https://github.com/agno-agi/agno
Build, run, and manage agent platforms.
https://github.com/agno-agi/agno
agents ai ai-agents developer-tools python
Last synced: 2 days ago
JSON representation
Build, run, and manage agent platforms.
- Host: GitHub
- URL: https://github.com/agno-agi/agno
- Owner: agno-agi
- License: apache-2.0
- Created: 2022-05-04T15:23:02.000Z (over 4 years ago)
- Default Branch: main
- Last Pushed: 2026-08-24T19:12:23.000Z (6 days ago)
- Last Synced: 2026-08-24T20:22:01.063Z (6 days ago)
- Topics: agents, ai, ai-agents, developer-tools, python
- Language: Python
- Homepage: https://docs.agno.com
- Size: 299 MB
- Stars: 41,888
- Watchers: 237
- Forks: 5,817
- Open Issues: 1,290
-
Metadata Files:
- Readme: README.md
- Contributing: CONTRIBUTING.md
- License: LICENSE
- Code of conduct: CODE_OF_CONDUCT.md
- Codeowners: CODEOWNERS
- Agents: AGENTS.md
- Claude: CLAUDE.md
- Cursor: .cursorrules
Awesome Lists containing this project
- awesome-LLM-resources - Agno
- awesome-github-projects - agno - Build, run, and manage agent platforms. โญ41,682 `Python` ๐ฅ (๐ค AI & Machine Learning)
- awesome-ai - Agno
- best-of-Agent-Harnesses - **agno** - agi/agno/stargazers) | Python agents with memory, knowledge bases, tools, and structured outputs; continues the PhiData-era product line under the Agno nameโproduction apps, evals, and pipelines. <sup>`memory` ยท `evals` ยท `python`</sup> | โ | complex (memory, KB, observability โ product suite) | [Agent with tools](https://github.com/agno-agi/agno/blob/main/cookbook/02_agents/01_quickstart/agent_with_tools.py) | (Frameworks / Or hire a skeleton)
- awesome-agent-evolution - **agno** - Production-ready agent framework that turns agents into deployable services with multi-framework support. by [@agno-agi](https://github.com/agno-agi) (41,772 stars) (Agent Development Platforms)
- awesome-prompts - **Agno** - first agent framework โ memory, knowledge, tools, multi-agent teams, and structured workflows; rebrand of phidata (2026)  | (Agent Ecosystem / Frameworks)
- awesome-ai-coding - Agno - agi/agno?style=flat-square&label=%E2%98%85)](https://github.com/agno-agi/agno) | Agno AI | Open-source framework for building multi-modal agents. | Fast execution, built-in vector integrations, multi-modal support. | (โ๏ธ AI Agent Frameworks & Multi-Agent Platforms)
- awesome-offensive-mcp - **Agno**
- awesome-ai-agents - Agno - agent runtime and AgentOS for secure and production-ready systems. (Frameworks)
- awesome-agents - Agno - Lightweight library for building multi-modal agents with memory and knowledge. (Frameworks)
- awesomeLibrary - agno - Agno is a lightweight library for building multi-modal Agents (่ฏญ่จ่ตๆบๅบ / python)
- awesome-safety-critical-ai - `agno-agi/agno` - modal agents (<a id="tools"></a>๐ ๏ธ Tools / Bleeding Edge โ๏ธ)
- awesome-ai-agents-2026 - Agno - agnostic. | (๐งฑ Agent Frameworks / Lightweight / Minimalist)
- awesome-local-llm - agno - a full-stack framework for building Multi-Agent Systems with memory, knowledge and reasoning (Tools / Agent Frameworks)
- awesome-context-engineering - agno - agi`)  Full-stack framework for building Multi-Agent Systems with memory, knowledge and reasoning. (๐ฆ Isolate Context / Multi-Agent Frameworks)
- definitive-opensource - Agno
- awesome-ai-for-economists - Agno - Open-source Python framework with memory, knowledge, and 100+ toolkits including MCP support.  (Coding Tools for Economists / AI Agent Frameworks)
- awesome-github-repos - agno-agi/agno - Build, run, and manage agent platforms. (Python)
- AiTreasureBox - agno-agi/agno - 11-03_34823_3](https://img.shields.io/github/stars/agno-agi/agno.svg)|Agno is a lightweight library for building Multimodal Agents. It exposes LLMs as a unified API and gives them superpowers like memory, knowledge, tools and reasoning.| (Repos)
- awesome-ai - ๐
- awesome - agno-agi/agno - Build, run, and manage agent platforms. (Python)
- awesome-opensource-ai - Agno - Build, run, and manage agentic software at scale. High-performance framework for multi-agent systems with memory, knowledge, and tools.  (4. Agentic AI & Multi-Agent Systems)
- awesome-nlp-llm-spanish-espa-ol - Agno
- awesome-claude-multi-agent - Agno - High-performance Python framework for multi-agent teams with memory and knowledge; model-agnostic interface including Claude. (Orchestration Frameworks)
- awesome-local-ai-agents - Agno
- awesome-ai-agents-2026 - Agno
- awesome - agno-agi/agno - The complete stack for AI Engineers: framework, runtime and control plane. (<a name="Python"></a>Python)
- awesome-llm-tools - Agno (Phidata) - modal agent framework | Multi-modal agents with memory & storage | (2. Libraries & Frameworks / Python)
- awesome-rainmana - agno-agi/agno - Build, run, and manage agent platforms. (Python)
- awesome-ai-agents-2026 - Agno (ๆง Phidata) - ใกใขใชใป็ฅ่ญใปใใผใซใปๆจ่ซใคใใใซใใขใผใใซใจใผใธใงใณใ๏ผv2.7.x๏ผ2026-07๏ผใ (๐๏ธ ใจใผใธใงใณใใใฌใผใ ใฏใผใฏ / ใใฎไปใฎๆจๆบ)
- Awesome-Prompt-Engineering - GitHub
- awesome-agent-cortex - Agno - Framework for building and running agentic software at scale. (Agent Frameworks)
- Awesome-AI-Agents - Agno - Build multi-agent systems with memory, knowledge, and tool integrations in Python.  (Frameworks / Tools)
- my-awesome-list - agno - agi | 41748 | (Python)
- awesome-agi-agents - Agno - agi/agno)|Full-stack framework for building Multi-Agent Systems with memory, knowledge and reasoning.|ๅ Phidata๏ผ้ซๆง่ฝๅ จๆ ๅค Agent ๆกๆถ๏ผๅ ็ฝฎ่ฎฐๅฟใ็ฅ่ฏใๆจ็ไธๅทฅๅ ท๏ผไธปๆ่ฝป้ไธ่ฟ่ก้ๅบฆใ| (Agents ๅผๅๅนณๅฐ)
- awesome-ai-agents - Agno - agent systems at scale. (Frameworks & Libraries / Multi-Agent Orchestration)
- fucking-awesome-python - Agno - Open-source Python library for building AI agents and agentic systems. (Machine Learning)
- awesome-workflow-automation - Agno (Phidata)
- awesome-langchain - Agno - agi/agno?style=social) (Other LLM Frameworks / Videos Playlists)
- Awesome-LLMOps - Agno - source framework for building multi-agent systems with memory, knowledge and reasoning.    (Orchestration / Agent Framework)
- awesome-ai-agents - Agno - agi/agno) | Multi-agent framework, runtime, and control plane for AI products | (๐ Core Frameworks)
- awesome-production-agentic-systems - Agno - agi/agno.svg?cacheSeconds=86400) - Agno is a full-stack framework for building multi-agent systems with memory, knowledge, and tools. (Agentic Frameworks)
- awesome-ai-coding-agent-tools - Agno - Lightweight stateful-agent framework with memory and knowledge (formerly Phidata). (Agent SDKs & Frameworks / Lightweight & Typed)
- awesome-agent-harness - GitHub - 40783-f4b400?style=flat-square)](https://github.com/agno-agi/agno) | scale, runtime, management | Agent software runtime focused on running and managing agentic systems at scale. | (Catalog / Harness Architecture & Orchestration)
- Awesome-Agentic-Engineering - Agno - agnostic agent framework with native multi-modal support. | `[official]` | (โ๏ธ Orchestration Frameworks / Frameworks Landscape)
- awesome-a2a - Agno - agi](https://github.com/agno-agi) [](https://github.com/agno-agi/agno) - A lightweight library for building agentic AI systems. AgentOS exposes agents, teams, and workflows as A2A-compatible services with `A2AClient` and `RemoteAgent` for calling remote A2A agents, and also supports AG-UI. Apache 2.0 and published on PyPI as `agno`. (โ๏ธ Implementations & Libraries)
- awesome-mac-mini-homeserver - Agno - Python runtime and AgentOS control plane for building, deploying, and operating agentic systems at scale.     (Agentic AI  / Agentic frameworks)
- awesome-ai-pulse-georgia - agno - แแก lightweight production framework AI แแแแแขแแแแกแแแแก, แ แแแแแแช 2025 แฌแแแก rebrand-แ แแแแแ แ. agents, multi-agent teams, workflows, memory, tools, knowledge bases แแ monitoring แแ แ แแแแแแแแฃแ แ dependencies-แแก แแแแแขแจแ แแ แแแแแแแแ. แกแฎแแ แคแ แแแแแแ แแแแแกแแแ แแแแกแฎแแแแแแแ, agno-แก แแแ แแแ แแแ แขแแแ แแ แแแกแแแแแแ โ production deployment-แแกแแแแก แแแแแแขแ abstractions-แ แแ แแแแญแแ แแแแ. 40,000+ แแแ แกแแแแแแ; แแชแแ แ แแฃแแแแแแกแแแแก, แแแแช LangChain-แแก แกแแ แแฃแแแก แแแ แแจแ production-ready แแแแแขแแแก แฅแแแแก, แแก แแคแแฅแขแฃแ แ แฉแแ แฉแแ. | (๐งฌ AI แแแแแขแแแแก แคแ แแแแแแ แแแแ)
- awesome-ai-agents - agno-agi/agno - Agno is a lightweight, model-agnostic library for building advanced AI agents with memory, knowledge, tools, and reasoning capabilities, supporting multi-modal inputs and outputs and featuring an advanced multi-agent architecture. (AI Agent Frameworks & SDKs / Multi-Agent Collaboration Systems)
- awesome-list - agno: Build, run, and manage your own agent platform.
- awesome-agents - Agno - agi/agno?style=social) (Automation)
- awesome-x-ops - Agno - source platform for building, running, and managing AI agent platforms with model-agnostic support and production-grade tooling. (Agentic Workflow)
README
Build, run, and manage agent platforms.
## Introduction
Agno is a framework and runtime for agent platforms. Build agents, run them as a service, manage your platform using a web UI.
- Build your agent platform using the Agno SDK.
- Run your agent platform using the AgentOS runtime.
- Manage everything using the AgentOS UI.
Agno allows you to own your agent stack. Maintain control of your data, memory, and security posture (JWT-based RBAC), and turn your agent platform into a learning loop with simulations and usage data.

## Get started
Hand this prompt to your coding agent (Claude Code, Cursor, Codex):
```text
Help me set up my agent platform.
Clone https://github.com/agno-agi/agentos-railway into a folder called
agent-platform, cd in, read the README, and follow the get started guide.
```
Your coding agent will set up your agent platform and run it locally using Docker, giving you a REST API for serving your agents, a Postgres database for storing your data and traces, an MCP server, and a control plane.
Deploying somewhere else? Use the same prompt but point it to a different repo. The starter templates are identical except for the deploy scripts: swap [agentos-railway](https://github.com/agno-agi/agentos-railway) for [agentos-docker](https://github.com/agno-agi/agentos-docker), [agentos-aws](https://github.com/agno-agi/agentos-aws), [agentos-gcp](https://github.com/agno-agi/agentos-gcp), [agentos-azure](https://github.com/agno-agi/agentos-azure), [agentos-fly](https://github.com/agno-agi/agentos-fly), [agentos-render](https://github.com/agno-agi/agentos-render), [agentos-modal](https://github.com/agno-agi/agentos-modal), or [agentos-helm](https://github.com/agno-agi/agentos-helm).
### Prefer to code by hand?
- [Build your first agent in 20 lines of code.](https://docs.agno.com/first-agent)
- [Build your own agent platform.](https://docs.agno.com/agent-platform/overview)
- [Read the docs.](https://docs.agno.com)
## Features
- [Production API](https://docs.agno.com/runtime/serve-as-api). 50+ endpoints with SSE and websockets to build a product on top.
- [Storage](https://docs.agno.com/runtime/storage). Store sessions, memory, knowledge, and traces in your own database.
- [100+ integrations](https://docs.agno.com/tools/toolkits/overview). Connect to GitHub, Slack, Postgres, and more using pre-built toolkits.
- [Context Providers](https://docs.agno.com/runtime/context). Access live data from Slack, Drive, wikis, MCP, and custom sources.
- [Human approval](https://docs.agno.com/runtime/human-approval). Pause runs for user confirmation. Block tools that require admin approval.
- [Observability](https://docs.agno.com/runtime/observability). Monitor with OpenTelemetry tracing, run history, and audit logs.
- [Security](https://docs.agno.com/runtime/security-and-auth). Get JWT-based RBAC and multi-user, multi-tenant isolation out of the box.
- [Interfaces](https://docs.agno.com/runtime/interfaces). Expose your agents via Slack, Telegram, WhatsApp, Discord, AG-UI, A2A.
- [Scheduling](https://docs.agno.com/runtime/scheduling). Cron-based scheduling and background jobs with no external infrastructure.
- [Deploy anywhere](https://docs.agno.com/runtime/deploy). Run on any cloud platform that runs containers. Docker, Railway, AWS, GCP.
## Use Agno with your coding agent
Two options:
1. Recommended: Add Agno docs as an MCP server. Add [docs.agno.com/mcp](https://docs.agno.com/mcp) to your favourite coding agent.
2. Add Agno docs as an indexed source. In Cursor: Settings โ Indexing & Docs โ Add `https://docs.agno.com/llms-full.txt`. Also works in VSCode, Windsurf, and similar tools.
Read the full guide [here](https://docs.agno.com/coding-agents).
## Community
- [X](https://x.com/AgnoAgi): follow for releases and demos
- [Newsletter](https://www.agno.com/the-agno-loop-newsletter): monthly updates on what's shipping
## Contributing
See the [contributing guide](https://github.com/agno-agi/agno/blob/main/CONTRIBUTING.md).
## License
Agno is distributed under the [Apache-2.0 license](LICENSE).
## Telemetry
Agno sends a telemetry event per agent run so we know which model providers to prioritize. Prompts, messages, and outputs are never sent. Disable by setting `AGNO_TELEMETRY=false`.