Zeroshot separates AI coding from AI code checking
Zeroshot is an CLI tool built to reduce a common problem in : an AI can say the work is finished even when the code is wrong. It splits the job across separate AI roles: planners, implementers, and validators. The validator does not share the same context as the worker that wrote the code.
It checks the result by running tests in clean . If the tests pass, the work is accepted. If they fail, the validator rejects it with concrete logs so the code can be fixed.
Zeroshot saves its state in SQLite, so work can continue after a crash or interruption. It supports Claude Code, Codex, Gemini, and OpenCode.
Key points
- Zeroshot is an CLI for running .
- It uses separate planner, implementer, and validator roles.
- Validators run tests in clean without sharing the worker’s context.
- Failed work is rejected with logs until it passes the tests.
- It supports Claude Code, Codex, Gemini, and OpenCode, and stores state in SQLite.