Open Multi-Agent

Self-hosted TypeScript AI agent runtime with durable approvals and verifiable, auditable run records.

PlatformWebfree

Open Multi-Agent is a self-hosted TypeScript runtime for AI agents where consequential actions wait for durable, tamper-evident approvals and every run leaves a verifiable, offline-checkable record. It has no telemetry or hosted control plane, and works with cloud, local, or other model providers under the operator's own keys. It's built for organizations that want to own and audit what their AI agents do rather than trust a vendor's control plane.

Website

Full match profile

Behind the summary, Matchbox keeps a richer profile of Open Multi-Agent - the signals our matcher actually reads to decide when to surface it. It stays private; claim the listing to see and control it.

Problem & pain-point mapping
Who we surface it to (audience fit)
What it's a strong alternative to
Trust & credibility signals

Claim Open Multi-Agent to unlock →

Something wrong with this listing — dead link, not a real product, wrong info?

Try Matchbox with your own problem

Describe what is not working - we’ll show you whether Open Multi-Agent (or something else) actually fits.

Try a problem