memU
Bridges the gap between local development environments and AI agent context, reducing context loss and improving agent reasoning accuracy across multi-sessio…
Memory framework that compiles conversations, documents, code, images, audio, video, URLs, and tool traces into a human-readable Markdown tree (INDEX.md, MEMORY.md, SKILL.md) that agents traverse to load only the context they need. Ships a bundled Claude Code agent skill for memorize/retrieve workspace commands, plus a CLI and Python library; storage backends include in-memory, SQLite, and Postgres.
- Ask Claude to retrieve code context from your workspace memory during development sessions.
- Generate documentation by extracting relevant code snippets from memU's stored workspace knowledge.
- Automate context switching by loading saved project memories instead of re-explaining codebase details.
Bridges the gap between local development environments and AI agent context, reducing context loss and improving agent reasoning accuracy across multi-session workflows.
Engineering teams integrating AI agents into development pipelines requiring persistent, workspace-aware memory.
https://github.com/NevaMind-AI/memU
By NevaMind-AI
How to Get It
git clone https://github.com/NevaMind-AI/memU && cp -r memU/.claude/skills/memu ~/.claude/skills/ # skill drives the memU CLI — install with: pip install memu-py (or use npx memu-cli)
Tip: Paste this into a Claude Code conversation. Verify command matches your Claude Code version.
After installing, paste this into Claude:
Retrieve code context from my workspace memory during development sessions
Trust Signals Auto-scanned
Community Pulse Active
Discussed on Hacker News
- Show HN: A file-based agent memory framework that works like skill — Hacker News · 11 pts
- Show HN: MemU: Let AI Memorize You — Hacker News · 11 pts
- Show HN: Unified multimodal memory framework, without embeddings — Hacker News · 7 pts
3 mentions across 1 sources
Reviewer notes
Auto-scanned review. These are observations, not a security certification.
Scored from trust signals (evidence-eval-v1): 13,900 GitHub stars; contributors unknown; last commit 1d ago; license no license.
Things to check
- Scanned, not hands-on tested — this entry was auto-scanned from public metadata (GitHub metrics, license, security flags). No reviewer has run it, and no tool-specific limitations have been documented yet.
How to evaluate tools before deploying →
Data shown here comes from public APIs and automated scanning. Reviewer notes reflect one person's experience. This is not a security certification or legal recommendation. Always evaluate tools according to your own organization's policies.
Evaluation
Scored from trust signals (evidence-eval-v1): 13,900 GitHub stars; contributors unknown; last commit 1d ago; license no license.