{"full_name":"agno-agi/agno","owner":"agno-agi","name":"agno","shard":"1","url":"https://github.com/agno-agi/agno","description":"The self-managing agent platform","homepage":"https://docs.agno.com","topics":["developer-tools","python","agents","ai","ai-agents"],"tag_pages":["agents","ai","ai-agents","developer-tools","python"],"language":"Python","license":"Apache-2.0","avatar":"https://avatars.githubusercontent.com/u/104874993?v=4","created_at":"2022-05-04T15:23:02Z","pushed_at":"2026-11-15T17:46:12Z","metrics":{"stars":43200,"forks":6300,"watchers":234,"issues":3414,"prs":7142,"releases":261,"issues_open":955,"issues_closed":2459,"prs_open":918,"prs_closed":2001,"prs_merged":4223,"discussions":295},"growth":{"day":{"stars":9,"forks":4,"base_day":"2026-11-15"},"week":{"stars":86,"forks":34,"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":[43114,43128,43150,43173,43178,43181,43191,43200],"forks":[6266,6271,6281,6285,6289,6295,6296,6300],"watchers":[235,235,235,235,235,235,234,234],"issues_open":[null,null,947,952,955,979,950,955],"prs_open":[null,null,925,927,926,918,917,918]},"boards":{},"same_owner":[],"issues":[{"number":10366,"title":"`Agent(retries=N)` re-executes tool calls that already succeeded","comments":18,"created_at":"2026-09-20T08:29:27Z"},{"number":4952,"title":"[Feature Request] Token-aware Context Management and Compact Summaries","comments":18,"created_at":"2025-10-08T14:11:52Z"},{"number":9084,"title":"[Feature Request] Run pre/post hooks on continue_run + AgentOS-level global Agent/Team run hooks","comments":17,"created_at":"2026-07-21T00:34:05Z"},{"number":6892,"title":"Feature: Verifiable action receipts for agent tool calls","comments":17,"created_at":"2026-03-06T19:58:21Z"},{"number":7781,"title":"[feat] Add ToolAuditHook for structured tool call audit logging","comments":15,"created_at":"2026-05-03T23:02:45Z"},{"number":7266,"title":"[Feature Request] Add conversation branching (tree-based sessions) support","comments":12,"created_at":"2026-04-01T05:49:42Z"},{"number":8304,"title":"[Bug] tool_call_limit does not stop agent loop — unbounded tool-call retries","comments":11,"created_at":"2026-06-08T19:22:26Z"},{"number":7024,"title":"[Bug] Agent Output Schema being passed to MCP Tools","comments":11,"created_at":"2026-03-17T12:27:10Z"}],"discussions":[{"number":11679,"title":"Chopper: a small open model that cuts only the needed sentences out of retrieved text","comments":0,"category":"Show and tell","created_at":"2026-11-14T09:06:22Z"},{"number":11616,"title":"Exploring Moli with Agno","comments":0,"category":"General","created_at":"2026-11-13T08:29:56Z"},{"number":11595,"title":"Mapping four guardrail habits onto Agno's confirmation, tool_hooks and tool_call_limit (free MIT)","comments":0,"category":"Show and tell","created_at":"2026-11-12T06:44:31Z"},{"number":11594,"title":"mcp-slim: Cut MCPTools schema & output tokens by 50%-98% and normalize schemas for Agno agents","comments":0,"category":"Show and tell","created_at":"2026-11-12T02:34:15Z"},{"number":11527,"title":"About thingery.dev mcp","comments":0,"category":"General","created_at":"2026-11-08T22:00:05Z"},{"number":11512,"title":"Late external results after revocation: an offline ARQUIA-EVAL-001 invitation","comments":0,"category":"Show and tell","created_at":"2026-11-07T01:28:37Z"},{"number":11487,"title":"Cloud Alter Ego: a remote MCP connector that gives every AI chat your own rules and context","comments":0,"category":"Show and tell","created_at":"2026-11-05T08:16:46Z"},{"number":11390,"title":"Kilobat: All-in-one Mac networking for AI agents and humans too","comments":0,"category":"Show and tell","created_at":"2026-10-29T22:33:47Z"}],"latest_release":{"name":"v3.2.0","tag":"v3.2.0","published_at":"2026-11-12T17:47:14Z","body":"## Summary\r\n\r\nAgno v3.2 makes Super Agent faster and more capable with direct tools, expands Company task governance and coordination, introduces database-backed AgentOS homepage metrics, upgrades A2A to the v1.0 protocol, updates the Slack interface to use the Bolt SDK and makes external agents first-class stored components.\r\n\r\n## Changelog\r\n\r\n## Breaking changes\r\n\r\n- **OS Manager defaults and validation:** `OSManager.tool_call_limit` now defaults to 24 (was 8), and `num_history_runs` defaults to 5 (was 7). AgentOS refuses startup when `OSManager(root=...)` is combined with custom tools named `read_file`, `list_files`, or `search_content`.\r\n- **A2A v1.0:** AgentOS and `A2AClient` now run on the official `a2a-sdk` 1.x, so upgrade the Agno server and client together. ([#10956](https://github.com/agno-agi/agno/pull/10956))\r\n    - The `/v1/message:*` and `/v1/tasks:*` routes are removed; use each entity's A2A endpoint instead.\r\n    - Stream events and response artifacts follow the v1.0 shape.\r\n    - The `a2a` extra now requires `a2a-sdk[http-server]>=1.2.2,<2`.\r\n    - Direct imports of removed A2A helpers need updating.\r\n    - Standard v0.3 clients still work through the compatibility wire by default.\r\n- **Slack interface:** the interface now runs on Slack Bolt, and only the person who started a run can Approve or Deny it, unless they're named in `approvers=` or mapped to the same user with `users=`. ([#11599](https://github.com/agno-agi/agno/pull/11599))\r\n    - The `slack` extra now requires `slack_bolt>=1.29.0,<2` and `slack_sdk>=3.43.0,<4`; run `pip install -U \"agno[slack]\"`.\r\n    - List anyone else who approves runs in `approvers=`.\r\n    - AgentOS refuses startup when Slack serves `agent_os.manager` under `AgentOS(authorization=...)` or an authorization middleware without `users=`.\r\n    - Direct imports of removed internal Slack helpers (`SlackEventHandler`, `HITLHandler`, `verify_slack_signature`) need updating.\r\n\r\n## New features\r\n\r\n- **Super Agent:** Super Agent now does the work itself instead of routing requests through manager members. Platform Builder is its only member. ([#11572](https://github.com/agno-agi/agno/pull/11572))\r\n    - Lists and runs agents, teams, and workflows, and reads platform activity and schedules.\r\n    - Uses Company, docs, source-file, and custom OS Manager tools, and reads the current chat history.\r\n    - Its context includes accessible components, and every tool keeps its own permission check.\r\n- **Company OS:** Routines get a dedicated runner, Tasks carry richer state, and published Studio components can execute work.\r\n    - **Mini Agent for Routines:** Routines run on a restricted, non-chat Mini Agent with Company tools and packaged Routine skills, but no platform or general run tools. It is hidden from agent discovery, MCP, and A2A, and refuses non-Routine runs. ([#11572](https://github.com/agno-agi/agno/pull/11572))\r\n    - **Task coordination:** Tasks expose `last_run` and API-computed `allowed_transitions`, support direct start, and record durable attempt state. Super Agent can start an accepted Task on the durable queue without blocking the conversation; human acceptance and review are unchanged. ([#11430](https://github.com/agno-agi/agno/pull/11430), [#11562](https://github.com/agno-agi/agno/pull/11562))\r\n    - **Company details:** set a Company name and description in config, through `/company/details`, or from chat, with confirmation before replacing existing details. Super Agent gets fresh Company context on every run plus concise coordination guidance. ([#11502](https://github.com/agno-agi/agno/pull/11502), [#11569](https://github.com/agno-agi/agno/pull/11569), [#11563](https://github.com/agno-agi/agno/pull/11563))\r\n    - **Studio components as executors:** published Studio agents, teams, and workflows can execute Company Tasks and Routines. Drafts cannot, and normal executor safety checks still apply. ([#11443](https://github.com/agno-agi/agno/pull/11443))\r\n- **AgentOS homepage metr","is_prerelease":false},"readme":true,"readme_zh":false,"news":[],"stale":false,"snapshot_at":"2026-11-16T09:23:14Z","history_start":"2026-09-06"}