MemPalace

    MemPalace/mempalace

    The best-benchmarked open-source AI memory system. And it's free.

    60.6K stars
    7.7K forks
    309 GitHub watchers
    Updated Nov 15, 2026
    View on GitHub

    Build with Backblaze B2

    SDKs, agent skills, IDE extensions, and reference pipelines from Backblaze Labs. All open source.

    Explore Backblaze Labs

    Loading star history...

    Where it stands

    Rank, growth pace and release cadence relative to everything GStars tracks.

    5 releases in the last 90 days, the latest 3 days ago, with 162 contributors on GitHub.

    Use Cases & Benefits

    • Implements a local-first AI memory system that stores and retrieves conversation history verbatim using semantic search with a structured index.
    • Offers high retrieval recall without requiring any API calls or cloud services, ensuring privacy and offline capability.
    • Use for managing and searching large personal or project conversation histories with scoped semantic queries.
    • Use for integrating a pluggable vector-store backend in AI agents or tools requiring efficient memory recall.
    • Use for building knowledge graphs with temporal entity relationships and validity windows backed by local SQLite.

    Should you depend on it?

    License terms, project hygiene and risks, from GitHub metadata and GStars' snapshots.

    License

    MIT

    Permissive: commercial use, modification and redistribution are allowed with attribution.

    Community files

    • README: present
    • Contributing guide: present

    Watch-outs

    No watch-outs from GStars' checks.

    General guidance from repository metadata, not legal advice. How we score

    From the README

    Local-first AI memory. Verbatim storage, pluggable backend, 96.6% R@5 raw on LongMemEval — zero API calls.

    MemPalace stores your conversation history as verbatim text and retrieves it with semantic search. It does not summarize, extract, or paraphrase. The index is structured — people and projects become wings, topics become rooms, and original content lives in drawers — so searches can be scoped rather than run against a flat corpus.

    The retrieval layer is pluggable. The current default is ChromaDB; the interface is defined in mempalace/backends/base.py and alternative backends can be dropped in without touching the rest of the system.

    Nothing leaves your machine unless you opt in.

    Architecture, concepts, and mining flows: mempalaceofficial.com/concepts/the-palace.

    MemPalace ships a CLI, so install it in an isolated environment to avoid PEP 668 errors on Debian/Ubuntu/Homebrew Pythons and to keep mempalace's deps (chromadb, numpy, grpcio, …) from conflicting with anything else in your global site-packages.

    We recommend uv — uv tool install puts the mempalace CLI in an isolated environment on your PATH:

    pipx works the same way if you prefer it: pipx install mempalace.

    Excerpt from the MemPalace/mempalace README on GitHub (MIT license). © its authors.Read the full README on GitHub

    Daily snapshots

    Stars gained per day, and how forks and open issues moved, from GStars' daily snapshots

    0204060Nov 1: +35Nov 4: +75Nov 5: +28Nov 6: +48Nov 1Nov 4Nov 5Nov 6

    +1,826 stars over 77 days across 12 snapshot days; best day +75 on Nov 4.

    Forks

    7.7K+132

    Open issues

    822+95

    Compared with peers in AI

    Fastest-growing repositories GStars tracks in this cohort for the week of Nov 15, by 7-day star growth

    MemPalace/mempalace compared with AI repositories by stars, 7-day star growth, health score and last release
    RepositoryStars+7dHealthLast release
    firecrawl/firecrawl206.2K+5.4K52155 days ago
    Leonxlnx/taste-skill119.7K+4.1K5014 days ago
    heygen-com/hyperframes87.9K+3.5K45today
    jingyaogong/minimind68.1K+2.6K32396 days ago
    microsoft/markitdown197.5K+2.2K5831 days ago
    MemPalace/mempalace60.6K—603 days ago
    Category median119.7K+3.5K50—

    Discover Repositories

    Search across tracked repositories by name or description