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 v2.1.149 adds per-category usage breakdowns, keyboard-scrollable diffs, GFM task list rendering, and enterprise MCP connector controls.
└──▷ GET THIS VERSION
$ git clone --branch v2.1.149 https://github.com/anthropics/claude-code.git
# already have the repo? check out this version:$ git checkout v2.1.149
└──▷ TRY IT
Check which categories (skills, subagents, plugins, MCP servers) are eating into your usage limits before hitting a cap.
$ /usage
Allow all claude.ai cloud MCP connectors in an enterprise managed deployment, alongside your existing managed-mcp.json config.
json
{ "allowAllClaudeAiMcps": true }
›Adds per-category breakdown in /usage showing what's consuming your limits — skills, subagents, plugins, and per-MCP-server cost.
›Enables keyboard scrolling in /diff detail view via arrows, j/k, PgUp/PgDn, Space, and Home/End.
›Renders GFM task list checkboxes (- [ ] todo / - [x] done) in Markdown output instead of plain bullets.
Cline CLI v3.0.11 adds Vertex Gemini auth via Google auth and full model list, plus tool-name tracking in session history.
└──▷ GET THIS VERSION
$ git clone --branch cli-v3.0.11 https://github.com/cline/cline.git
# already have the repo? check out this version:$ git checkout cli-v3.0.11
›Supports Vertex Gemini authentication via Google auth when gcp.projectId is configured, exposing the full Vertex model list beyond Claude-only models.
›Includes tool names in tool result content blocks so message logs and session history consistently track which tool produced each result.
Jan v0.8.0 adds MiniMax cloud provider, /v1/orchestrations MCP API, Chain of Thought, API key rotation, and a Rust-native inference backend.
└──▷ GET THIS VERSION
$ git clone --branch v0.8.0 https://github.com/janhq/jan.git
# already have the repo? check out this version:$ git checkout v0.8.0
└──▷ TRY IT
Trigger server-side MCP tool orchestration without relying on the client — useful for headless or API-only deployments.
$ curl -X POST http://localhost:1337/v1/orchestrations \
-H 'Content-Type: application/json' \
-d '{"model": "gpt-4o", "messages": [{"role": "user", "content": "Search the web for the latest CVEs in OpenSSL."}]}'
Enable server-side tool execution for /chat/completions via the Jan GUI so MCP tools run on the server rather than requiring client approval each call.
📍In the Jan GUI, go to Settings › Connectors, select your MCP server, and toggle 'Server-side tool execution' on.
›Adds /v1/orchestrations API endpoint for server-side MCP tool execution.
›Adds GUI toggle for server-side tool execution on /chat/completions.
›Adds optional lightweight router model for MCP tool routing, with routing telemetry.
›Adds feat(llamacpp): expands llama.cpp server flags and wires llama.cpp-only sampling parameters.
›Adds MiniMax as a predefined cloud provider with M2.7 as the default model.
+18 moreshow less
›Adds configurable token limits and auto-compact for remote model providers.
›Adds API key fallbacks with automatic rotation across remote model providers.
›Adds options to preserve user data during a factory reset.
›Moves backend download and management logic to a Rust plugin with dependency verification.
›Implements initial Chain of Thought (CoT) display for reasoning-capable models.
›Adds paragraph-level 'Edit with AI' for assistant markdown responses.
›Adds auto-summarize of thread titles after the first response, with cancellable background inference.
›Adds message queuing during streaming with auto-send, two-stage stop, and editable pending chips in the input area.
›Stores all user settings in local files instead of browser localStorage.
›Splits the provider list into local and remote sections in the UI.
›Adds an assistant chat button to start conversations directly from an assistant.
›Adds optional health-check auto-restart for crashed model sessions.
›Adds a regenerate button on failed message responses.
›Adds a file attachment progress bar.
›Expands supported file types for document attachments to include many additional extensions.
›Adds Korean, Catalan, Hindi language localizations.
›Renames MCP to 'Connectors' in the Settings sidebar.
›Allows retrieving the last typed message by pressing the up arrow key.
$ git clone --branch b9291 https://github.com/ggml-org/llama.cpp.git
# already have the repo? check out this version:$ git checkout b9291
›Improves SYCL MoE prefill throughput by replacing an O(n_as * n_routed_rows) expert-routing loop in k_copy_src1_to_contiguous with a counting sort-based procedure of O(n_as + n_routed_rows) complexity, enabling faster batch inference on SYCL backends.
Vulkan backend gains fused snake activation kernel for audio decoder models (BigVGAN, Vocos) across F32/F16/BF16.
└──▷ GET THIS VERSION
$ git clone --branch b9279 https://github.com/ggml-org/llama.cpp.git
# already have the repo? check out this version:$ git checkout b9279
›Adds a fused Vulkan kernel (snake.comp) that collapses the 5-op snake activation decomposition (mul, sin, sqr, mul, add) into a single elementwise dispatch via ggml_vk_snake_dispatch_fused, accelerating audio decoder models such as BigVGAN and Vocos on Vulkan backends across F32, F16, and BF16 precisions.
llama.cpp server now exposes prompt token counts in the /slots endpoint for client-side progress monitoring.
└──▷ GET THIS VERSION
$ git clone --branch b9276 https://github.com/ggml-org/llama.cpp.git
# already have the repo? check out this version:$ git checkout b9276
›Adds n_prompt_tokens, n_prompt_tokens_processed, and n_prompt_tokens_cache fields to the GET /slots JSON response, enabling clients to monitor prompt evaluation progress during processing.
vMLX 1.5.47 adds Tahoe-native DMG for macOS Tahoe, tightens parser boundaries across model families, and expands DSV4 release guards.
└──▷ GET THIS VERSION
$ git clone --branch v1.5.47 https://github.com/jjang-ai/vmlx.git
# already have the repo? check out this version:$ git checkout v1.5.47
›Adds a Tahoe-native DMG (vMLX-1.5.47-tahoe-arm64.dmg) for macOS Tahoe users who want native macosx_26 MLX wheels, alongside the existing Sequoia-compatible DMG (vMLX-1.5.47-sequoia-arm64.dmg).
›Adds stronger parser boundaries so non-reasoning families such as Qwen2 and Qwen2-VL no longer silently inherit reasoning parsers, while MiniMax, DSV4, ZAYA, Hy3, Gemma, and GLM parser rows remain covered.
›Adds DSV4-specific release guards for stale native-MTP launch args, cache/prefix policy, and JANG source parity.
LangGraph SDK 0.3.15 adds metadata filtering for cron job search and count operations.
└──▷ GET THIS VERSION
$ git clone --branch sdk==0.3.15 https://github.com/langchain-ai/langgraph.git
# already have the repo? check out this version:$ git checkout sdk==0.3.15
└──▷ USE IT
Filter cron job searches by metadata to find only crons matching specific labels or properties.
Milvus v2.6.17 adds ARRAY_APPEND and ARRAY_REMOVE partial update operators for Array fields via gRPC and REST APIs.
└──▷ GET THIS VERSION
$ git clone --branch v2.6.17 https://github.com/milvus-io/milvus.git
# already have the repo? check out this version:$ git checkout v2.6.17
›Adds ARRAY_APPEND and ARRAY_REMOVE partial update operators for Array fields, exposed through both gRPC and REST upsert APIs.
›Improves load/search isolation by using separate C++ executor pools and converting SegmentLoad and ReopenSegment to async futures with proper context cancellation.
THE AI TOOLCHAIN