{"full_name":"microsoft/autogen","owner":"microsoft","name":"autogen","shard":"1","url":"https://github.com/microsoft/autogen","description":"A programming framework for agentic AI","homepage":"https://microsoft.github.io/autogen/","topics":["chatgpt","llm-agent","llm-framework","agentic","agentic-agi","agents","ai","autogen","framework","autogen-ecosystem"],"tag_pages":["agentic","agents","ai","autogen","chatgpt","framework","llm-agent"],"language":"Python","license":"CC-BY-4.0","avatar":"https://avatars.githubusercontent.com/u/6154722?v=4","created_at":"2023-08-18T11:43:45Z","pushed_at":"2026-11-12T10:19:36Z","metrics":{"stars":61854,"forks":9408,"watchers":523,"issues":3107,"prs":3965,"releases":98,"issues_open":575,"issues_closed":2532,"prs_open":603,"prs_closed":822,"prs_merged":2540,"discussions":1169},"growth":{"day":{"stars":36,"forks":4,"base_day":"2026-11-15"},"week":{"stars":98,"forks":15,"base_day":"2026-11-09"}},"history":{"dates":["2026-11-09","2026-11-10","2026-11-11","2026-11-12","2026-11-13","2026-11-14","2026-11-15","2026-11-16"],"stars":[61756,61769,61786,61793,61797,61807,61818,61854],"forks":[9393,9391,9391,9391,9391,9397,9404,9408],"watchers":[521,521,523,523,523,522,522,523],"issues_open":[null,null,574,575,575,575,575,575],"prs_open":[null,null,600,601,601,605,606,603]},"boards":{},"same_owner":[{"full_name":"microsoft/markitdown","name":"markitdown","shard":"1","boards":{"daily":151,"weekly":176,"monthly":103,"total":36}},{"full_name":"microsoft/vscode","name":"vscode","shard":"1","boards":{"daily_watchers":21,"total":37}},{"full_name":"microsoft/PowerToys","name":"PowerToys","shard":"1","boards":{"daily_watchers":111,"total":81}},{"full_name":"microsoft/generative-ai-for-beginners","name":"generative-ai-for-beginners","shard":"1","boards":{"daily_forks":40,"total":98}},{"full_name":"microsoft/TypeScript","name":"TypeScript","shard":"1","boards":{"daily_watchers":120,"total":120}},{"full_name":"microsoft/terminal","name":"terminal","shard":"1","boards":{"total":133}},{"full_name":"microsoft/playwright","name":"playwright","shard":"1","boards":{"total":143}},{"full_name":"microsoft/Web-Dev-For-Beginners","name":"Web-Dev-For-Beginners","shard":"1","boards":{"total":155}},{"full_name":"microsoft/ML-For-Beginners","name":"ML-For-Beginners","shard":"1","boards":{"total":173}},{"full_name":"microsoft/AI-For-Beginners","name":"AI-For-Beginners","shard":"1","boards":{}},{"full_name":"microsoft/AirSim","name":"AirSim","shard":"1","boards":{}},{"full_name":"microsoft/BitNet","name":"BitNet","shard":"1","boards":{}},{"full_name":"microsoft/Bringing-Old-Photos-Back-to-Life","name":"Bringing-Old-Photos-Back-to-Life","shard":"1","boards":{}},{"full_name":"microsoft/CNTK","name":"CNTK","shard":"1","boards":{}},{"full_name":"microsoft/Data-Science-For-Beginners","name":"Data-Science-For-Beginners","shard":"1","boards":{}},{"full_name":"microsoft/FluidFramework","name":"FluidFramework","shard":"1","boards":{}},{"full_name":"microsoft/IoT-For-Beginners","name":"IoT-For-Beginners","shard":"1","boards":{}},{"full_name":"microsoft/MMdnn","name":"MMdnn","shard":"1","boards":{}},{"full_name":"microsoft/Ontology-Playground","name":"Ontology-Playground","shard":"1","boards":{}},{"full_name":"microsoft/Procexp-Mac","name":"Procexp-Mac","shard":"1","boards":{"daily_rate":96,"weekly_rate":32,"monthly_rate":87}}],"issues":[{"number":7353,"title":"Feature: Cryptographic action receipts for enterprise agent governance (AAR)","comments":431,"created_at":"2026-03-06T18:26:48Z"},{"number":7405,"title":"Proposal: GuardrailProvider protocol for tool call interception","comments":147,"created_at":"2026-03-14T18:08:09Z"},{"number":7487,"title":"Multi-agent systems need a 'mission keeper' role — not a Boss Agent, but a dedicated goal integrity node","comments":74,"created_at":"2026-03-29T13:44:49Z"},{"number":7492,"title":"Payment primitive for multi-agent systems - how are teams handling this?","comments":63,"created_at":"2026-03-30T19:45:38Z"},{"number":7372,"title":"Cryptographic governance layer for AutoGen distributed agent runtime","comments":62,"created_at":"2026-03-11T22:08:34Z"},{"number":7525,"title":"Feature: Agent trust verification via MoltBridge for cross-org multi-agent scenarios","comments":58,"created_at":"2026-04-04T00:40:44Z"},{"number":7265,"title":"[Question] Practical reliability patterns for multi-agent production","comments":57,"created_at":"2026-02-24T11:07:32Z"},{"number":7748,"title":"RFC: Cross-agent shared memory store with on-demand capsule recall (agent/group/global scopes)","comments":41,"created_at":"2026-05-25T06:36:38Z"}],"discussions":[{"number":8477,"title":"Chopper: a small open model that cuts only the needed sentences out of retrieved text","comments":1,"category":"Show and tell","created_at":"2026-11-13T09:07:48Z"},{"number":8473,"title":"mcp-slim: Zero-dependency MCP stdio proxy for AutoGen (-50% to -98% schema tokens, $ref inlining, SecretGuard)","comments":2,"category":"Show and tell","created_at":"2026-11-12T02:34:16Z"},{"number":8471,"title":"A short checklist for AutoGen teams that write to real systems","comments":2,"category":"Show and tell","created_at":"2026-11-11T06:47:06Z"},{"number":8464,"title":"Handling authorization state drift during agent-to-tool transitions (Architecture Lab)","comments":2,"category":"Ideas","created_at":"2026-11-09T19:25:03Z"},{"number":8443,"title":"A small offline permission-revocation fixture for tool workflows — independent runs and counterexamples welcome","comments":2,"category":"Show and tell","created_at":"2026-11-07T00:49:17Z"},{"number":8432,"title":"Show and tell: giving an AutoGen team a check tool — so \"the other agent reviewed it\" becomes a record","comments":1,"category":"Show and tell","created_at":"2026-11-05T15:11:00Z"},{"number":8413,"title":"A wheel turns forward at 40 rpm and looks backward on camera: an interactive sampling puzzle made with an AI assistant","comments":0,"category":"Show and tell","created_at":"2026-11-02T08:21:18Z"},{"number":8411,"title":"Governed memory for AutoGen multi-agent conversations — audit chains, poisoning defense","comments":0,"category":"Show and tell","created_at":"2026-11-02T05:21:30Z"}],"latest_release":{"name":"python-v0.7.5","tag":"python-v0.7.5","published_at":"2025-09-30T06:18:26Z","body":"## What's Changed\r\n* Fix docs dotnet core typo by @lach-g in https://github.com/microsoft/autogen/pull/6950\r\n* Fix loading streaming Bedrock response with tool usage with empty argument by @pawel-dabro in https://github.com/microsoft/autogen/pull/6979\r\n* Support linear memory in RedisMemory by @justin-cechmanek in https://github.com/microsoft/autogen/pull/6972\r\n* Fix message ID for correlation between streaming chunks and final mes… by @smalltalkman in https://github.com/microsoft/autogen/pull/6969\r\n* fix: extra args not work to disable thinking by @liuyunrui123 in https://github.com/microsoft/autogen/pull/7006\r\n* Add thinking mode support for anthropic client by @SrikarMannepalli in https://github.com/microsoft/autogen/pull/7002\r\n* Fix spurious </think> tags caused by empty string reasoning_content in streaming by @Copilot in https://github.com/microsoft/autogen/pull/7025\r\n* Fix GraphFlow cycle detection to properly clean up recursion state by @Copilot in https://github.com/microsoft/autogen/pull/7026\r\n* Add comprehensive GitHub Copilot instructions for AutoGen development by @Copilot in https://github.com/microsoft/autogen/pull/7029\r\n* Fix Redis caching always returning False due to unhandled string values by @Copilot in https://github.com/microsoft/autogen/pull/7022\r\n* Fix OllamaChatCompletionClient load_component() error by adding to WELL_KNOWN_PROVIDERS by @Copilot in https://github.com/microsoft/autogen/pull/7030\r\n* Fix finish_reason logic in Azure AI client streaming response by @litterzhang in https://github.com/microsoft/autogen/pull/6963\r\n* Add security warnings and default to DockerCommandLineCodeExecutor by @ekzhu in https://github.com/microsoft/autogen/pull/7035\r\n* Fix: Handle nested objects in array items for JSON schema conversion by @kkutrowski in https://github.com/microsoft/autogen/pull/6993\r\n* Fix not supported field warnings in count_tokens_openai by @seunggil1 in https://github.com/microsoft/autogen/pull/6987\r\n* Fix(mcp): drain pending command futures on McpSessionActor failure by @withsmilo in https://github.com/microsoft/autogen/pull/7045\r\n* Add missing reasoning_effort parameter support for OpenAI GPT-5 models by @Copilot in https://github.com/microsoft/autogen/pull/7054\r\n* Update version to 0.7.5 by @ekzhu in https://github.com/microsoft/autogen/pull/7058\r\n\r\n## New Contributors\r\n* @lach-g made their first contribution in https://github.com/microsoft/autogen/pull/6950\r\n* @pawel-dabro made their first contribution in https://github.com/microsoft/autogen/pull/6979\r\n* @smalltalkman made their first contribution in https://github.com/microsoft/autogen/pull/6969\r\n* @liuyunrui123 made their first contribution in https://github.com/microsoft/autogen/pull/7006\r\n* @SrikarMannepalli made their first contribution in https://github.com/microsoft/autogen/pull/7002\r\n* @litterzhang made their first contribution in https://github.com/microsoft/autogen/pull/6963\r\n* @kkutrowski made their first contribution in https://github.com/microsoft/autogen/pull/6993\r\n* @seunggil1 made their first contribution in https://github.com/microsoft/autogen/pull/6987\r\n\r\n**Full Changelog**: https://github.com/microsoft/autogen/compare/python-v0.7.4...python-v0.7.5","is_prerelease":false},"readme":true,"readme_zh":false,"news":[],"stale":false,"snapshot_at":"2026-11-16T09:23:14Z","history_start":"2026-09-06"}