{"full_name":"crewAIInc/crewAI","owner":"crewAIInc","name":"crewAI","url":"https://github.com/crewAIInc/crewAI","description":"Framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks.","homepage":"https://crewai.com","topics":[],"language":"Python","license":"MIT","avatar":"https://avatars.githubusercontent.com/u/170677839?v=4","created_at":"2023-10-27T03:26:59Z","pushed_at":"2026-11-10T00:05:12Z","metrics":{"stars":60720,"forks":9136,"watchers":386,"issues":2864,"prs":5897,"releases":252,"issues_open":null,"issues_closed":null,"prs_open":null,"prs_closed":null,"prs_merged":null,"discussions":0},"growth":{"day":{"stars":41,"forks":19,"base_day":"2026-11-09"}},"history":{"dates":["2026-11-09","2026-11-10"],"stars":[60679,60720],"forks":[9117,9136],"watchers":[386,386],"issues_open":[null,null],"prs_open":[null,null]},"boards":{},"same_owner":[],"issues":[{"number":5802,"title":"Tool re-execution on task retry has no idempotency guard — duplicate payments, emails, trades possible","comments":220,"created_at":"2026-05-14T03:00:55Z"},{"number":5888,"title":"[FEATURE]:Governance middleware hook for tool call authorization","comments":148,"created_at":"2026-05-21T11:37:57Z"},{"number":6025,"title":"[FEATURE] Runtime release-control mediation layer before agent/tool execution","comments":127,"created_at":"2026-06-03T07:53:04Z"},{"number":6414,"title":"[FEATURE] Native deterministic guardrail to prevent infinite agent delegation and tool loops","comments":53,"created_at":"2026-07-01T14:39:09Z"},{"number":5556,"title":"[FEATURE] Add pre-execution validation for agent-to-agent actions","comments":34,"created_at":"2026-04-20T17:27:02Z"},{"number":6043,"title":"[FEATURE] Memory write guards for multi-agent crews — prevent cross-agent memory poisoning","comments":31,"created_at":"2026-06-04T20:37:16Z"},{"number":6221,"title":"Agent governance: deterministic tool permission gating for crew agents","comments":14,"created_at":"2026-06-18T17:02:06Z"},{"number":6072,"title":"[BUG] `human_input=True`: the feedback prompt references a \"Final Result above\" that is never displayed unless `verbose=True`","comments":14,"created_at":"2026-06-08T20:12:44Z"}],"discussions":[],"latest_release":{"name":"1.15.38","tag":"1.15.38","published_at":"2026-11-08T19:39:30Z","body":"## What's Changed\n\n### Features\n- Make gpt-6-luna crewAI's default model everywhere\n- Read spreadsheet URLs in an agent's input with tools over every row\n- Tag eval usage spans with target and a per-evaluation id\n- Add --no-open to crewai eval for headless use\n\n### Bug Fixes\n- Count a crewai eval run that exits with an error as run_failed\n- Create the project .env owner-only when crewai eval turns tracing on\n- Upload a failed anonymous run that crewai eval started\n- Check openai-compatible providers' API key on the first call\n- Scope memoized crew methods to their instance\n- Exit non-zero when crewai run's project script fails\n- Eval asks to share the trace with Enter meaning yes, and explains why\n\n### Documentation\n- Document required_inputs on GET /inputs and which flow fields are inputs\n\n## Contributors\n\n@joaomdmoura"},"readme":true,"readme_zh":false,"news":[],"stale":false,"snapshot_at":"2026-11-10T09:35:25Z","history_start":"2026-09-06"}