subcog
Persistent memory system for AI coding assistants. Captures decisions, learnings, and context from coding sessions. Features hybrid search (semantic + BM25), MCP server integration, SQLite persistence with knowledge graph, and proactive memory surfacing. Written in Rust.
Subcog is a persistent memory system for AI coding assistants that captures decisions, learnings, and context from coding sessions. It features a single-binary distribution, three-layer storage architecture (SQLite, FTS5, usearch HNSW), MCP server integration, and Claude Code hooks. It achieves high accuracy on factual recall benchmarks.
Features
Compatibility
Quick start
Use cases
Alternatives
Related searches
Comments
- BBlake WilsonMay 16, 2026
Subconscious memory layer makes the AI feel more like a continuing collaborator.
- JJamie JohnsonApr 1, 2026
Captures decisions and learnings from AI coding sessions persistently.
- AAlex JacksonMar 12, 2026
Decision capture is useful for understanding why past choices were made.
- DDakota JacksonMar 5, 2026
Good for teams who want AI assistants that learn from past project context.