memUNevaMind-AI/memU
Local private multi-tier memory architecture for LLMs and agents, supporting long-term user preference extraction,…
No ratings yet
Rate this skill
Stars14.4k
Forks1.1k
Watchers14.4k
Open Issues122
InstallOne-line install
UnconfirmedWhether this repository follows the Agent Skills spec (that is, whether it contains a SKILL.md) has not been verified yet. Until that is settled, clone it and use what you need:
git clone https://github.com/NevaMind-AI/memU.git
OverviewOverview
Core Features
Local private multi-tier memory architecture for LLMs and agents, supporting long-term user preference extraction, temporal knowledge graphing, and low-latency state recall.
Use Cases & Scenarios
个人长期偏好事实抽取环节, 多轮会话时序关联记忆沉淀环节, 本地私有化智能体记忆召回环节.
Target Professions
AI / Algorithm Engineer, Backend Engineer.
TopicsTopics
RatingUser ratings
Nobody has rated this skill yet. Yours would be the first on the site — your vote becomes the initial average.
RepositoryRepository
| Skill ID | 100 |
|---|---|
| Data source | GitHub |
| Repository | NevaMind-AI/memU |
| Category | AI Agent Architecture & RAG / Agent Orchestration & Workflow |
| Primary language | Python |
| License | Other |
| Default branch | main |
| GitHub repository ID | 1028070615 |
| Node ID | R_kgDOPUcc1w |
| Rank | #82 (position within the source ranking) |
| Site-wide popularity rank | #112 (computed live from Stars, across all 5833 entries) |
GrowthStar / Fork growth
One snapshot per day, tracking how Stars and Forks changed
- Now14,427
- Previous point · 10-14 14,427
- vs previous point ±0
- 3 data points 23 days
- Now1,070
- Previous point · 10-14 1,070
- vs previous point ±0
- 3 data points 23 days
TimelineTimeline
Repository created2025-07-29 01:54:402025-07-29
Data last updated2026-10-16 16:00:551 months ago
Last commit2026-09-21 11:46:161 months ago
CommitLatest commit
committed by Jun516. Category: Bug Fixes & Stability Improvements. Commit message: 🐛 fix: retain Windows absolute resource paths (#727).