on the Hexagon backend, reducing inference latency when the backend claims full graph ownership.
llama.cpp b9366 adds Vulkan REPEAT op support for f16-to-f16 tensors.
└──▷ GET THIS VERSION
$ git clone --branch b9366 https://github.com/ggml-org/llama.cpp.git
# already have the repo? check out this version:$ git checkout b9366
›Adds Vulkan GPU pipeline support for the REPEAT operation on f16-to-f16 tensor types, enabling models that use this op to run fully on Vulkan backends.
llama.cpp b9354 adds MiniCPM5 tokenizer support for GGUF conversion
└──▷ GET THIS VERSION
$ git clone --branch b9354 https://github.com/ggml-org/llama.cpp.git
# already have the repo? check out this version:$ git checkout b9354
›Adds MiniCPM5 pre-tokenizer support to convert_hf_to_gguf_update.py, enabling conversion of MiniCPM5 models to GGUF format with correct BPE tokenization via hardcoded regex handling in llama-vocab.cpp.
Phoenix v16.3.0 adds drag-to-zoom on metric charts, skills for the PXI agent, and an expanded model selector.
└──▷ GET THIS VERSION
$ git clone --branch arize-phoenix-v16.3.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:$ git checkout arize-phoenix-v16.3.0
›Adds drag-to-zoom interaction on project metric charts for faster time-range exploration.
›Adds skills capability to the PXI agent, expanding what the built-in AI agent can do.
›Expands the PXI settings model selector with additional model options.
THE AI TOOLCHAIN