SwarmWright, structured multi-agent AI defined in markdowns

Name: SwarmWright, structured multi-agent AI defined in markdowns
Availability: InStock
Author: ralphbarendse

by ralphbarendse·May 15, 2026·4 points·0 comments

Visit Project View on HN

AI Analysis

●●●BangerBig BrainSolve My ProblemShip It

Markdown-defined agents with enforced topology—finally structured autonomy that compliance can approve.

Strengths

•Agents as plain markdown files makes workflows readable by non-technical stakeholders
•Runtime enforces declared connections preventing unauthorized agent-to-agent calls
•Two Docker commands to self-host with real-time observability built in

Weaknesses

•No authentication yet—requires keeping the port unexposed for security
•CC BY-NC license limits commercial use without separate agreement

Post Description

I had a bunch of custom AI pipelines and a growing folder of markdown files and Python scripts holding it together. Built this to give that chaos some structure.

Agents are markdown files, topology is a JSON file the runtime enforces hard. The agents are still fully autonomous: they make their own decisions, but the graph they operate in isn't. You declare who can call whom upfront and the runtime holds that line.

No auth yet, fine if you don't expose the port, i guess. Two Docker commands to run it.