Stord — The Undo Button for AI Agents
write · rev 41 saved✗ blocked · outside scope✓ rolled back · 2 filesread · logged<br>Open source · MIT · works with Claude Code, Codex & moreThe Undo Button for AI Agents<br>Let your agents run with permissions skipped. Stord records every file they read and write — attributed to the agent that did it — and makes every change reversible.<br>$npm install -g stordaicopy★ Star on GitHubJoin the cloud waitlist
See it in action<br>Every Operation, On the Record<br>An agent reads your .env and rm -rfs your build. Stord shows you exactly who did what — then stord undo brings it all back.
stord — agent flight recorder
The problem<br>Agents act with production access and no seatbelt.<br>Coding agents run with skip-permissions flags. Ops agents hold credentials broader than any employee’s. When one overwrites a config, wipes a directory, or leaks a file, there’s no record of what happened and no way back.<br>Identity tools know who the agent is. Gateways know what it called . Nobody knows what happened to your data — or can undo it.
63% of orgs can’t stop their AI agents when something goes wrong<br>33% have no audit trail of agent activity at all<br>45:1 machine identities now outnumber humans
What Stord does<br>A governance layer between agents and your files.<br>Start with the open-source CLI today — audit and undo on your own machine, zero dependencies. The cloud layer adds enforced permissions and tamper-evident, fleet-wide audit. That’s what the waitlist is for.
01 · AUDITAvailable now<br>Flight recorder<br>An append-only journal of every read, write, and delete — attributed to the exact agent, session, and user. stord log shows the timeline; stord agents shows who touched what.
02 · REVERSEAvailable now<br>The undo button<br>Every write is snapshotted before it runs. Reverse a single operation with stord undo or roll the whole tree back with stord restore — even after rm -rf. Your real git history is never touched.
03 · PERMISSIONOn the roadmap<br>Scoped agent credentials<br>Least-privilege keys per agent, not per team. Path-scoped permissions like write: /build/**, enforced — plus tamper-evident, off-host audit and a fleet dashboard. Join the waitlist →
Free & open source<br>Install it in one line.<br>One Node file, zero dependencies, MIT licensed. Works with Claude Code out of the box, and with Codex, Hermes, OpenClaw, or any custom agent via hooks.<br>★ Star on GitHubView on npm
$npm install -g stordaicopy# in any project your agents work in<br>$ stord enable<br>$ claude --dangerously-skip-permissions<br>$ stord log # everything it touched<br>$ stord undo last # take it back
Cloud — early access<br>Run your fleet. Keep the receipts.<br>The CLI is yours today. The cloud layer — enforced per-agent permissions, tamper-evident off-host audit, and a dashboard across every agent and machine — is onboarding early teams now. Join for early access and founding-user pricing.
Get early access<br>No spam — launch updates only.