# any-agent

## Docs

- [Introduction](https://mozilla-ai.github.io/index.txt): any-agent is a Python library providing a single interface to different agent frameworks.
- [Agents - Index](https://mozilla-ai.github.io/agents/index.txt): To define any agent system you will always use the same imports:
- [Agents - Callbacks](https://mozilla-ai.github.io/agents/callbacks.txt): For greater control when running your agent, any-agent includes support for custom [Callbacks][any_agent.callbacks.base.Callback] that
- [Agents - Frameworks - Agno](https://mozilla-ai.github.io/agents/frameworks/agno.txt): https://github.com/agno-agi/agno
- [Agents - Frameworks - Google Adk](https://mozilla-ai.github.io/agents/frameworks/google_adk.txt): https://github.com/google/adk-python
- [Agents - Frameworks - Langchain](https://mozilla-ai.github.io/agents/frameworks/langchain.txt): https://github.com/langchain-ai/langchain
- [Agents - Frameworks - Llama Index](https://mozilla-ai.github.io/agents/frameworks/llama_index.txt): https://github.com/run-llama/llama_index
- [Agents - Frameworks - Openai](https://mozilla-ai.github.io/agents/frameworks/openai.txt): https://github.com/openai/openai-agents-python
- [Agents - Frameworks - Smolagents](https://mozilla-ai.github.io/agents/frameworks/smolagents.txt): https://github.com/huggingface/smolagents
- [Agents - Frameworks - Tinyagent](https://mozilla-ai.github.io/agents/frameworks/tinyagent.txt): As part of the bare bones library, we provide our own Python implementation based on HuggingFace Tiny Agents.
- [Agents - Tools](https://mozilla-ai.github.io/agents/tools.txt): any-agent provides 2 options to specify what tools are available to your agent: Callables and MCP (Model Context Protocol). In order to support multi-agent systems, any agents served via A2A can also be integrated by wrapping the A2A connection in a callable function tool as described below.
- [Tracing](https://mozilla-ai.github.io/tracing.txt): An [AgentTrace][any_agent.tracing.agent_trace.AgentTrace] is returned when calling [agent.run][any_agent.AnyAgent.run] or [agent.run_async][any_agent.AnyAgent.run_async].
- [Evaluation](https://mozilla-ai.github.io/evaluation.txt): The any-agent evaluation module encourages three approaches for evaluating agent traces:
- [Serving](https://mozilla-ai.github.io/serving.txt): any-agent provides a simple way of serving agents from any of the supported frameworks using the
- [Api - Agent](https://mozilla-ai.github.io/api/agent.txt)
- [Api - Callbacks](https://mozilla-ai.github.io/api/callbacks.txt)
- [Api - Config](https://mozilla-ai.github.io/api/config.txt)
- [Api - Evaluation](https://mozilla-ai.github.io/api/evaluation.txt)
- [Api - Logging](https://mozilla-ai.github.io/api/logging.txt): any-agent comes with a logger powered by Rich
- [Api - Serving](https://mozilla-ai.github.io/api/serving.txt)
- [Api - Tools](https://mozilla-ai.github.io/api/tools.txt)
- [Api - Tracing](https://mozilla-ai.github.io/api/tracing.txt)