# Agno

Build, run, and manage agent platforms.

Repository: https://github.com/agno-agi/agno
Canonical: https://ross.abutalabs.com/products/agno
Homepage: https://docs.agno.com
Language: Python
License: Apache-2.0
License Family: permissive
Topics: developer-tools, python, agents, ai, ai-agents
Last push: 2026-08-27T00:27:45+00:00
Link (homepage): https://docs.agno.com
Link (site_page): https://docs.agno.com/faq/environment-variables
Link (site_page): https://docs.agno.com/features/sdk
Link (site_page): https://docs.agno.com/features/runtime
Link (site_page): https://docs.agno.com/features/control-plane

## Health v2 (maintenance only)
Score: 95/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 99, release rhythm 87, longevity 100
- inputs: {"age_days": 1582, "days_push": 7, "days_rel": 7, "gap_med": 1.0, "n_releases_24m": 221}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 41938, forks 5830 (observed 2026-08-28T04:12:08.721863+00:00)

## What it is
Agno is a Python SDK and runtime (AgentOS) for building, running, and managing full agent platforms, including agents, teams, and workflows with memory, knowledge, and 100+ tool integrations. It serves agents as REST/SSE APIs and MCP servers via FastAPI, with a web control plane for tracing, evals, sessions, and governance.

## Use cases
- build a multi-agent AI platform in python
- serve llm agents as a REST API
- add memory and knowledge to my chatbot
- run an MCP server for my agents
- trace and debug agent tool calls
- evaluate agent quality in CI
- self-host an agent runtime with RBAC

## When to choose
- you want an end-to-end agent platform with runtime, storage, and observability in one stack
- you need production features like sessions, tracing, evals, guardrails, and scheduling
- you want to self-host and own your agent data and security posture
- you need multi-interface serving (REST, SSE, MCP, Slack/Telegram) from one agent definition

## When to avoid
- you only need a thin LLM client or simple prompt chaining without a runtime
- you are locked into a managed agent cloud and don't want to operate infrastructure
- your stack is not Python
- you need a minimal library with no control plane or platform opinions

## Facets
- artifact type: framework
- maturity: active
- function: agent-framework, llm-inference, rag, mcp, chatbot, web-framework, monitoring, tracing, testing, sdk
- domain: large-language-models, artificial-intelligence, developer-tools, backend, apis
- platform: python, self-hosted, cross-platform
- tags: agent-platform, agentos, multi-agent, fastapi, control-plane, agent-evals, tool-integrations, jwt-rbac, ai-agents, docker

## Member repositories
- agno-agi/agno (main) score 95
- agno-agi/dash (examples) score 56

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:12:08.721863+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T16:22:53.901305+00:00, confidence not recorded.
  - readme: https://github.com/agno-agi/agno (fetched 2026-08-28T04:12:08.721863+00:00, sha 65a38125f2be)
  - homepage: https://docs.agno.com (fetched 2026-08-29T07:46:25.434132+00:00, sha 5897770c70e8)
  - site_page: https://docs.agno.com/faq/environment-variables (fetched 2026-08-29T07:46:25.437948+00:00, sha 35d6006d7eaa)
  - site_page: https://docs.agno.com/features/sdk (fetched 2026-08-29T07:46:25.440491+00:00, sha a4cbf36d3059)
  - site_page: https://docs.agno.com/features/runtime (fetched 2026-08-29T07:46:25.443072+00:00, sha e42c7ddd34f6)
  - site_page: https://docs.agno.com/features/control-plane (fetched 2026-08-29T07:46:25.445393+00:00, sha 777031e40c02)
  - site_page: https://docs.agno.com/features/api (fetched 2026-08-29T07:46:25.448018+00:00, sha b15724b412e1)
  - site_page: https://docs.agno.com/features/storage (fetched 2026-08-29T07:46:25.450390+00:00, sha 3f9a6f6b7266)
  - site_page: https://docs.agno.com/features/observability (fetched 2026-08-29T07:46:25.452650+00:00, sha 7cda051475a8)
  - site_page: https://docs.agno.com/features/evaluation (fetched 2026-08-29T07:46:25.454901+00:00, sha 370f4e13ee72)
- Data as of 2026-08-30T08:39:29.467469+00:00.