llm-memory 开源项目推荐（692 个）

alibaba /zvec

一个轻量、极速的进程内向量数据库

Mirix-AI /MIRIX

Mirix is a multi-agent personal assistant designed to track on-screen activities and answer user questions intelligently. By capturing real-time visual data and consolidating it into structured memories, Mirix transforms raw inputs into a rich knowledge base that adapts to your digital experiences.

memodb-io /memobase

面向 AI 聊天机器人应用的基于用户画像的长期记忆。

vshulcz /deja-vu

跨 43 个智能体的 Claude Code 记忆、Codex 记忆、Cursor 记忆、OpenCode 记忆、Gemini CLI 记忆、Windsurf 记忆与 Cline 记忆。AI 编程记忆、Claude Code 历史、Cursor 历史、本地编程智能体记忆、MCP 记忆服务器与 Claude 上下文压缩。

AutoArk /TinyEngram

基于Qwen-3和Stable Diffusion系列的DeepSeek Engram架构研究。

IAAR-Shanghai /Awesome-AI-Memory

令人敬畏的AI记忆|LLM记忆|针对LLM和代理的人工智能记忆精心策划的知识库，涵盖长期记忆、推理、检索和内存原生系统设计。 Awesome-AI-Memory 是一个 集中式、持续更新的 AI 记忆知识库，系统性整合了与 大模型记忆（LLM Memory）和智能体记忆（Agent Memory）相关的前沿研究、工程框架、系统设计、评测基础与真实应用实践。

NirDiamant /Agent_Memory_Techniques

Agent memory for LLMs: 30 runnable Jupyter notebooks covering conversation buffers, vector stores, knowledge graphs, episodic and semantic memory, MemGPT, Mem0, Letta, Zep, Graphiti, LoCoMo benchmarks, and production patterns.

CodeAbra /iai-personal-memory-engine

Independent Autistic Intelligence——为你的 AI 打造的赛博大脑。它从不会忘记任何细节，能准确记住你说过的话，并随着时间了解你的工作方式。免费、本地运行，兼容 Cursor、Claude Code、Codex、OpenClaw、Hermes 等。MIT 许可。

omdsh-dev /dsh-mnemon

Composable, view-based context for DeepSeek Harness. Pluggable sources and strategies, with layered memory and self-evolving skills out of the box.

okf-memory /okf-agent-memory

Git-native persistent memory for AI coding agents. Implements Google OKF v0.2 with sub-300µs in-memory BM25 search, embedded MCP server, and progressive disclosure. Slashes token bloat by 80% with zero external databases or dependencies. Built in pure Go.

kitfunso /hippo-memory

Stop re-teaching your agent. Make your agent's memory work like a brain. Hippo is long-term memory for coding agents. It's a critical layer for your AI harness that connects across your different tools (Cursor, Claude Code, Codex). It keeps your proprietary data completely local, and it actually learns over time.

TeleAI-UAGI /Awesome-Agent-Memory

Curated systems, benchmarks, and papers etc. on memory for LLMs/MLLMs --- long-term context, retrieval, and reasoning.

mnemon-dev /mnemon

LLM-supervised persistent memory for AI agents — graph-based recall, cross-session knowledge, single binary. Works with DeepSeek Harness, Claude Code, OpenClaw, and any agent runtime.

memvid /claude-brain

Give Claude Code photographic memory in ONE portable file. No database, no SQLite, no ChromaDB - just a single .mv2 file you can git commit, scp, or share. Native Rust core with sub-ms operations.

caura-ai /caura

Caura（原 MemClaw）——面向 AI 智能体集群的受治理共享内存。多智能体、多租户、MCP 原生。信任层级、核心策略、审计追踪、知识图谱、自我改进的检索。Apache 2.0。

grpcer /ownmem

Open-source, Git-native memory for AI coding agents — deterministic local recall for Claude Code, Codex, Cursor, Gemini CLI, and compatible tools.

divagr18 /memlayer

只需 3 行代码即可为 LLM 提供即插即用的记忆。几分钟内为任何模型添加持久、智能、类人的记忆与回忆能力。

qualixar /superlocalmemory

世界上第一个在LoCoMo上实现74%检索和60%零LLM的本地AI内存。没有云，没有API，也没有数据流出你的机器。此外，C模式（LLM/云端）的LoCoMo比例为87.7%。有研究支持。arXiv： 2603.14588

sachitrafa /YourMemory

智能人工智能记忆与埃宾豪斯忘记曲线衰减。比《LoCoMo》的记忆力+16页。

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.