Esta página se muestra en inglés. Una traducción al español está en curso.
SkillsApr 1, 2026·2 min de lectura

Agno — Production AI Agent Runtime

Agno is a runtime for building and managing agentic software at scale. 39.1K+ GitHub stars. Stateful agents, FastAPI serving, 100+ integrations, tracing. Apache 2.0.

Introducción

Agno is a runtime for building, running, and managing agentic software at scale. With 39,100+ GitHub stars and Apache 2.0 license, it provides stateful agents with streaming responses and per-user/session isolation, production API serving via FastAPI backend, native tracing and auditability, human-in-the-loop approval workflows, guardrails, 100+ integrations and tool support, AgentOS UI for monitoring and management, and horizontally scalable stateless runtime with data stored in your own database.

Best for: Teams deploying AI agents as production services with monitoring and management Works with: Claude Code, OpenAI Codex, Cursor, Gemini CLI, Windsurf Architecture: FastAPI backend, horizontally scalable, stateless


Key Features

  • Stateful agents: Per-user/session isolation with streaming
  • Production serving: FastAPI backend with API endpoints
  • Native tracing: Built-in auditability and observability
  • Human-in-the-loop: Approval workflows and guardrails
  • 100+ integrations: Tools, databases, APIs
  • AgentOS UI: Web dashboard for monitoring and management
  • Horizontally scalable: Stateless runtime, your own database

FAQ

Q: What is Agno? A: Agno is a production AI agent runtime with 39.1K+ stars. Stateful agents, FastAPI serving, tracing, human-in-the-loop, 100+ integrations. Apache 2.0.

Q: How do I install Agno? A: pip install agno. Create agents with Agent(model=OpenAIChat()) and serve with FastAPI.


🙏

Fuente y agradecimientos

Created by Agno. Licensed under Apache 2.0. agno-agi/agno — 39,100+ GitHub stars

Discusión

Inicia sesión para unirte a la discusión.
Aún no hay comentarios. Sé el primero en compartir tus ideas.