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.
Agno v2.1.10 adds experimental Culture for collective agent learning, Gmail mark-as-read/unread tools, and standalone Knowledge on AgentOS.
└──▷ GET THIS VERSION
$ git clone --branch v2.1.10 https://github.com/agno-agi/agno.git
# already have the repo? check out this version:$ git checkout v2.1.10
›Adds mark-as-read and mark-as-unread functions to the Gmail toolkit.
›[Experimental] Introduces Culture, a shared space for agents to think, write, and build on each other's ideas, enabling collective learning across an agent group.
›Enables Knowledge to be added and managed via any AgentOS interface without requiring it to be attached to an Agent or Team.
Framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks.
CrewAI 1.1.0 adds multi-provider LLM support in InternalInstructor, a mypy plugin base, and improves QdrantVectorSearchTool.
└──▷ GET THIS VERSION
$ git clone --branch 1.1.0 https://github.com/crewAIInc/crewAI.git
# already have the repo? check out this version:$ git checkout 1.1.0
›Adds multi-provider LLM support to InternalInstructor, enabling structured output extraction across different LLM backends.
›Introduces a mypy plugin base for improved static type checking of CrewAI code.
›Improves QdrantVectorSearchTool for better vector search integration.
$ git clone --branch prebuilt==0.6.5 https://github.com/langchain-ai/langgraph.git
# already have the repo? check out this version:$ git checkout prebuilt==0.6.5
›Adds Redis node-level cache via feat(langgraph): implement redis node level cache, enabling per-node result caching backed by Redis.
›Adds query-parameter support to the Python SDK client (feat(sdk-py): client qparams), allowing callers to pass arbitrary query parameters through SDK calls.
Continue 1.5.0 adds background agents, secrets parsing for all CLI flags, and a session-selector preview panel.
└──▷ GET THIS VERSION
$ git clone --branch @continuedev/[email protected] https://github.com/continuedev/continue.git
# already have the repo? check out this version:$ git checkout @continuedev/[email protected]
›Adds full secrets parsing for all CLI flags, so secrets are resolved across every flag passed to the CLI.
›Adds a preview panel to the session selector surfaced by cn ls and /resume, letting users inspect session history before resuming.
›Adds background agent creation and execution, enabling agents to run without an active foreground session.
›Reports cache write tokens from the Anthropic OpenAI adapter, surfacing prompt-cache cost data.
›Returns fetch errors to the agent runtime so agents can handle network failures programmatically.
Continue v1.2.10 adds token usage tracking, message editing in CLI, and renames workflows to agent files.
└──▷ GET THIS VERSION
$ git clone --branch v1.2.10-vscode https://github.com/continuedev/continue.git
# already have the repo? check out this version:$ git checkout v1.2.10-vscode
›Adds token usage tracking to the OpenAI adapter, surfacing consumption data per request.
›Decouples anonymous telemetry from the CONTINUE_CLI_ENABLE_TELEMETRY environment variable, giving finer-grained control over telemetry opt-out.
›Allows the --agent flag to be used without a prompt in headless mode.
›Renames 'workflows' to 'agent files' throughout the product.
›Makes chat messages editable in the CLI and adds the ability to navigate back to an older message.
+1 moreshow less
›Rehauled onboarding flow updated for new billing.
└──▷ BREAKING ON UPGRADE
!Bundled esbuild is removed from the VSCode extension; users must now have esbuild installed separately for config.ts to work.
An open-source AI agent that brings the power of Gemini directly into your terminal.
gemini-cli v0.11.0-nightly adds a message bus and policy engine, plus full extension passing to context.
└──▷ GET THIS VERSION
$ git clone --branch v0.11.0-nightly.20251021.e72c00cf https://github.com/google-gemini/gemini-cli.git
# already have the repo? check out this version:$ git checkout v0.11.0-nightly.20251021.e72c00cf
›Implements a message bus and policy engine for internal event routing and rule enforcement.
›Passes whole extensions (not just context files) to the model context, giving richer extension-aware sessions.
LanceDB python-v0.25.3-beta.2 exposes storage options directly on table objects.
└──▷ GET THIS VERSION
$ git clone --branch python-v0.25.3-beta.2 https://github.com/lancedb/lancedb.git
# already have the repo? check out this version:$ git checkout python-v0.25.3-beta.2
›Exposes storage options on table objects, enabling per-table storage configuration.
LanceDB v0.22.3-beta.2 exposes storage options directly on table objects.
└──▷ GET THIS VERSION
$ git clone --branch v0.22.3-beta.2 https://github.com/lancedb/lancedb.git
# already have the repo? check out this version:$ git checkout v0.22.3-beta.2
›Exposes storage options on table instances, enabling per-table storage configuration.
Milvus 2.6.4 adds Struct-in-ARRAY for complex data modeling, enables JSON Shredding by default, and supports Qwen GTE-rerank-v2 via DashScope.
└──▷ GET THIS VERSION
$ git clone --branch v2.6.4 https://github.com/milvus-io/milvus.git
# already have the repo? check out this version:$ git checkout v2.6.4
›Introduces DataType.ARRAY of Struct elements, enabling Array of Vector storage where each row can contain multiple vectors for complex data modeling and search.
›Enables JSON Shredding by default, improving query performance and efficiency across JSON fields.
›Adds disk quota for loaded binlog size to prevent query node load failures under memory pressure.
›Adds load parameters for vector index configuration.
›Adds mmap support for struct array in MemVectorIndex.
+6 moreshow less
›Adds caching layer management for TextMatchIndex.
›Adds accesslog.$consistency_level field to access logs representing the actual consistency level used.
›Adds access log field for template value length information.
›Supports the Qwen GTE-rerank-v2 reranking model via DashScope integration.
›Allows overwriting the current index type during index build.
THE AI TOOLCHAIN