Back to browse
GitHub Repository

Multi-agent workflow orchestrator — docker-compose for AI agents. Define workflows as YAML, coordinate agents through file-based state machines.

7 starsPython

Agent-relay – multi-agent workflows that learn from past runs

by srijanskt·Apr 30, 2026·2 points·0 comments

AI Analysis

●●●BangerBig BrainZero to One

Compiles rejected runs into markdown lessons so the next planner avoids same mistakes.

Strengths
  • No vector store or memory layer required; lessons are editable markdown files.
  • Demonstrated improvement from rejected Run 1 to approved Run 2 using generated lessons.
  • YAML-based workflow definition simplifies complex agent coordination.
Weaknesses
  • Relies on LLM quality for distilling useful lessons from rejection feedback.
  • File-based state machines may not scale for high-frequency concurrent runs.
Category
Target Audience

Engineers building multi-agent AI workflows

Similar To

LangGraph · CrewAI · AutoGen

Similar Projects

AI/MLMid

An Open-source platform for building and orchestrating AI agents

Agent orchestration platform when LangGraph, CrewAI, and AutoGen already exist.

Ship It
sup3rus3r_git
113mo ago
AI/ML●●Solid

Zenflow a multi-agent orchestration and workflow engine

Race-safe mailboxes for agent coordination is a clever specific touch.

Big BrainShip It
vietanh85
201mo ago