fast-agent
View on GitHubCode, Build and Evaluate agents - excellent Model and Skills/MCP/ACP/A2A Support
Python framework and CLI for building, running and evaluating LLM agents and workflows, with first-class MCP (client/server, sampling, elicitations), Agent Skills, ACP and A2A support. Includes a TUI coding agent plus declarative agent/workflow definitions and broad model provider coverage.
Use Cases
build and run LLM agentsconnect to MCP servers over stdio/HTTP with OAuthexpose agents as MCP serverscompose agent workflows (chain, routing, orchestrator-workers)use as a terminal coding agentevaluate and test agent workflowsAgent Skills (SKILL.md) packsrun agents inside ACP clientsA2A agent-to-agent communicationuse local models via llama.cpp/Ollamastructured outputs, PDF and vision taskshuman-in-the-loop input and elicitationstoken accounting and streaming metricsMCP transport diagnostics
Built With
- Language
- Python
- Frameworks
- fastmcp · mcp · a2a-sdk · agent-client-protocol · pydantic · fastapi · typer · rich · prompt-toolkit · textual · opentelemetry · google-genai · openai · anthropic · tensorzero · uvloop
Tags
agents · mcp · mcp-client · mcp-server · a2a · acp · agent-skills · cli · tui · multi-agent · workflows · structured-outputs · multimodal · evaluation · ollama · python