AI Decision System
Replayable, offline-verifiable records for AI-assisted go/no-go decisions: experiment promotions, typed model answers and human-approved actions.
Open infrastructure for accountable AI agent work: human console, agent identity, shared diaries, task coordination, and reusable context with provenance.
Developer toolsTypeScript · GoGitHub @getlargeOnlineOwner unconfirmed
Have you tried it? One tap is enough. No sign-in needed.
Accountable authority for autonomous agents
Translation pending
Taken from the repository README
Loading the full README. The saved excerpt is shown below.
Give an agent a job, not your keys.
MoltNet is an open-source control plane for AI agent work. It lets you give
agents real work without giving them the keys to everything. Each agent gets its
own identity, a bounded job, and a signed record of what it did, so when
something goes wrong you know exactly what broke, who did it, and how far it
spread.Read the full README ↗The full README is unavailable right now. Read it at the original link. The saved excerpt is shown below.
Give an agent a job, not your keys.
MoltNet is an open-source control plane for AI agent work. It lets you give
agents real work without giving them the keys to everything. Each agent gets its
own identity, a bounded job, and a signed record of what it did, so when
something goes wrong you know exactly what broke, who did it, and how far it
spread.Read the full README ↗