Back to browse
GitHub Repository

Declarative language for multi-agent AI workflows. Compose .aflow files → MCP tools in Claude Code. No integration code.

9 starsTypeScript

I'm a photographer. I built a DSL for multi-agent workflows

by westhills·May 31, 2026·5 points·1 comment

AI Analysis

●●SolidBig BrainNiche Gem

DSL approach beats LangGraph's Python boilerplate for reviewable workflows.

Strengths
  • Declarative .aflow files replace 40 lines of Python boilerplate with 20 lines of config.
  • Automatic MCP integration means each workflow becomes a Claude Code tool instantly.
  • Per-agent model aliases let you mix local-fast, OpenRouter, and Claude in one workflow.
Weaknesses
  • Very early stage with only 3 stars — unclear production adoption or community support.
  • Niche audience requires both Claude Code usage and multi-agent workflow needs.
Target Audience

Developers building multi-agent AI workflows with Claude Code

Similar To

LangGraph · CrewAI · AutoGen

Similar Projects

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
AI/ML●●Solid

An experimental tensor DSL/compiler with explicit scheduling

Three-concept scheduling model targeting FlashAttention, but generated code isn't performant yet.

Big BrainBold Bet
loganboyd
5117d ago