GStars
    NevaMind-AI

    NevaMind-AI/memU

    Personal memory across agents

    backend
    agent-memory
    claude-skills
    harness
    loop-engineering
    mcp
    Python
    NOASSERTION
    14.6K stars
    1.1K forks
    63 GitHub watchers
    Updated Nov 6, 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.

    No releases in the last 90 days; the most recent was 106 days ago, with 49 contributors on GitHub.

    The biggest single-day gain in the last year, +555 stars on Jan 29, coincided with release v1.3.0.

    Use Cases & Benefits

    • Implements an agentic memory system that processes multimodal inputs into a hierarchical, structured memory for AI agents.
    • Enables dual retrieval methods combining fast embedding-based search with deep semantic LLM reasoning for flexible and efficient memory access.
    • Use for building personal AI assistants that remember and organize user preferences, habits, and conversations over time.
    • Use for extracting and evolving skills and lessons from agent execution logs to support DevOps and agent self-improvement workflows.
    • Use for unifying diverse content types like documents and images into a cross-modal memory system for research and documentation platforms.

    Should you depend on it?

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

    License

    Other

    GitHub could not identify this license; read the LICENSE file before depending on it.

    Community files

    • README: present
    • Contributing guide: present

    Watch-outs

    • License not identified by GitHub; read the LICENSE file before depending on it.

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

    From the README

    MemU is an agentic memory framework for LLM and AI agent backends. It receives multimodal inputs (conversations, documents, images), extracts them into structured memory, and organizes them into a hierarchical file system that supports both embedding-based (RAG) and non-embedding (LLM) retrieval.

    MemU is collaborating with four open-source projects to launch the 2026 New Year Challenge. 🎉Between January 8–18, contributors can submit PRs to memU and earn cash rewards, community recognition, and platform credits. 🎁Learn more & get involved

    Excerpt from the NevaMind-AI/memU README on GitHub (NOASSERTION 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

    1.1K+42

    Open issues

    142+31

    Compared with peers in Backend

    Fastest-growing repositories GStars tracks in this cohort for the week of Nov 8, by 7-day star growth

    View category →
    NevaMind-AI/memU compared with Backend repositories by stars, 7-day star growth, health score and last release
    RepositoryStars+7dHealthLast release
    anthropics/skills192.3K+5.2K75—
    zed-industries/zed94.7K+2.3K756 days ago
    google/skills23.8K+2.0K75—
    NationalSecurityAgency/ghidra99.4K+1.8K7519 days ago
    DuarteSantos8/openGym20.8K+1.7K757 days ago
    NevaMind-AI/memU14.6K—54106 days ago
    Category median94.7K+2.0K75—
    Compare memU with skills, zed, skills →

    Discover Repositories

    Search across tracked repositories by name or description