https://github.com/agno-agi/agno
Build multi-agent systems that learn and improve with every interaction.
https://github.com/agno-agi/agno
agents ai ai-agents developer-tools python
Last synced: 12 days ago
JSON representation
Build multi-agent systems that learn and improve with every interaction.
- Host: GitHub
- URL: https://github.com/agno-agi/agno
- Owner: agno-agi
- License: apache-2.0
- Created: 2022-05-04T15:23:02.000Z (almost 4 years ago)
- Default Branch: main
- Last Pushed: 2026-02-11T00:18:16.000Z (26 days ago)
- Last Synced: 2026-02-11T00:19:50.931Z (26 days ago)
- Topics: agents, ai, ai-agents, developer-tools, python
- Language: Python
- Homepage: https://docs.agno.com
- Size: 258 MB
- Stars: 37,761
- Watchers: 227
- Forks: 5,004
- Open Issues: 570
-
Metadata Files:
- Readme: README.md
- Contributing: CONTRIBUTING.md
- License: LICENSE
- Code of conduct: CODE_OF_CONDUCT.md
- Codeowners: CODEOWNERS
- Agents: AGENTS.md
Awesome Lists containing this project
- awesome-LLM-resources - Agno
- awesome-ai - Agno
- awesome-ai-agents - Agno - agent runtime and AgentOS for secure and production-ready systems. (Frameworks)
- awesome-rainmana - agno-agi/agno - Build, run, manage agentic software at scale. (Python)
- 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 (语言资源库 / python)
- awesome-safety-critical-ai - `agno-agi/agno` - modal agents (<a id="tools"></a>🛠️ Tools / Bleeding Edge ⚗️)
- awesome-local-llm - agno - a full-stack framework for building Multi-Agent Systems with memory, knowledge and reasoning (Tools / Agent Frameworks)
- awesome - agno-agi/agno - Build, run, manage agentic software at scale. (Python)
- Awesome-LLMOps - Agno - source framework for building multi-agent systems with memory, knowledge and reasoning.    (Orchestration / Agent Framework)
- my-awesome-list - agno - agi | 38431 | (Python)
- awesome-github-repos - agno-agi/agno - Build, run, manage agentic software at scale. (Python)
- definitive-opensource - Agno
- 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-nlp-llm-spanish-espa-ol - Agno
- 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-ai-agents - Agno - agi/agno) | Multi-agent framework, runtime, and control plane for AI products | (🌟 Core Frameworks)
- awesome - agno-agi/agno - The complete stack for AI Engineers: framework, runtime and control plane. (<a name="Python"></a>Python)
- awesome-context-engineering - agno - agi`)  Full-stack framework for building Multi-Agent Systems with memory, knowledge and reasoning. (📦 Isolate Context / Multi-Agent Frameworks)
- Awesome-Prompt-Engineering - GitHub
- awesome-workflow-automation - Agno (Phidata)
README
Build multi-agent systems that learn.
## What is Agno?
**A framework for building multi-agent systems that learn and improve with every interaction.**
Most agents are stateless. They reason, respond, forget. Session history helps, but they're exactly as capable on day 1000 as they were on day 1.
Agno agents are different. They remember users across sessions, accumulate knowledge across conversations, and learn from decisions. Insights from one user benefit everyone. The system gets smarter over time.
Everything runs in your cloud. Your data never leaves your environment.
## Quick Example
```python
from agno.agent import Agent
from agno.db.sqlite import SqliteDb
from agno.models.openai import OpenAIResponses
agent = Agent(
model=OpenAIResponses(id="gpt-5.2"),
db=SqliteDb(db_file="tmp/agents.db"),
learning=True,
)
```
One line. Your agent now remembers users, accumulates knowledge, and improves over time.
## Production Stack
Agno provides the complete infrastructure for building multi-agent systems that learn:
| Layer | What it does |
|-------|--------------|
| **Framework** | Build agents with learning, tools, knowledge, and guardrails |
| **Runtime** | Run in production using [AgentOS](https://docs.agno.com/agent-os/introduction) |
| **Control Plane** | Monitor and manage via the [AgentOS UI](https://os.agno.com) |
## Get Started
1. [Build your first agent](https://docs.agno.com/first-agent)
2. [Build your first multi-agent system](https://docs.agno.com/first-multi-agent-system)
3. [Deploy to production](https://docs.agno.com/production/overview)
More: [Docs](https://docs.agno.com) · [Cookbook](https://github.com/agno-agi/agno/tree/main/cookbook)
## Features
| Category | What you get |
|----------|--------------|
| **Learning** | User profiles that persist across sessions. User memories that accumulate over time. Learned knowledge that transfers across users. Always or agentic learning modes. |
| **Core** | Model-agnostic: OpenAI, Anthropic, Google, local models. Type-safe I/O with `input_schema` and `output_schema`. Async-first, built for long-running tasks. Natively multimodal (text, images, audio, video, files). |
| **Knowledge** | Agentic RAG with 20+ vector stores, hybrid search, reranking. Persistent storage for session history and state. |
| **Orchestration** | Human-in-the-loop (confirmations, approvals, overrides). Guardrails for validation and security. First-class MCP and A2A support. 100+ built-in toolkits. |
| **Production** | Ready-to-use FastAPI runtime. Integrated control plane UI. Evals for accuracy, performance, latency. |
## IDE Integration
Add our docs to your AI-enabled editor:
**Cursor:** Settings → Indexing & Docs → Add `https://docs.agno.com/llms-full.txt`
Also works with VSCode, Windsurf, and similar tools.
## Contributing
See the [contributing guide](https://github.com/agno-agi/agno/blob/main/CONTRIBUTING.md).
## Telemetry
Agno logs which model providers are used to prioritize updates. Disable with `AGNO_TELEMETRY=false`.