Back to directory

any-agent

A single Python interface for running and evaluating AI agents built with different frameworks such as Agno, Google ADK, LangChain, LlamaIndex, the OpenAI Agents SDK, and smolagents.

any-agent

any-agent gives developers one API to define, run, and evaluate agents built on several different agent frameworks, including Agno, Google ADK, LangChain, LlamaIndex, the OpenAI Agents SDK, and smolagents. Agents are configured with a common AgentConfig and can call tools, be traced, and be served, using whichever underlying framework is chosen.

The project also supports multi-agent systems through an agents-as-tools pattern, and ships cookbooks for building a first agent, evaluating it, using callbacks, adding MCP tools, and serving or composing agents with the A2A protocol.

The project is in soft deprecation: its distilled core has moved to a separate package, mozilla-ai-tinyagent, recommended for new projects that only need the core agent loop. any-agent continues to receive security and bug-fix updates and is best suited for comparing or evaluating agents across multiple frameworks under one API. It requires Python 3.11 or newer and installs with pip.

More in Agent frameworks

See all 902
  • Recurse

    recurse.run

    A serverless harness that lets a coding agent design, test, and deploy its own specialist sub-agents as tools, MCP servers, or bots, defined by a schema-validated manifest.

  • ProofForge

    shulgin.is-a.dev

    An AI-agent pipeline that decomposes a mathematics problem, proves each piece, and formalizes the result in Lean 4 and Mathlib until the Lean kernel accepts it, with six of its proofs already merged into Google DeepMind's formal-conjectures repository.

  • local-coder

    github.com

    Builds a local coding-agent team on top of Ollama and OpenCode by detecting the machine's hardware, recommending models for seven specialist roles, and testing whether each assigned model can actually use tools, edit a repository and pass verification.