What is Any Agent

any-agent is a unified interface designed to facilitate the use and evaluation of various agent frameworks, allowing users to seamlessly integrate and compare different technologies.

Use cases

Use cases for any-agent include developing AI applications that leverage different agent frameworks, conducting comparative evaluations of agent performance, and simplifying the integration process for developers working with diverse technologies.

How to use

To use any-agent, users can refer to the comprehensive documentation available online, which includes guides on agents, tools, tracing, serving, and evaluation. Users can set up their environment and follow the instructions to implement different agent frameworks.

Key features

Key features of any-agent include support for multiple agent frameworks, a single interface for evaluation, detailed documentation, and tools for tracing and serving agents, making it easier for developers to work with different technologies.

Where to use

any-agent can be utilized in various fields such as artificial intelligence, machine learning, and software development, particularly in projects that require the integration of multiple agent frameworks.

Documentation

• Agents
• Tools
• Tracing
• Serving
• Evaluation

Supported Frameworks

Agno AI

Planned for Support (Contributions Welcome!)

Open Github tickets for new frameworks

Requirements

• Python 3.11 or newer

Quickstart

Refer to pyproject.toml for a list of the options available.
Update your pip install command to include the frameworks that you plan on using:

pip install 'any-agent'

To define any agent system you will always use the same imports:

from any_agent import AgentConfig, AnyAgent

For this example we use a model hosted by openai, but you may need to set the relevant API key for whichever provider being used.
See our Model docs for more information about using different models.

export OPENAI_API_KEY="YOUR_KEY_HERE"  # or MISTRAL_API_KEY, etc

from any_agent.tools import search_web, visit_webpage

agent = AnyAgent.create(
    "tinyagent",  # See all options in https://mozilla-ai.github.io/any-agent/
    AgentConfig(
        model_id="gpt-4.1-nano",
        instructions="Use the tools to find an answer",
        tools=[search_web, visit_webpage]
    )
)

agent_trace = agent.run("Which Agent Framework is the best??")
print(agent_trace)

[!TIP]
Multi-agent can be implemented today using the A2A protocol (see A2A docs)
and will be also supported with Agent-As-Tools (follow progress at https://github.com/mozilla-ai/any-agent/issues/382)

Cookbooks

Get started quickly with these practical examples:

• Creating your first agent - Build a simple agent with web search capabilities
• Creating an agent with MCP - Integrate Model Context Protocol tools
• Serve an Agent with A2A - Deploy agents with Agent-to-Agent communication
• Building Multi-Agent Systems with A2A - Using an agent as a tool for another agent to interact with.

Contributions

The AI agent space is moving fast! If you see a new agentic framework that AnyAgent doesn’t yet support, we would love for you to create a Github issue. We also welcome your support in development of additional features or functionality.

Running in Jupyter Notebook

If running in Jupyter Notebook you will need to add the following two lines before running AnyAgent, otherwise you may see the error RuntimeError: This event loop is already running. This is a known limitation of Jupyter Notebooks, see Github Issue

import nest_asyncio
nest_asyncio.apply()