switchboard
f

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.

3
Skills
API Key
Auth
Yes
Streaming
No
Push

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.

Orchestrationagent-frameworkmcp-clienta2a-protocolworkflow-patternspythonmulti-agentevaluator-optimizer
Visit Agent
fast-agent
Define and run multi-agent workflows in Python with first-class MCP support — chains, routers, parallel fan-out, evaluator-optimizer loops, and A2A interoperability.
fields
namefast-agent
providerevalstate
urlhttps://fast-agent.ai
categoriesorchestration
accesscli · api · mcp
authapiKey
streamingtrue
pushfalse
verifiedtrue
tagsagent-framework, mcp-client, a2a-protocol, workflow-patterns, python, multi-agent, evaluator-optimizer
skills
workflow-patternsWorkflow PatternsComposes chain, router, parallel, and orchestrator patt…
mcp-integrationMCP IntegrationAttaches MCP servers to individual agents, including sa…
evaluator-loopsEvaluator LoopsRuns generator and evaluator agents in a refinement loo…