Write tasks
Describe what your agent should do and how it should do it. Pome runs each task against digital twins of the APIs it calls.
Your agent runs against digital twins of GitHub, Stripe, Slack, Gmail, and Linear — graded against the live API every day. Every run comes back scored.
One command boots a digital twin on your own machine. It prints its MCP URL and its own token, so you can point an agent at a real GitHub, Stripe, Slack, Gmail, or Linear surface before you sign up for anything. The twins are Apache-2.0 and the runtime is public.
npx @pome-sh/cli twin start githubNeeds Node.js 24 or newer. Everything ships in @pome-sh/cli. Grading a run against pass/fail criteria is the hosted half.
Start a sandbox and run your agent against digital twins of the real APIs at every stage of development. Test edge cases that track API changes and production failures.
Describe what your agent should do and how it should do it. Pome runs each task against digital twins of the APIs it calls.
Every tool call and state mutation is logged into a replayable audit trail. Rewind and debug multi-step failures that standard observability misses.
Surface every destructive action from production traces. Toggle off unauthorized calls. Past tasks inform future runs to prevent regressions.
Every run is graded on what actually changed inside the digital twins — exact assertions on tool calls and state, not an opinion about the transcript.
01
Assert on twin state and tool calls after each run. Identical seeds produce identical results, so you can gate merges in CI. This is what grades a run by default.
02
For open-ended behavior you can opt a task into a judge model that scores the run against your rubric and cites what failed. It is in beta, it is off unless you ask for it, and it is not what gates a merge.
Explore by path
Ready to try it
Book a demo for a walkthrough or try it yourself.
Frameworks & agents we support