{"data":{"slug":"nevamind-ai-memu","name":"memU","tagline":"Personal memory for agents with fast retrieval and self-evolving skills","github_url":"https://github.com/NevaMind-AI/memU","owner":"NevaMind-AI","repo":"memU","owner_avatar_url":"https://avatars.githubusercontent.com/u/217726889?v=4","primary_language":"Python","stars":14420,"forks":1071,"topics":["agent-memory","claude-skills","harness","loop-engineering","mcp","memory","openclaw","openclaw-skills","sandbox","skills"],"archived":false,"github_pushed_at":"2026-09-14T08:30:50+00:00","maintenance_label":"Very active","stars_delta_30d":358,"url":"https://www.graphcanon.com/tools/nevamind-ai-memu","markdown_url":"https://www.graphcanon.com/tools/nevamind-ai-memu.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/nevamind-ai-memu","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=nevamind-ai-memu","description":"Personal memory across agents","homepage_url":"https://memu.pro","license":"Other","open_issues":120,"watchers":68,"ai_summary":"memU provides fast memory retrieval capabilities for AI agents alongside features like self-evolving skills to reduce operational costs.","readme_excerpt":"## Quick start\n\nmemU works with Codex, Claude Code, Cursor, OpenClaw, Hermes, WorkBuddy, Cola, pi, and more. See [Host adapters](#host-adapters-memory-for-desktop-coding-agents).\n\n**Cross-device · Free · Unlimited · [View online](https://memu.so)**\n\nGet your API key from [memu.so](https://memu.so), then send this message to your agent:\n\n> Read [https://memu.pro/SKILL.md](https://memu.pro/SKILL.md), follow its instructions to install and configure memU, API Key is memu_•••••••••(get Api Key from memu.so).\n\n---\n\n## License\n\nApache-2.0\n\n\n<sub>Partnership Community: <a href=\"https://linux.do\">LINUX DO</a></sub>","github_created_at":"2025-07-29T01:54:40+00:00","created_at":"2026-07-11T11:49:02.546894+00:00","updated_at":"2026-09-20T06:38:49.509169+00:00","categories":[{"slug":"ai-agents","name":"AI Agents","url":"https://www.graphcanon.com/categories/ai-agents","markdown_url":"https://www.graphcanon.com/categories/ai-agents.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/ai-agents"}],"tags":[{"slug":"agent-memory","name":"agent-memory"},{"slug":"claude-skills","name":"claude-skills"},{"slug":"harness","name":"harness"},{"slug":"loop-engineering","name":"loop-engineering"},{"slug":"mcp","name":"mcp"},{"slug":"memory","name":"memory"},{"slug":"openclaw","name":"openclaw"},{"slug":"openclaw-skills","name":"openclaw-skills"}],"trust":{"provenance":{"is_fork":false,"github_id":1028070615,"owner_type":"Organization","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-09-20T03:49:46.624Z","maintenance":{"label":"Very active","score":96,"methodology":"github_public_v1","releases_90d":1,"days_since_push":5,"last_release_at":"2026-07-23T04:16:09Z","stars_delta_30d":358,"open_issues_delta_30d":26},"security_summary":{"status":"no_manifest","scanner":null,"low_count":0,"high_count":0,"last_scan_at":"2026-07-11T11:49:03.625Z","medium_count":0,"scan_profile":"mcp_manifest","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-09-20T03:49:47.648Z"},"has_cli":{"value":true,"source":"pyproject.toml:[project.scripts]","observed_at":"2026-09-20T03:49:47.648Z"},"languages":{"value":["python"],"source":"github.language+pyproject.toml","observed_at":"2026-09-20T03:49:47.648Z"},"license_spdx":{"value":"Other","source":"github.license","observed_at":"2026-09-20T03:49:47.648Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":null,"constraints":null,"when_to_use":["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."],"when_not_to_use":["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."],"source":"enrich:decision_facts","observed_at":"2026-07-16T21:20:32.514Z"},"constraint_facets":null,"decision_summary":[{"label":"Adopt for","value":"memU offers fast memory retrieval and self-evolving skills for AI agents at lower operational costs."}]}}