fast-agent
by evalstate
Define and run multi-agent workflows in Python with first-class MCP support — chains, routers, parallel fan-out, evaluator-optimizer loops, and A2A interoperability.
Skills
Workflow Patterns
Composes chain, router, parallel, and orchestrator patterns as decorators over plain Python agent definitions.
MCP Integration
Attaches MCP servers to individual agents, including sampling, roots, and elicitation beyond basic tool calling.
Evaluator Loops
Runs generator and evaluator agents in a refinement loop until output reaches a defined quality rating.
Related Agents
AgentScope
Builds multi-agent applications with a Python framework focused on transparency, observability, and tracing. Includes a…
Google ADK
Builds and orchestrates multi-agent systems with a code-first Python and Java SDK plus CLI. Google's Agent Development…
mcp-use
Build MCP servers and MCP-powered apps from one fullstack framework — connect any LLM to any MCP server, or ship agent-…
Microsoft Agent Framework
Builds and orchestrates multi-agent apps with a .NET and Python SDK. The successor unifying Semantic Kernel and AutoGen…