Vibe Coding Discoverhippo-memory
View on GitHubBiologically-inspired memory for AI agents. Decay, retrieval strengthening, consolidation. Zero runtime deps, SQLite, MCP. Benchmarked retrieval with an opt-in TypeSafe Jev reranker.
Biologically-inspired long-term memory layer for AI agents: memories decay by default and strengthen on retrieval, with buffer/episodic/semantic consolidation. SQLite-backed, zero runtime deps, exposes MCP so Claude Code, Cursor, Codex and other agents share one portable store.
Use Cases
Give CLI coding agents durable long-term memory across sessionsShare one memory store across Claude Code, Cursor, and CodexSurface past errors so agents stop repeating the same mistakeImport ChatGPT memories, CLAUDE.md, and .cursorrules into one storeIngest Slack events as provenance-tracked memories with GDPR deletionCreate session handoffs so the next agent resumes where you left offMaintain a bounded working-memory scratchpad per scopeExplainable recall showing why a memory was retrievedSleep-time consolidation of decayed and deduplicated memoriesMulti-tenant memory with API keys and audit log
Built With
- Language
- TypeScript
- Frameworks
- Model Context Protocol · SQLite · TypeScript · Node.js · Transformers.js · Claude Code · Codex · Cursor · OpenCode · OpenClaw · Vitest · OpenLint
Tags
agent-memory · long-term-memory · memory-decay · consolidation · retrieval · hybrid-search · bm25 · embeddings · sqlite · mcp · provenance · multi-tenant · cross-tool · cli · session-handoff · working-memory