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 v2.1.170 adds access to Claude Fable 5, Anthropic's most capable generally available model.
└──▷ GET THIS VERSION
$ git clone --branch v2.1.170 https://github.com/anthropics/claude-code.git
# already have the repo? check out this version:$ git checkout v2.1.170
›Adds access to Claude Fable 5 (Mythos-class model), Anthropic's most capable generally available model.
Lightweight coding agent that runs in your terminal
Codex CLI adds standalone web search in code mode, richer MCP schema support, and improved plugin marketplace JSON output.
└──▷ GET THIS VERSION
$ git clone --branch rust-v0.139.0 https://github.com/openai/codex.git
# already have the repo? check out this version:$ git checkout rust-v0.139.0
└──▷ TRY IT
List all plugin marketplace sources in JSON to script or audit which catalogs are configured.
$ codex plugin marketplace list --json
›Enables standalone web search in code mode, including from nested JavaScript tool calls, returning plaintext results.
›Tool and connector input schemas now preserve oneOf and allOf, and large schemas retain more shallow structure when compacted for better MCP tool compatibility.
›codex doctor now includes editor and pager environment details in the local report, with raw values redacted in JSON output.
›codex plugin marketplace list --json now includes each marketplace source per entry.
›Plugin lists can now return from the cached remote catalog before refreshing in the background, improving responsiveness.
+2 moreshow less
›Adds -P as a sandbox permissions profile alias flag.
AzureOpenAIChatGenerator now accepts Secret for azure_endpoint and api_version, enabling runtime env-var resolution.
└──▷ GET THIS VERSION
$ git clone --branch v2.30.1 https://github.com/deepset-ai/haystack.git
# already have the repo? check out this version:$ git checkout v2.30.1
└──▷ USE IT
Use a single serialized pipeline across dev and prod Azure OpenAI deployments by resolving the endpoint and API version from environment variables at runtime.
python
from haystack.components.generators.chat import AzureOpenAIChatGenerator
from haystack.utils import Secret
generator = AzureOpenAIChatGenerator(
azure_deployment="gpt-4o",
azure_endpoint=Secret.from_env_var("AZURE_OPENAI_ENDPOINT"),
api_version=Secret.from_env_var("AZURE_OPENAI_API_VERSION"),
)
›Adds Secret type support to the azure_endpoint and api_version parameters of AzureOpenAIChatGenerator, allowing values to be resolved at runtime via Secret.from_env_var() so a single serialized pipeline can target different environments by swapping environment variables.
langchain-openai 1.3.0 adds support for OpenAI's apply_patch built-in tool
└──▷ GET THIS VERSION
$ git clone --branch langchain-openai==1.3.0 https://github.com/langchain-ai/langchain.git
# already have the repo? check out this version:$ git checkout langchain-openai==1.3.0
›Supports the apply_patch built-in tool from OpenAI, enabling patch-application workflows directly via the LangChain OpenAI integration.
OpenClaw v2026.6.5 adds Parallel web search, GitHub-backed ClawHub skills, native Google Chat approval cards, QMD rerank, and a QQBot @mention toggle.
└──▷ GET THIS VERSION
$ git clone --branch v2026.6.5 https://github.com/openclaw/openclaw.git
# already have the repo? check out this version:$ git checkout v2026.6.5
└──▷ TRY IT
Toggle whether your QQBot responds to group messages without an @mention, useful for dedicated bot channels that should always reply.
$ /bot-group-allways on
›Adds Parallel bundled web-search plugin with API-key discovery, guarded api.parallel.ai/v1/search endpoint support, cache-safe session IDs, and onboarding integration.
›Adds GitHub-backed ClawHub skill installation: downloads pinned GitHub commits, applies install-policy checks, and reports install telemetry on success.
›Adds native Google Chat approval card actions and click handling so approvals use platform-native cards instead of generic message flow.
›Adds /bot-group-allways on|off slash command in QQBot (with named-account and default-account support) to toggle whether group messages require an @mention before the bot replies.
›Adds QMD memory search rerank toggle for more precise memory retrieval.
+2 moreshow less
›Adds Matrix voice-message preflight and thread-aware read/reply behavior.
›Adds clearer expiring, unavailable, unresolved, and attention states to Android provider/model screens.
›Adds --log-prompts-dir flag to the server to write each incoming prompt to a separate text file in a specified directory, enabling prompt logging and audit trails.
$ git clone --branch b9575 https://github.com/ggml-org/llama.cpp.git
# already have the repo? check out this version:$ git checkout b9575
›Adds GGML_OP_COL2IM_1D CPU operator (F32, F16, BF16 with F32 accumulator) implementing the overlap-add scatter step of a 1D transposed convolution, allowing ConvTranspose1d to be factorized as a plain mul_mat followed by col2im_1d so the heavy work stays on optimized, quantizable matmul kernels.
›Bumps RPC_PROTO_PATCH_VERSION to cover the new op (GGML_OP_COUNT rises from 96 to 97); the op is appended so no existing op codes shift.
Phoenix client 2.8.0 adds span annotation, code evaluators, sandboxing, and provider-native web search for agents.
└──▷ GET THIS VERSION
$ git clone --branch arize-phoenix-client-v2.8.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:$ git checkout arize-phoenix-client-v2.8.0
›Adds a span annotation tool for agents, enabling programmatic annotation of spans during agent execution.
›Adds sandboxing and code evaluator support, allowing safe execution of custom evaluation code.
›Adds a code-evaluator authoring interface in the PXI playground for building and editing code-based evaluators.
›Adds a playground model-switching tool in PXI, enabling dynamic model selection during prompt experimentation.
›Enables provider-native web search and fetch capabilities for agents when the underlying provider supports them.
+1 moreshow less
›Stamps tool execution environment onto tool-call provider metadata, making agent infrastructure context visible in traces.
›Releases the v3 Scores API as the canonical endpoint, with a flattened response shape, cursor-based forward migration (v: 1), case-insensitive source and dataType query parameters, and strict rejection of unknown query params on the v3 list endpoint; Scores v2 is now demoted to legacy.
›Adds GOOGLE_CLOUD_UNIVERSE_DOMAIN environment variable to configure the universe domain for GCP blob storage (supports non-standard GCP endpoints).
›Adds metric alerting with a scheduler, processor, alert dispatch pipeline, and management UI.
›Exposes code evaluators (TypeScript) via public API endpoints, including an expanded allowlist of TypeScript evaluator helper functions.
›Adds in-app agent tracing with tool-call visibility in the UI and a Langfuse Docs MCP integration.
+1 moreshow less
›Adds Team/Enterprise urgent (Sev-1) support request workflows.
THE AI TOOLCHAIN