Does it work with my AI coding agent?

That's the point. Refactron verifies a diff whoever authored it: Cursor, Claude Code, Copilot, Codex, a codemod, or you. Via MCP your agent can call it before it lands (early access).

What does UNPROVEN mean?

Your tests pass, but the changed lines aren't actually exercised by any test, so “green” proves nothing. We say so explicitly and list the tests to add, instead of hand-waving.

Does my code leave my machine?

No. Refactron runs locally against your real test suite in an isolated shadow tree. Nothing is sent to an external service to make the verdict.

How is this different from just running my tests in CI?

Refactron scopes the run to the blast radius of the change, tells you when the change is uncovered (UNPROVEN), lands atomically only on green, and produces a signed, reproducible record of why it was safe.

What ships today vs. what's coming?

Live today: the SQLAlchemy migration + verification report. Building in the open: the MCP server and the CI gate. Join early access to be a design partner.

All releases

Jan 30, 2026 · v1.0.13

Pattern Learning, Performance & Safety

A pattern-learning engine, AST caching, an interactive dashboard, and git-integrated rollback.

Om Sherikar

Major features

Pattern learning. Engine that learns project-specific patterns and ranks suggestions based on historical acceptance.
Interactive dashboard. Welcome animation with live system checks and an interactive session dashboard.
AST caching. Faster analysis via AST caching, incremental analysis on only changed files, and parallel processing.
Safety system. Git-integrated backup and automatic rollback before any refactoring operation.

Bug fixes

Linting. Resolved numerous linting and type-checking issues across the codebase.
Python 3.8. Additional compatibility improvements for Python 3.8.