Show HN: Mnemolith – AI coding memory that goes stale when your code changes

Anish released Mnemolith v0.2.1, an MCP server that gives Claude Code, Cursor and Codex a shared per-project memory keyed by git repo and invalidates memories when linked files change. Mnemolith stores each dependency file's git blob hash and sets a memory aside for review when contents change, with contradictions judged by the agent rather than a similarity threshold — Anish said "we use Postgres" versus "we migrated to MySQL" scored only 0.30 similarity. The tool runs on a from-scratch Java engine with a Redis-compatible server and HNSW vector index, uses local all-MiniLM-L6-v2 embeddings, requires Java 11+, and lacks team sync beyond AGENTS.md/CLAUDE.md files.

Hi HN, I'm Anish. I built Mnemolith because the AI coding tools I use Claude Code, Cursor, Codex either forget my project between sessions, or remember things that quietly stopped being true. Tell the agent "we use Postgres", migrate to MySQL two weeks later, and it keeps building on the old fact. How it works: - It's an MCP server, so Claude Code, Cursor and Codex share one memory per project keyed by the git repo . - When the agent saves a memory, it can link it to the files it depends on. Mnemolith stores each file's git blob hash. If the file's contents change committed or not , the memory is set aside and flagged for review, so the agent stops relying on it. - A local dashboard shows what the agent remembers, where each memory came from tool, session, file versions , and its full history. You can confirm a memory is still true, or retire it and say what's true now. - Contradictions are judged by the agent, not by a similarity threshold. In my calibration, "we use Postgres" vs "we migrated to MySQL" only scored 0.30 similarity, so a threshold can't tell a contradiction from an unrelated fact. - Current memories can sync into a managed section of AGENTS.md / CLAUDE.md, so they get reviewed in PRs. Under the hood it runs on an engine I wrote from scratch in Java: a Redis-compatible server with a built-in memory model and an HNSW vector index. Embeddings run locally all-MiniLM-L6-v2 . Everything stays on your machine. It's early v0.2.1 . There's no team sync yet beyond the AGENTS.md/CLAUDE.md files, and it needs Java 11+ it downloads a private copy if you don't have one . I'd really like feedback, especially from people running coding agents on real codebases. What does your agent keep getting wrong? Comments URL: https://news.ycombinator.com/item?id=50199581 https://news.ycombinator.com/item?id=50199581 Points: 1 Comments: 0