The datasheet for every AI agent

SearchSearch agents (press slash)Submit an agent

Agno

Own Agno? Claim this listing

An Apache 2.0 Python agent SDK and AgentOS runtime, with a Control Plane you run in your own cloud.

Visit Agno Compare
Screenshot of AgnoVerified · theagentsindex.com
Category
Agent frameworks
From
Free
Pricing model
freemium
Free tier
Yes
Deployment
Self-host
Interface
Library
Open source
Yes
Public API
Yes
Model / LLM
Model-agnostic (20+ providers —…

Facts re-verified

Our verdict

Agno is a fast-moving open-source project that started in 2023 as Phidata, a data-engineering toolkit, became Agno in January 2025 and now ships as three pieces: the free Apache 2.0 Agent SDK, the free AgentOS runtime, and the AgentOS Control Plane, which is local and free on the developer machine and becomes a live hosted URL on the paid Pro tier.

The current version (Agno 3.0) is positioned as "built for coding agents" and ships its docs as an MCP server at docs.agno.com/mcp so a coding agent can scaffold a platform from documented parts.

The SDK page quotes a 3.2-microsecond agent instantiation and 5.2 KiB of memory per agent, measured on a public harness the team publishes, which is more defensible than the older "10,000x faster than LangGraph" claim and is the one you should treat as the speed story today. 30+ model providers and 100+ tool integrations sit behind one Python API.

The honest catches: the paid Pro tier is the only entry point for a hosted production Control Plane at $150/month with no per-seat or per-connection add-ons published today, and self-hosting the Control Plane is gated to Enterprise. Pick Agno for an Apache 2.0 Python SDK with memory, knowledge, learning, guardrails and a Control Plane you keep inside your own cloud. Look at CrewAI instead if a fully managed cloud runtime matters more than owning the infrastructure yourself.

What is Agno?

Agno is an open-source Python SDK for building agents, teams and workflows, paired with AgentOS, the runtime that serves them, and the AgentOS Control Plane, a web UI you connect to from your browser. The SDK and AgentOS are Apache 2.0 and free. The paid Pro tier adds a live hosted Control Plane at a real URL with shared, role-scoped access.

Enterprise adds a self-hosted Control Plane, SLAs and a dedicated technical lead. Founded in 2023 as Phidata, the project rebranded to Agno in January 2025 and ships as Agno 3.0 today. The codebase sits under the agno-agi organisation at 41,839 GitHub stars and 5,807 forks.

What does Agno do?

You build agents, teams and workflows in Python with the Agno SDK. Capabilities attach as needed: learning, context providers, memory, knowledge, state, storage, sessions, guardrails, hooks, dependencies, a filesystem and human-in-the-loop. There are 30+ model providers and 100+ tool integrations behind one API.

An agent is created in 3.2 microseconds and holds 5.2 KiB of memory, measured on a public harness you can run yourself. Register the same agents, teams and workflows with AgentOS and they run behind a FastAPI application. AgentOS exposes 50+ REST endpoints with SSE and websockets for sessions, memory, knowledge and traces, and ships observability, background execution, evals, a scheduler and JWT-based RBAC.

The Control Plane is a web UI you connect to from your browser to the runtime in your own cloud, so data stays in your database. The SDK docs are also exposed as an MCP server at docs.agno.com/mcp, so a coding agent can scaffold a platform from documented parts.

How Agno works

  1. Install the SDK (pip install agno) and define an Agent, a Team (coordinate, route, broadcast or tasks mode) or a Workflow (Step, Steps, Parallel, Loop, Condition, Router) in Python.
  2. Attach the capabilities you need: learning, context providers, memory, knowledge, state, storage, sessions, guardrails, hooks, dependencies, filesystem and human-in-the-loop.
  3. Register the same Agents, Teams and Workflows with AgentOS to serve them behind a FastAPI application with 50+ REST endpoints, SSE and websockets.
  4. Connect the AgentOS Control Plane (free, local on the developer machine; hosted on Pro; self-hosted on Enterprise) for chat, tracing, sessions, knowledge, memory and evals.

Key features

Apache 2.0 Agent SDK
Python SDK for building agents, teams and workflows. Three primitives (Agent, Team, Workflow) and attachable capabilities including memory, knowledge, learning, guardrails, hooks and human-in-the-loop.
Model-agnostic, 30+ providers
OpenAI, Anthropic, Google and 27 other providers behind one API. Switch providers without rewriting agent code.
100+ tool integrations
Pre-built toolkits for GitHub, Slack, Postgres, and more. Plus native MCP support, both consuming external MCP servers and exposing agents as MCP servers.
AgentOS runtime
50+ REST endpoints with SSE and websockets, sessions, memory, knowledge, traces, background execution, evals, scheduler and JWT-based RBAC. Runs in your own cloud.
AgentOS Control Plane
Web UI to manage agents, sessions, knowledge, memory and evals. Connects from your browser directly to your runtime, so data stays in your database. Free locally on the developer machine, hosted on Pro.
Docs as an MCP server
The full documentation is exposed at docs.agno.com/mcp, so a coding agent (Claude Code, Cursor, Codex) can scaffold a platform from documented parts.

What are Agno's use cases?

Building an internal agent platform with coding-agent scaffolding
A Python team hands the docs MCP URL to Claude Code or Cursor and the coding agent scaffolds an agent platform from documented parts, with memory, knowledge, sessions and a Control Plane the team operates inside their own AWS or GCP account.
Multi-agent research or support team
A developer composes several specialist agents (researcher, writer, reviewer) in an Agno Team that shares context and hands off work, coordinated rather than as a single monolithic agent.
Regulated deployment inside a private cloud
A team whose agents touch sensitive data runs AgentOS in their own Railway, AWS, GCP, Azure or air-gapped Helm environment, so sessions, memory, knowledge and traces stay in infrastructure they control.

Who is Agno for?

  • Python developers who want a fast, lightweight, model-agnostic framework for building individual agents or collaborating multi-agent teams
  • Teams that want built-in memory, knowledge/RAG and native MCP support without assembling those pieces from separate libraries
  • Teams that need a production runtime (monitoring, HITL approval, RBAC, audit logs) they operate inside their own cloud account rather than a third-party's

Not forTeams that want a fully managed, zero-infrastructure cloud runtime with no cloud account of their own to operate. CrewAI's managed cloud or a no-code agent platform fits that need better than Agno's paid tier, which still requires running your own Postgres and container host.

What does Agno integrate with?

  • 30+ LLM providers (OpenAI, Anthropic, Google and others)
  • 100+ tool integrations including GitHub, Slack, Postgres
  • Model Context Protocol (MCP), both consuming and exposing
  • Chat channels: Slack, Telegram, WhatsApp, Discord, AG-UI, A2A
  • Deploy targets: Docker, Railway, AWS, GCP, Azure, Fly, Render, Modal, Helm

Why use Agno?

  1. Apache 2.0 SDK and runtime with 41,839 GitHub stars, an active and growing project rather than an abandoned one.
  2. A 3.2-microsecond agent instantiation measured on a public, self-runnable harness, a more defensible speed story than marketing superlatives.
  3. Memory, knowledge, learning, guardrails, hooks and human-in-the-loop ship built in, so fewer separate libraries to assemble and keep compatible.
  4. Control Plane connects from your browser to your runtime in your own cloud, so data stays in your database.
  5. Docs ship as an MCP server, so a coding agent can scaffold a platform from documented parts.

What are Agno's pros and cons?

What's great

  • Apache 2.0 SDK and runtime, free, with 41,839 GitHub stars and 5,807 forks under agno-agi, an active and growing project.
  • The SDK quotes a 3.2-microsecond agent instantiation and 5.2 KiB of memory per agent, measured on a public harness you can run yourself, a more defensible speed story than the older "10,000x faster than LangGraph" headline figure.
  • The Control Plane connects from the browser directly to a runtime in your own cloud, so sessions, memory, knowledge and traces stay in your database, not a vendor's.
  • Docs ship as an MCP server at docs.agno.com/mcp, so a coding agent (Claude Code, Cursor, Codex) can scaffold an agent platform from documented parts.

Watch-outs

  • Self-hosting the Control Plane is gated to Enterprise. Free gets a local-only Control Plane on the developer machine; Pro gets a hosted Control Plane at a real URL but the customer still pays for hosting and operates their own database.
  • The January 2025 rebrand from Phidata and the rename of "Agent Framework" to "Agent SDK" with the 3.0 release mean older tutorials, Stack Overflow answers and blog posts can reference outdated import paths or a pre-3.0 API surface.
  • The Control Plane lives in the same repo as the SDK and AgentOS, so platform upgrades ride along with framework upgrades. A pinned SDK version does not pin the Control Plane.
  • The 3.2-microsecond / 5.2 KiB figure is measured on Agno's own published harness. Independent, reproducible benchmarks against LangGraph on neutral hardware were not found.
  • Tutorial content predating the January 2025 Phidata-to-Agno rebrand and predating the SDK 3.0 release may reference a stale import path or API surface.
  • Agno sends a telemetry event per agent run by default, with prompts, messages and outputs excluded. Disable with AGNO_TELEMETRY=false.

Agno pricing

Free SDK and AgentOS, Apache 2.0. Free Control Plane runs locally. Hosted Pro Control Plane $150/month with shared, role-scoped access. Enterprise is custom and adds a self-hosted Control Plane option.

  • Free

    Free

    • Full Apache 2.0 SDK and AgentOS runtime
    • Local Control Plane: chat, tracing, sessions, knowledge, memory and evals
    • Community support

  • Pro

    $150/mo

    • Everything in Free
    • Hosted Control Plane at a real URL
    • Shared, role-scoped access for the team

  • Enterprise

    Custom (contact sales)

    • Everything in Pro
    • Self-hosted Control Plane option
    • Ship agents to your own end users
    • Support SLA
    • Dedicated technical lead

See current pricing on agno.com ↗Compare Agno alternatives →

Frequently asked questions

Is Agno free and open-source?
Yes. The SDK and AgentOS runtime are Apache 2.0 and free. The Control Plane is free and runs locally on the developer machine. A hosted Control Plane at a real URL costs $150/month on Pro. Self-hosted Control Plane is Enterprise.
Is Agno the same as Phidata?
Yes. Agno is the rebrand of Phidata, announced in January 2025. The GitHub organisation moved from phidatahq/phidata to agno-agi/agno. The current release line is Agno 3.0, which renamed "Agent Framework" to "Agent SDK".
How much does Agno cost?
The SDK and AgentOS are free, Apache 2.0. A hosted Control Plane is $150/month on Pro. Enterprise is custom and adds a self-hosted Control Plane option, the ability to ship agents to your own end users, SLAs and a dedicated technical lead.
Which LLM providers does Agno support?
30+ providers including OpenAI, Anthropic, Google and others behind one Python API, so agent code is not rewritten when switching providers.
Can AgentOS run agents built on other frameworks?
AgentOS serves agents, teams and workflows registered through the Agno SDK. It is not a runtime for arbitrary third-party agent frameworks.
Where does Agno's data live?
Sessions, memory, knowledge and traces are stored in your own Postgres database when you run AgentOS yourself. The Pro hosted Control Plane connects from your browser to a runtime in your cloud.

Agno alternatives

  • CrewAI

    The closer comparison on business model: another open-source Python multi-agent framework with a paid production layer, but CrewAI's is a fully managed cloud runtime with real production volume, while Agno's paid tier still runs inside the customer's own cloud account.

  • Pydantic AI

    A framework centred on type-safe, validated structured output via your own Pydantic models, for teams whose main production problem is malformed model output rather than Agno's built-in memory, knowledge, learning and multi-agent-team primitives.

  • LangChain

    The largest, most battle-tested ecosystem with the widest third-party integration surface, for teams that want the deepest community and tooling rather than Agno's narrower but faster, more opinionated SDK.

  • Compare the whole category

    Every agent in Agent frameworks, side by side on the same fields.

Visit AgnoOpens the vendor's own siteCompare AgnoSide by side with the categorySee alternativesOther options worth weighing

Anything to add?

This page is researched and re-verified by our editors — but the people who actually use Agno know things we cannot see from the outside.

Report an issueSomething wrong, outdated or a dead link? Tell us and we re-verify.
Write a reviewUsed Agno? Your experience helps the next buyer decide.
Get a quote from AgnoTell us what you need and we make the introduction.
Get weekly Agent frameworks updates

New agents and fresh verdicts. One short email, every week. One-click unsubscribe.