CRTX – AI code gen that tests and fixes its own output (OSS)
Ditched multi-model bloat, proved single model + local test loop beats expensive debate.
AI compiles hallucinated code that pass. This fixes it before accepting it. 100% Deterministic
For example Supabase auth, it allows user metadata to be writable by clients and leaving service role keys in next.js components. I’ve tried prompting and skills.md to catch this, but it’s not consistent without good test feedback.
So I open sourced a collection of test to with no LLM involved from official docs to catch and fix bad code integrations. Enjoy
Ditched multi-model bloat, proved single model + local test loop beats expensive debate.
120+ built-in test playbooks with JSON output agents can read and fix.
Records flows and auto-fixes failing tests until green.
Self-healing Playwright tests via AI agent repair, but Playwright Inspector and Cypress already auto-fix selectors.
Auto-fix PRs with pair-reviewed AI fixes compete directly with CodeRabbit and Sweep.
Claude drafts tests locally; Decipher executes and fixes failures in cloud—smart division of labor.