kevin-hs-sohn/hipocampus
Drop-in memory harness for AI agents — 3-tier memory, compaction tree, hybrid search. One command to set up. Works with Claude Code and OpenClaw.
This tool gives your AI agent a 'long-term memory' by helping it proactively recall past conversations and decisions, even if you don't explicitly ask. It takes your agent's conversation history and creates a searchable topic index, then feeds that index to the agent. This is for anyone who uses AI assistants like Claude Code or OpenClaw for complex, ongoing projects and wants them to remember crucial details over weeks or months without explicit prompting.
Available on npm.
Use this if your AI agent frequently 'forgets' important past context, leading to missed considerations or redundant work in long-running projects.
Not ideal if your AI agent tasks are always short, self-contained, and don't require recalling information from weeks or months ago.
Stars
12
Forks
1
Language
JavaScript
License
MIT
Category
Last pushed
Mar 17, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/rag/kevin-hs-sohn/hipocampus"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Featured in
Higher-rated alternatives
MemoriLabs/Memori
SQL Native Memory Layer for LLMs, AI Agents & Multi-Agent Systems
volcengine/OpenViking
OpenViking is an open-source context database designed specifically for AI Agents(such as...
mem0ai/mem0
Universal memory layer for AI Agents
zjunlp/LightMem
[ICLR 2026] LightMem: Lightweight and Efficient Memory-Augmented Generation
MemTensor/MemOS
AI memory OS for LLM and Agent systems(moltbot,clawdbot,openclaw), enabling persistent Skill...