verygoodplugins

    verygoodplugins/automem

    Long-term memory for AI assistants. Graph + vector store that recalls decisions, relationships, and context across sessions.

    ai
    llm
    ai-memory
    anthropic
    automem
    falkordb
    graph-database
    Python
    MIT
    827 stars
    111 forks
    827 GitHub watchers
    Updated Nov 3, 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.

    1 release in the last 90 days, the latest 68 days ago, with 15 contributors on GitHub.

    Use Cases & Benefits

    • Provides a long-term memory system for AI assistants using a hybrid graph and vector store to recall decisions, relationships, and context across sessions.
    • Delivers state-of-the-art accuracy on long-term conversational memory benchmarks by combining semantic, lexical, temporal, and graph-based reasoning for meaningful memory recall.
    • Use for enhancing AI assistants with persistent, evolving memory that understands complex multi-hop relationships and temporal context.
    • Use for building knowledge graphs that automatically extract entities, detect patterns, and consolidate memories inspired by neuroscience principles.
    • Use for integrating with AI platforms via REST API or MCP protocol to enable production-grade memory recall with sub-100ms latency and automated background enrichment.

    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

    Watch-outs

    No watch-outs from GStars' checks.

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

    From the README

    AutoMem is the world's best-performing long-term memory system for AI assistants. On December 2, 2025, AutoMem achieved 90.53% accuracy on the LoCoMo benchmark (ACL 2024), beating the previous state-of-the-art by 2.29 points.

    Deploy production-grade AI memory in 60 seconds:

    Your AI forgets everything between sessions. RAG dumps similar documents. Vector databases match keywords but miss meaning. None of them learn.

    AutoMem gives AI assistants the ability to remember, connect, and evolve their understanding over time—just like human long-term memory.

    Excerpt from the verygoodplugins/automem 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

    Forks

    111+11

    Open issues

    18+6

    Compared with peers in AI

    Fastest-growing repositories GStars tracks in this cohort for the week of Nov 1, by 7-day star growth

    verygoodplugins/automem compared with AI repositories by stars, 7-day star growth, health score and last release
    RepositoryStars+7dHealthLast release
    thedotmack/claude-mem113.6K+8.8K35today
    D4Vinci/Scrapling98.1K+6.9K651 day ago
    Leonxlnx/taste-skill110.7K+5.2K551 day ago
    calesthio/OpenMontage77.2K+4.2K40—
    heygen-com/hyperframes79.6K+4.1K45today
    verygoodplugins/automem827—3268 days ago
    Category median98.1K+5.2K45—

    Discover Repositories

    Search across tracked repositories by name or description