{"data":{"slug":"mempalace-mempalace","name":"mempalace","tagline":"The best-benchmarked open-source AI memory system.","github_url":"https://github.com/MemPalace/mempalace","owner":"MemPalace","repo":"mempalace","owner_avatar_url":"https://avatars.githubusercontent.com/u/275135684?v=4","primary_language":"Python","stars":58400,"forks":7498,"topics":["ai","chromadb","llm","mcp","memory","python"],"archived":false,"github_pushed_at":"2026-08-15T01:20:08+00:00","maintenance_label":"Very active","stars_delta_30d":1001,"url":"https://www.graphcanon.com/tools/mempalace-mempalace","markdown_url":"https://www.graphcanon.com/tools/mempalace-mempalace.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/mempalace-mempalace","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=mempalace-mempalace","description":"The best-benchmarked open-source AI memory system. And it's free.","homepage_url":"http://mempalaceofficial.com/","license":"MIT","open_issues":704,"watchers":322,"ai_summary":"MemPalace is an advanced open-source AI memory system that provides solutions for managing and optimizing machine learning model memories. It integrates with ChromaDB as a vector database component to enhance data retrieval efficiency.","readme_excerpt":"## Install\n\nMemPalace ships a CLI, so install it in an isolated environment to avoid\nPEP 668 errors on Debian/Ubuntu/Homebrew Pythons and to keep mempalace's\ndeps (`chromadb`, `numpy`, `grpcio`, …) from conflicting with anything\nelse in your global site-packages.\n\nWe recommend [`uv`](https://docs.astral.sh/uv/) — `uv tool install` puts\nthe `mempalace` CLI in an isolated environment on your PATH:\n\n```bash\nuv tool install mempalace\nmempalace init ~/projects/myapp\n```\n\n[`pipx`](https://pipx.pypa.io/) works the same way if you prefer it:\n`pipx install mempalace`.\n\nPrefer plain `pip` only inside an activated virtualenv where you\nexplicitly want `import mempalace` available:\n\n```bash\npython -m venv .venv && source .venv/bin/activate\npip install mempalace\n```\n\n---\n\n### Docker\n\nA container image is also available for running the MCP server or the CLI\nwithout a local Python toolchain. Multi-arch (amd64 + arm64), so it runs\nnatively on Apple Silicon:\n\n```bash\ndocker pull ghcr.io/mempalace/mempalace:latest\n```\n\nEverything persists under `/data` — palace, config, and the cached embedding\nmodel — so mount a volume there and reuse it across runs:\n\n```bash\n\n---\n\n## Requirements\n\n- Python 3.9+\n- A vector-store backend (ChromaDB by default)\n- ~300 MB disk for the embedding model. Onboarding (`python -m mempalace.onboarding`) offers `embeddinggemma-300m` (multilingual, 100+ languages, recommended) or `all-MiniLM-L6-v2` (English-only, ~30 MB). See the docstring at [`mempalace/embedding.py`](mempalace/embedding.py) for details and migration notes.\n- Optional — compute embeddings on a server instead of locally. Set `embedding_model: \"openai-compat\"` in `~/.mempalace/config.json` together with `embedding_api_url` / `embedding_api_model` (and `embedding_api_key` if the server needs auth) to use any OpenAI-compatible `/v1/embeddings` endpoint — LM Studio, llama.cpp, vLLM, Ollama's OpenAI shim, or a self-hosted server (e.g. a larger multilingual or GPU-served embedder). Each key is overridable via the matching `MEMPALACE_EMBEDDING_API_*` env var. When the endpoint is on your machine or LAN, no content leaves your network. Switching to it requires `mempalace repair rebuild-index` (different vector space).\n\nNo API key is required for the core benchmark path.\n\n---\n\n## License\n\nMIT — see [LICENSE](LICENSE).\n\n\n[version-shield]: https://img.shields.io/badge/version-3.7.1-4dc9f6?style=flat-square&labelColor=0a0e14\n[release-link]: https://github.com/MemPalace/mempalace/releases\n[python-shield]: https://img.shields.io/badge/python-3.9+-7dd8f8?style=flat-square&labelColor=0a0e14&logo=python&logoColor=7dd8f8\n[python-link]: https://www.python.org/\n[license-shield]: https://img.shields.io/badge/license-MIT-b0e8ff?style=flat-square&labelColor=0a0e14\n[license-link]: https://github.com/MemPalace/mempalace/blob/main/LICENSE\n[discord-shield]: https://img.shields.io/badge/discord-join-5865F2?style=flat-square&labelColor=0a0e14&logo=discord&logoColor=5865F2\n[discord-link]: https://discord.com/invite/ycTQQCu6kn","github_created_at":"2026-04-05T01:12:07+00:00","created_at":"2026-07-07T17:31:06.422829+00:00","updated_at":"2026-08-16T06:02:08.191612+00:00","categories":[{"slug":"model-training","name":"Model Training","url":"https://www.graphcanon.com/categories/model-training","markdown_url":"https://www.graphcanon.com/categories/model-training.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/model-training"},{"slug":"vector-databases","name":"Vector Databases","url":"https://www.graphcanon.com/categories/vector-databases","markdown_url":"https://www.graphcanon.com/categories/vector-databases.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/vector-databases"}],"tags":[{"slug":"ai","name":"ai"},{"slug":"chromadb","name":"chromadb"},{"slug":"llm","name":"llm"},{"slug":"memory","name":"memory"}],"trust":{"provenance":{"is_fork":false,"github_id":1201656210,"owner_type":"Organization","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-08-16T06:02:07.390Z","maintenance":{"label":"Very active","score":96,"methodology":"github_public_v1","releases_90d":7,"days_since_push":1,"last_release_at":"2026-08-14T17:51:05Z","stars_delta_30d":1001,"open_issues_delta_30d":77},"security_summary":{"status":"no_manifest","scanner":null,"low_count":0,"high_count":0,"last_scan_at":"2026-07-11T10:56:50.219Z","medium_count":0,"scan_profile":"mcp_manifest","critical_count":0}},"capability_facts":{"mcp":{"source":"repo_scan","observed_at":"2026-08-16T06:02:07.858Z","server_manifest":false},"scan":{"source":"repo_scan","observed_at":"2026-08-16T06:02:07.858Z"},"deploy":{"source":"dockerfile:Dockerfile","self_host":true,"observed_at":"2026-08-16T06:02:07.858Z","managed_saas":false},"has_cli":{"value":true,"source":"pyproject.toml:[project.scripts]","observed_at":"2026-08-16T06:02:07.858Z"},"languages":{"value":["python"],"source":"github.language+pyproject.toml","observed_at":"2026-08-16T06:02:07.858Z"},"has_docker":{"value":true,"source":"dockerfile:Dockerfile","observed_at":"2026-08-16T06:02:07.858Z"},"license_spdx":{"value":"MIT","source":"github.license","observed_at":"2026-08-16T06:02:07.858Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":null,"constraints":null,"when_to_use":["When you need a highly benchmarked solution for managing AI model memories, MemPalace can provide superior performance due to its optimization features integrated specifically around ML model needs.","If your application requires seamless integration with ChromaDB as the vector database component, MemPalace offers enhanced data retrieval efficiency tailored to these integrations."],"when_not_to_use":["Avoid if requiring a proprietary system where full transparency or customization of the memory management layer may not be necessary, since MemPalace is open source and might involve deeper technical啃","\"如果你的应用场景对内存管理层的完全透明或定制化需求不高，因为MemPalace是开源的，可能需要更深的技术介入来满足特定需求。\"","If your project strictly adheres to non-MIT licenses, then MemPalace might not be suitable due to its MIT license which may conflict with licensing requirements."],"source":"enrich:decision_facts","observed_at":"2026-07-11T12:22:21.293Z"},"constraint_facets":null,"decision_summary":[{"label":"Adopt for","value":"MemPalace is an advanced open-source AI memory system that integrates with ChromaDB to optimize machine learning model memories and enhance data retrieval efficiency."}]}}