SwarmWright
Self-hosted multi-agent AI orchestration platform for agentic LLM workflows
SwarmWright is a self-hosted, Docker-based platform for designing and running multi-agent AI workflows using a visual canvas and topology-enforced agent graphs. It provides human-in-the-loop approval gates, full audit trails, and granular permission controls so teams can deploy AI agents with confidence and compliance. Agents are defined in plain markdown, orchestrated via a single config, and all data stays locally on the user's machine.
Users spin up a Docker container, design agent graphs on a visual canvas, define agent constitutions in plain markdown, and orchestrate workflows with topology enforcement, approval inboxes, and real-time monitoring.
Small teams and compliance-conscious organizations deploying AI agent workflows
Background.
- Status
- launched
- Business model
- free
Founders
- Ralph Barendsegithub
Similar projects.
Editorial take on the space this project sits in — momentum signals, adjacent moves, our call on whether the wedge is real. Get pinged when we publish a new read or when the landscape shifts.
Have a take on this space?
Tell us what you’d build differently, where you think the incumbents miss, or what we’ve gotten wrong about this project. Comments + reactions are coming soon.