agno

What it is and what it does

Agno is a framework for building agent platforms—systems where AI agents perform tasks autonomously or with human oversight. It provides an SDK to define agents, a runtime (AgentOS) to execute them as services, and a web UI to manage the platform. The package includes 10 runtime dependencies (pydantic, httpx, pyyaml, rich, and others) that handle configuration, HTTP communication, and data validation.

The framework is designed to give you control over your agent stack: you own the data, memory, and security model (JWT-based role-based access control). It supports scheduling, human approval workflows, observability via OpenTelemetry, and deployment to any container platform. Agents can be exposed via REST API, Slack, Telegram, Discord, and other interfaces. The package sends telemetry per agent run (model provider signals only, not prompts or outputs) unless disabled via environment variable.

Use it for:

• Build a customer support agent that handles tickets autonomously with human approval for sensitive actions
• Deploy a multi-tenant agent platform where different teams manage their own agents via a web UI
• Create scheduled background jobs and cron tasks without external infrastructure
• Integrate agents with Slack, GitHub, and Postgres using pre-built toolkits
• Monitor agent runs with audit logs and OpenTelemetry tracing for compliance

Worth the install?

AI-flagged interpretation of the facts on this page — verify before relying

Agno is a framework and runtime for building, deploying, and managing agent platforms with built-in APIs, storage, security, and observability.

Yes. Agno is actively maintained, permissively licensed, has low install friction, and addresses a real need for developers building agent platforms. The framework is production-ready (Development Status 5) and offers a complete stack from agent definition through deployment and management. Start with it if you're building agents that need to run as services with multi-user control and observability.

Install

agno on PyPI

pip install agno

uv add agno

poetry add agno

Installing agno

Before you install

Low install friction with a pure-Python wheel and no compiled dependencies. Actively maintained with a release 1 day old and 41712 repository stars. Supports Python 3.9 through 3.13.

License in practice

Apache-2.0 permissive license allows commercial use, modification, and redistribution with minimal restrictions—suitable for proprietary applications.

Quickstart

pip install agno

from agno import Agent

agent = Agent()
response = agent.run("Your task here")

Verify before relying

• Whether the 50+ API endpoints and 100+ integrations mentioned in the description are current as of version 2.9.0
• Performance characteristics and scaling limits for concurrent agent runs
• Whether telemetry can be fully disabled and what data is actually collected per run

Package facts

Evidence: agno-2.9.0-py3-none-any.whl

Keywords: agno, agentos, agents

Tags

More Artificial Intelligence packages

Further reading