zircote/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.
This project provides a persistent memory system for AI coding assistants. It automatically captures decisions, learnings, and contextual information from your coding sessions, then makes them easily searchable and proactively surfaces relevant details. Developers and engineers who use AI coding assistants will find this useful for improving their assistant's recall and performance over time.
Use this if your AI coding assistant frequently 'forgets' previous conversations, decisions, or code context, and you want it to retain and leverage that knowledge across sessions.
Not ideal if you don't use AI coding assistants or are looking for a general-purpose database rather than a specialized memory system for AI.
Stars
17
Forks
4
Language
Rust
License
MIT
Category
Last pushed
Mar 10, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/vector-db/zircote/subcog"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
topoteretes/cognee
Knowledge Engine for AI Agent Memory in 6 lines of code
CaviraOSS/OpenMemory
Local persistent memory store for LLM applications including claude desktop, github copilot,...
verygoodplugins/automem
AutoMem is a graph-vector memory service that gives AI assistants durable, relational memory:
CortexReach/memory-lancedb-pro
Enhanced LanceDB memory plugin for OpenClaw — Hybrid Retrieval (Vector + BM25), Cross-Encoder...
divagr18/memlayer
Plug-and-play memory for LLMs in 3 lines of code. Add persistent, intelligent, human-like memory...