longmemeval repositories

Trending repositories tagged longmemeval, ranked by trending score. Updated daily.

  1. 1
    EternalNight996/memory-eternal

    🧠 给 AI 一个可信的第二大脑:本地 SQLite · 先审核再入库 · 不可篡改审计 · 记忆账本。🕷 蜘蛛侠皮肤 · 🔍 自建集 R@5 99.1% / LongMemEval-S 97.2% · 🧩 一个库接入 DSH / Claude Code / Codex / Cursor / 任意 MCP · ⭐ MIT 开源 · 🚀 零依赖开箱即用

    GitHub · JavaScript · 211 stars · 17 forks · +12 stars in 24 hours · Trending score 2.26

  2. 2
    jaylfc/taosmd

    Local-first AI memory — runs offline on any machine with 8 GB+ RAM (SBC, mini PC, laptop, workstation). Zero-loss verbatim archive, knowledge graph, hybrid retrieval. Framework-agnostic, no cloud.

    GitHub · Python · 85 stars · 5 forks · +1 stars in 24 hours · Trending score 0.55

  3. 3
    codecoradev/uteke

    Long-term memory for AI agents (MCP). One Rust binary, offline, 98.2% recall@5 on LongMemEval-S. Works with Claude Code, Cursor, Codex. Self-host free or use Uteke Cloud.

    GitHub · Rust · 289 stars · 31 forks · 0 stars in 24 hours · Trending score 0.35

  4. 4
    memoket/memoket-kite

    An open-source, vector-free long-term memory engine for AI agents, achieving SOTA on LoCoMo and LongMemEval with significantly less context.

    GitHub · Python · 234 stars · 24 forks · 0 stars in 24 hours · Trending score 0.30

  5. 5
    zensation-ai/zenbrain

    Agent memory for LLM agents: 7 neuroscience-inspired layers (working, episodic, semantic, procedural) with FSRS-style spaced repetition and memory consolidation. TypeScript, no third-party dependencies in the core packages; Model Context Protocol (MCP) server, Vercel AI SDK middleware. Paper: arXiv 2604.23878 · reproduction packages on Zenodo.

    GitHub · TypeScript · 29 stars · 6 forks · 0 stars in 24 hours · Trending score 0.21

  6. 6
    ContextFit/cf

    Token-native agent memory retrieval for LLMs, without embedding APIs or vector databases.

    GitHub · Python · 13 stars · 2 forks · 0 stars in 24 hours · Trending score 0.14

  7. 7
    hermes-labs-ai/fidelis

    Zero-LLM agent memory for Claude Code and AI agents: local-first BM25, dense-vector, and reciprocal-rank-fusion retrieval. Returns original passages verbatim by default. Available on PyPI as fidelis-memory. Apache-2.0.

    GitHub · Python · 25 stars · 3 forks · 0 stars in 24 hours · Trending score 0.00

  8. 8
    ZenSystemAI/Zengram

    A Multi Agent Memory MCP That Connect Agents Across Systems and Machines

    GitHub · JavaScript · 61 stars · 11 forks · 0 stars in 24 hours · Trending score 0.00

  9. 9
    NORTHTEKDevs/genome

    Auditable memory layer for AI agents: zero-LLM-call local ingest (~10ms/msg, air-gapped), matches Mem0 on accuracy at ~1000x lower ingest cost, bi-temporal belief-state, MCP server. Honest LoCoMo/LongMemEval benchmarks. Open source (Apache-2.0).

    GitHub · Python · 10 stars · 4 forks · 0 stars in 24 hours · Trending score 0.00

  10. 10
    Kerneta/daidocs

    Open plain-text file format for AI memory. Your assistant's long-term memory as .dai files on your disk: readable by Claude, GPT, Gemini, Cursor, local models and grep (all LLM models work). MCP server + hooks for Claude Code, Claude Desktop, Cursor, Windsurf, Codex. 83% LongMemEval-S (GPT-4o), 92% (Claude Fable 5), 10x fewer tokens.

    GitHub · Python · 53 stars · 4 forks · 0 stars in 24 hours · Trending score 0.00

  11. 11
    doronp/gitmemory

    Git-versioned, contiguity-checked memory for AI agents: verbatim transcripts, byte-offset recall, no LLM

    GitHub · Python · 20 stars · 0 forks · 0 stars in 24 hours · Trending score 0.00

  12. 12
    goyohan0611-png/turnbook

    Local long-term memory for AI coding agents. Keeps every conversation word for word, costs nothing to save, and is shared by all your agents. 91.8% on LongMemEval.

    GitHub · Python · 14 stars · 4 forks · 0 stars in 24 hours · Trending score 0.00