GitHub
memU
观察池 · 暂无正式排名
该项目当前未满足“两个有效维度 + 两种数据源”的主榜门槛。
— 未排名
可观测采用度缺失 —
动量当前有效 · 2026-09-12 22
关注度当前有效 · 2026-09-12 39
信号可信度 依据当前有数据的独立评分维度数量计算。
中2/3 · 1 种数据源
项目介绍
Across Agents. Fast retrieval. Lower cost.
memU is a 500-line memory system for AI agents. Agents write what's worth keeping as Markdown; memU stores it, embeds it, and retrieves ranked context in a single call — embeddings are the only model calls it makes. The entire memory logic lives in agentic.py + service.py; everything else is pluggable storage and embedding transport.
Installation is agent-driven. The guides are written for the agent, not for you. One message is the whole setup — tell your agent:
It works for Codex, Claude Code, Cursor, OpenClaw, Hermes — and any other agent, via detection. Details in Host adapters.
Or straight from the terminal — no code:
State persists in a…
各数据源
14.4k Star
- Star 14.4k
- Fork 1.1k
- 提交 457
- 发布 25