README

The self-managing agent platform


 Introduction

Agno is a self-managing agent platform. Build agents for your company, product, or customers. Run them as durable services on AgentOS. Put them to work automating company operations.

- Build agents with the Agno, Claude Agent, or Codex SDKs. Combine agents into teams and workflows.
- Run agents as durable services with built-in API and MCP. AgentOS handles authentication, role-based access, resume/replay, human approvals, scheduling, and durable execution.
- Automate company operations with Company OS. Give agents responsibilities, organize work into projects and tasks, and configure recurring routines. People set direction and review results; agents own and execute.

Agno provides the orchestration and service layer around your agents, making them available in:

1. Your product: using the REST API.
2. Claude and ChatGPT: using the MCP server.
3. Chat apps like Slack: using Agno Interfaces.

Run your platform in your own cloud and keep your data in your control. Review conversations, inspect traces, manage knowledge, and track your agent activity using the AgentOS UI.

 Get started

Agno is built for coding agents. Start with a pre-built template and give this prompt to your coding agent:

text
Help me set up my agent platform and build my first agent.

Clone https://github.com/agno-agi/agentos-railway into a folder called agent-platform, cd into it, and follow .agents/skills/setup-platform/SKILL.md.


The setup skill runs your platform locally and helps you build your first agent. You get:

- An API server and MCP server.
- PostgreSQL storage for conversations, memory, and platform activity.
- OS Manager to help build and manage your platform.
- Claude and Codex engineers to work on your code.
- Skills for building, evaluating, and improving agents.
- A Company workspace for organizing ongoing work, with a daily maintenance routine that reviews your codebase and Agno releases and proposes platform improvements.

Connect your platform to os.agno.com to start using it. Build agents with code, use the no-code UI, or chat with the OS Manager.

Start improving your agents and platform with the /improve skill. Keep useful changes and regression tests so each round builds on the last. When you're ready, configure scheduled improvement runs in a sandbox that return pull requests for review.

 Templates for every cloud

Choose a template for your cloud: Docker · Railway · AWS · GCP · Azure · Fly.io · Render · Modal · Helm

 What's included

| Capability | What you can do |
| --- | --- |
| Agents and teams | Build agents that use tools, delegate work, and collaborate. |
| Workflows | Control execution with routing, conditions, loops, and parallel steps. |
| Memory and knowledge | Remember users across sessions and retrieve answers from your data. |
| Tools and integrations | Connect agents to APIs, databases, and MCP servers. |
| Durable execution | Persist background jobs and track their status across re

Top issues

Discussions

Latest release

Changelog

 New Features:

- 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" | "