{"full_name":"agno-agi/agno","owner":"agno-agi","name":"agno","url":"https://github.com/agno-agi/agno","description":"The self-driving agent platform","homepage":"https://docs.agno.com","topics":[],"language":"Python","license":"Apache-2.0","avatar":"https://avatars.githubusercontent.com/u/104874993?v=4","created_at":"2022-05-04T15:23:02Z","pushed_at":"2026-11-10T08:41:21Z","metrics":{"stars":43128,"forks":6271,"watchers":235,"issues":3328,"prs":7070,"releases":260,"issues_open":null,"issues_closed":null,"prs_open":null,"prs_closed":null,"prs_merged":null,"discussions":291},"growth":{"day":{"stars":14,"forks":5,"base_day":"2026-11-09"}},"history":{"dates":["2026-11-09","2026-11-10"],"stars":[43114,43128],"forks":[6266,6271],"watchers":[235,235],"issues_open":[null,null],"prs_open":[null,null]},"boards":{},"same_owner":[],"issues":[{"number":10366,"title":"`Agent(retries=N)` re-executes tool calls that already succeeded","comments":17,"created_at":"2026-09-20T08:29:27Z"},{"number":6892,"title":"Feature: Verifiable action receipts for agent tool calls","comments":17,"created_at":"2026-03-06T19:58:21Z"},{"number":4952,"title":"[Feature Request] Token-aware Context Management and Compact Summaries","comments":17,"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":16,"created_at":"2026-07-21T00:34:05Z"},{"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":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":11427,"title":"Showcase: Apizie Finance Remote MCP Tool for SEC EDGAR and Macro Data in Agno","comments":0,"category":"Show and tell","created_at":"2026-11-02T03:25:06Z"},{"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"},{"number":11287,"title":"Leviathan: a free public meeting place for separately operated agents","comments":0,"category":"Show and tell","created_at":"2026-10-24T06:52:02Z"},{"number":11251,"title":"MCPTools: original-name filtering, prefixed functions and a public read without a model","comments":0,"category":"Show and tell","created_at":"2026-10-22T19:02:08Z"},{"number":11205,"title":"A consensus-check tool for Agno Teams (flag when member agents agree for the wrong reasons)","comments":0,"category":"Show and tell","created_at":"2026-10-21T07:08:45Z"},{"number":11128,"title":"Would a toolkit for sitemap, feed and tech-stack change events be welcome?","comments":0,"category":"Ideas","created_at":"2026-10-16T20:12:39Z"}],"latest_release":{"name":"v3.1.12","tag":"v3.1.12","published_at":"2026-10-29T14:00:55Z","body":"# Changelog\r\n\r\n## New Features:\r\n\r\n- **Native Approvals for Harness Agents**: Claude's and Codex's own permission requests now reach the AgentOS approval UI. When the agent has a database, including one AgentOS supplies, a native request persists a PAUSED run that shows up in the existing chat and Approvals views, and Resolve plus Continue Run delivers the decision back to the same native execution without replaying the prompt. The harness's own policy decides when to ask — Claude keeps its `permission_mode` and explicit permission callbacks, Codex supports `approval_policy=\"on-request\" | \"untrusted\" | \"never\"` alongside its existing SDK `auto_review` and `deny_all` modes — so there is no separate Agno setting to turn on. Decisions are validated against the exact action requested, with sync and async continuation, cancellation, expiry and storage-failure handling, and sandboxed agents keep this across Docker and AgentCore: capability negotiation, a decision RPC, fenced persistence, reattachment after an API-worker loss, separate approval-wait and execution budgets, and no replay after process loss. Note that a `CodexAgent` with no approval settings now runs under the native `on-request` policy, so a request that previously went nowhere pauses the run instead; `hitl_timeout` (default 900s) bounds how long it waits. See `cookbook/frameworks/human_in_the_loop/`.\r\n- **Initially Disabled Company Routines**: `Routine(enabled=False)` lets a template ship an inactive Routine that a user turns on later from the UI, with `True` still the default. Disabled Routines are created atomically, stay linked to their Product and visible in listings, are skipped by the scheduler, and keep the user's saved choice across restarts. The flag is honored in Python and YAML bootstrap, the setup and creation APIs, the sync and async Company Manager, and the Company tools. Duplicate create requests still return `409` and cannot enable an existing Routine, and the existing pause/resume endpoints enable it without recreating it. See `cookbook/05_agent_os/30_company/11_disabled_routine.py`.\r\n- **Headline Numbers on Charts**: `ChartTools.create_chart()` takes an optional preformatted `value` — a total or latest value such as `\"$22.3K\"` or `\"94%\"` — emitted as `\"value\"` in the chart block and rendered by Agno OS beside the chart title. The docstring tells the model to leave it out when no single number summarizes the chart, so averages and rates are not summed.\r\n\r\n## Improvements:\r\n\r\n- **Company Routine Sorting**: `GET /company/routines` now also sorts by `next_run_at`, `schedule_type` and `enabled`, so Agno OS can sort its routines table by Next run at, Schedule and Active. Paused and on-demand Routines have no upcoming run, so they come last in either direction, and Routines with the same value keep their creation order.\r\n- **Cookbooks**: Added an `ApifyTools` job search example that caps the Actor's item count with a tool hook and trims each dataset item to title, company, location, posted date and link, so a broad search stays small in context. Added a fully local Pixeltable RAG example that writes chunks through `langchain-pixeltable` and searches them with `LangChainVectorDb`, using local `sentence-transformers` embeddings and Ollama — no embedding API key and no separate vector database server.\r\n\r\n## Bug Fixes:\r\n\r\n- **FastAPI Native Tracing**: FastAPI 0.142.0 enables its own OpenTelemetry tracing as soon as a global tracer provider exists, which `AgentOS(tracing=True)` installs, so FastAPI's request spans were stored alongside Agno's. Every run became a child of the request span and traces were recorded as `fastapi.dependencies` with empty `run_id`, `session_id` and `agent_id`, breaking the Runs view, while each UI request stored a trace of its own. AgentOS now opts the app it builds out of FastAPI's tracing, and `setup_tracing()` filters foreign spans so a stored trace is rooted at the Agno run. Apps without `tracing=True` keep FastAPI's defaults, and "},"readme":true,"readme_zh":false,"news":[],"stale":false,"snapshot_at":"2026-11-10T09:35:25Z","history_start":"2026-09-06"}