Engrim - Universal local-first SQLite memory engine for AI CLIs
Show HN: Engrim – A universal, local-first SQLite memory engine for AI CLIs
Engrim is a local-first, project-scoped SQLite memory engine that gives AI coding agents a persistent, cross-model episodic memory. It enables seamless switching between Google Antigravity, Claude Code, Cursor, and Windsurf on the same project without losing context or architectural decisions. By consolidating key decisions and state into a compact, curated memory pack, Engrim dramatically reduces token usage and eliminates context amnesia. It features hybrid retrieval (BM25 + vector embeddings), agent provenance tracking, and a hardened MCP server, all while keeping data 100% local and private.
Why pay for 200,000 tokens of forgotten noise on every turn? The models are disposable utilities; your project's decisions are not.
- flippant
Congrats on releasing!
I've been using another memory plugin [1] for the past couple months. Since this change, I almost never run session compaction. Instead, I opt to just make a new session, give the agent a task, and have it figure out what happened in previous session(s).
Decision summaries look really cool -- though the agent/model info probably won't be useful for me because I don't actually ever let agents commit code autonomously (even in branches).
- [1] https://ctx.rs/
- thih9
> Run engrim setup without arguments. It automatically detects installed environments on your machine and configures them all
Does it come with an uninstall script?
- cedws
Does agent memory actually work as a concept yet? I've only seen LLMs commit garbage to memory and recall in irrelevant contexts.
- aidiveyt
Stop hooks can block the turn too: exit 2 with a message and the session keeps working until the check passes.
- whsoul
I like this local-first concept.
you have already good desktop resource.