Where most memory tools help your agent remember more, mnemoa helps it forget what no longer belongs.

A developer built mnemoa, a Rust-based tool that scans coding-agent instruction files like AGENTS.md and CLAUDE.md to find stale, redundant and contradictory lines so they can be pruned rather than accumulated. The tool runs deterministic checks locally, models how seven agents (including Claude Code, Codex, Cursor and Copilot) load instruction files, and can produce a dry-run prune plan with estimated token costs before and after, plus a GitHub Action for CI drift checks. An optional LLM feature for drafting rules is disabled by default, and the tool is available via CLI, an optional HTTP API and a Python SDK.

mnemoa is built to make coding agents forget: it finds the stale, redundant and contradictory lines in AGENTS.md, CLAUDE.md and other instruction files, so they can be deleted rather than piled on. Coding agents rely on files like AGENTS.md , CLAUDE.md , and project plans to understand a codebase. Over time, those files can get long, repeat rules already enforced by tools, and point to paths or commands that no longer exist. I built mnemoa to help keep that repo memory small, accurate, and useful. mnemoa scans a repository’s agent instruction files and plans. It checks for issues such as: It can also create a prune plan showing what it would remove or move, along with the estimated token cost before and after. You can review the diff before applying it. Some instructions describe rules that tools can already enforce. mnemoa can help turn those rules into checks, such as EditorConfig settings, Cargo lints, Ruff settings, ast-grep rules, or pre-commit hooks. It records the promotion in a ledger, so the instruction can leave the context file without losing track of why it existed. The goal is to keep useful guidance available while reducing repetition and stale instructions. mnemoa is written in Rust and runs deterministic checks locally. The optional LLM feature can help draft rules, but it is disabled by default. You can use the CLI, run the optional HTTP API, or connect through the Python SDK. It models how seven coding agents load instruction files: Claude Code, Codex, Cursor, Copilot, Kiro, Cline, and Gemini. Install from the repository and scan a project: cargo install --path crates/mnemoa-cli mnemoa scan . mnemoa forget mnemoa forget shows a dry-run plan. To apply the changes after reviewing them: mnemoa forget --apply --yes The project also includes a GitHub Action for running scans and drift checks in CI. I’d especially like to hear how mnemoa handles real instruction files: which findings are useful, which ones are noisy, and what kinds of repo drift it should catch next.