Home/AI Agents/memU

memU

NevaMind-AI/memU

Personal memory for agents with fast retrieval and self-evolving skills

GraphCanon updated 4w · GitHub synced 4w

14k stars1.0k forksLast push 4w Python Other

Decision brief

memU offers fast memory retrieval and self-evolving skills for AI agents at lower operational costs.

Good fit when

Use memU when your project requires fast access to stored agent actions and memories which can adapt over time without needing human intervention.
Integrate memU if cost reduction on maintenance and operation of AI agents is a priority without sacrificing performance or adaptability.

Avoid when

Avoid using memU if your application mandates proprietary memory systems that are tightly integrated with specific agent architectures not supported by memU.
memU is unsuitable for projects where the customizability and control over skill evolution are limited or require extensive manual adjustments, as this tool emphasizes self-evolving features.

Observed Jul 16, 2026 · Source: enrich:decision_facts

memU alternatives Trust report

Verify the decision

Maintenance and security

Full trust report

Maintenance: Very active (0d since push); As of 4w
Provenance: Not a fork · Organization account; As of 4w
Security (OSV): No MCP manifest; As of 1mo

Public GitHub metadata and optional OSV scans. Signals, not a guarantee. Trust methodology.

Install

pip install memU

Similar tools

Same-category neighbours. No typed graph edges are catalogued for this tool yet.

Persistent Context Across Sessions for Every Agent

The best-benchmarked open-source AI memory system.

TencentDB-Agent-Memory

Fully local long-term memory for AI Agents via 4-tier pipeline

Evidence and technical details

Sourced facts, taxonomy, compatibility claims, README excerpt, and machine-readable endpoints.

Overview

memU provides fast memory retrieval capabilities for AI agents alongside features like self-evolving skills to reduce operational costs.

Capability facts

CLI: CLI entrypoint
Source: pyproject.toml:[project.scripts] · Jul 26, 2026
Languages: python
Source: github.language+pyproject.toml · Jul 26, 2026

Categories

Compatibility

Sourced claims from the README excerpt - not unsourced marketing copy.

Works with CursorCursor

Source: README excerpt (regex_v1, Jul 26, 2026)

memU works with Codex, Claude Code, Cursor, OpenClaw, Hermes, WorkBuddy, and more. See [Host adapters](#host-adapters-memo

Tags

agent-memory claude-skills harness loop-engineering mcp memory openclaw openclaw-skills

README

Quick start

memU works with Codex, Claude Code, Cursor, OpenClaw, Hermes, WorkBuddy, and more. See Host adapters.

Choose Cloud or Local, then send the corresponding message to your agent.

For agents

This page has a .md twin and JSON over the API.

/tools/nevamind-ai-memu.md GET /api/graphcanon/tools/nevamind-ai-memu GET /api/graphcanon/graph?tool=nevamind-ai-memu

Was this helpful?

Anonymous feedback helps us improve pages and translations.