Wy turns an uncommitted diff into the questions you would need to answer to accept it, and shows which of them the agent own record actually answers. It imports existing local Codex, Claude Code, pi and OpenCode history, so no recorder has to be running first.
Be the first to rate Wy. Your feedback helps other users decide.
Four boxes: What changed, What to worry about, Was it tested and Progress, and every row opens its evidence.
The Steps screen shows the session as intent-sized steps, each with Why, Check, Gap and the worries it raises.
Verdicts persist and export as a review in your voice, push-backs first, so they paste back to the agent as the next instruction.
Similar tools in the same category — compare side-by-side
Seahaven is an open-source Python framework for building synthetic worlds: working copies of your ag...
LLMSchema extracts database schemas from PostgreSQL, MySQL and SQLite into simple, concise Markdown ...
DiffGuardian gives you a spoken walkthrough of a pull request or codebase, highlighting the code and...
Guides and comparisons about code tools
Eleven Show HN launches built for the moment after the agent finishes: PR walkthroughs, review bots, drift tests for MCP servers and scoped access.
Five Show HN launches for the parts around a coding agent: shared sessions, a leaner CLI, a commit review gate, cheaper routing and one governed MCP gateway.
Eleven Show HN launches that sit beneath the coding agent: deployment targets, repo-native work boards, session lists, cleanup skills and schema docs.
Eleven Show HN launches for the unglamorous middle: vector search, Postgres indexes, waste audits, budget breakers, routing, inference fleets and optimizers.
Eight Show HN launches where the agent owns the device rather than the editor: desktop control, phones, memory pressure, kernel security and live repair.
