超级本地记忆工具 是 AI Skill Hub 本期精选MCP工具之一。综合评分 7.5 分,整体质量较高。我们推荐使用将其纳入你的 AI 工具库,帮助提升工作效率。
超级本地记忆工具 是一款遵循 MCP(Model Context Protocol)标准协议的 AI 工具扩展。通过 MCP 协议,它可以让 Claude、Cursor 等主流 AI 客户端直接访问和操作外部工具、数据源和服务,实现 AI 能力的无缝扩展。无论是文件操作、数据库查询还是 API 调用,都可以通过自然语言在 AI 对话中直接触发,极大提升生产效率。
超级本地记忆工具 是一款遵循 MCP(Model Context Protocol)标准协议的 AI 工具扩展。通过 MCP 协议,它可以让 Claude、Cursor 等主流 AI 客户端直接访问和操作外部工具、数据源和服务,实现 AI 能力的无缝扩展。无论是文件操作、数据库查询还是 API 调用,都可以通过自然语言在 AI 对话中直接触发,极大提升生产效率。
# 方式一:通过 Claude Code CLI 一键安装
claude skill install https://github.com/qualixar/superlocalmemory
# 方式二:手动配置 claude_desktop_config.json
{
"mcpServers": {
"--------": {
"command": "npx",
"args": ["-y", "superlocalmemory"]
}
}
}
# 配置文件位置
# macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
# Windows: %APPDATA%/Claude/claude_desktop_config.json
# 安装后在 Claude 对话中直接使用 # 示例: 用户: 请帮我用 超级本地记忆工具 执行以下任务... Claude: [自动调用 超级本地记忆工具 MCP 工具处理请求] # 查看可用工具列表 # 在 Claude 中输入:"列出所有可用的 MCP 工具"
// claude_desktop_config.json 配置示例
{
"mcpServers": {
"________": {
"command": "npx",
"args": ["-y", "superlocalmemory"],
"env": {
// "API_KEY": "your-api-key-here"
}
}
}
}
// 保存后重启 Claude Desktop 生效
<p align="center"> <img src="https://superlocalmemory.com/assets/logo-mark.png" alt="SuperLocalMemory" width="200"/> </p>
Every other AI forgets. Yours won't.
Infinite memory for Claude Code, Cursor, Windsurf, and any MCP-compatible AI client.
v3.4.5 "Scale-Ready" — Five years of daily AI use. Your system won't feel it.
1 million memories. Zero slowdown. Tiered storage. Auto-migration. One command: pip install -U superlocalmemory && slm restart
Backed by 3 published research papers (arXiv preprints + Zenodo-archived) · arXiv:2603.02240 · arXiv:2603.14588 · arXiv:2604.04514
<p align="center"> <code>+10.6pp vs Mem0 zero-LLM</code> · <code>85% Open-Domain (best zero-LLM score)</code> · <code>EU AI Act Ready</code> </p>
<p align="center"> <a href="https://arxiv.org/abs/2603.14588"><img src="https://img.shields.io/badge/arXiv-2603.14588-b31b1b?style=for-the-badge&logo=arxiv&logoColor=white" alt="arXiv Paper"/></a> <a href="https://pypi.org/project/superlocalmemory/"><img src="https://img.shields.io/pypi/v/superlocalmemory?style=for-the-badge&logo=pypi&logoColor=white" alt="PyPI"/></a> <a href="https://www.npmjs.com/package/superlocalmemory"><img src="https://img.shields.io/npm/v/superlocalmemory?style=for-the-badge&logo=npm&logoColor=white" alt="npm"/></a> <a href="https://www.gnu.org/licenses/agpl-3.0"><img src="https://img.shields.io/badge/License-AGPL_v3-blue.svg?style=for-the-badge" alt="AGPL v3"/></a> <a href="#eu-ai-act-compliance"><img src="https://img.shields.io/badge/EU_AI_Act-Design_Compliant-brightgreen?style=for-the-badge" alt="EU AI Act Design Compliant"/></a> <a href="https://superlocalmemory.com"><img src="https://img.shields.io/badge/Web-superlocalmemory.com-ff6b35?style=for-the-badge" alt="Website"/></a> <a href="#dual-interface-mcp--cli"><img src="https://img.shields.io/badge/MCP-Native-blue?style=for-the-badge" alt="MCP Native"/></a> <a href="#dual-interface-mcp--cli"><img src="https://img.shields.io/badge/CLI-Agent--Native-green?style=for-the-badge" alt="CLI Agent-Native"/></a> <a href="#multilingual-embedding-support"><img src="https://img.shields.io/badge/Multilingual-30%2B_Languages-ff69b4?style=for-the-badge" alt="Multilingual 30+ Languages"/></a> </p>
<p align="center"> <video src="https://github.com/user-attachments/assets/c3b54a1d-f62a-4ea7-bba7-900435e7b3ab" width="800" autoplay loop muted playsinline></video> </p>
---
All new features default OFF. Zero breaking changes. Opt in when ready:
```bash
zeroconf>=0.140 (new in v3.4.48, optional, pure Python, auto-installed)httpx==0.28.1 (already in core deps)| Requirement | Version | Why |
|---|---|---|
| **Node.js** | 14+ | npm package manager |
| **Python** | 3.11+ | V3 engine runtime |
All Python dependencies install automatically during npm install — core math, dashboard server, learning engine, and performance optimizations. If anything fails, the installer shows exact fix commands. Run slm doctor after install to verify everything works. BM25 keyword search works even without embeddings — you're never fully blocked.
| Component | Size | When |
|---|---|---|
| Core libraries (numpy, scipy, networkx) | ~50MB | During install |
| Dashboard & MCP server (fastapi, uvicorn) | ~20MB | During install |
| Learning engine (lightgbm) | ~10MB | During install |
| Search engine (sentence-transformers, torch) | ~200MB | During install |
| Embedding model (nomic-embed-text-v1.5, 768d) | ~500MB | First use or slm warmup |
**Mode B** requires [Ollama](https://ollama.com) + a model (ollama pull llama3.2) | ~2GB | Manual |
---
npm install -g superlocalmemory
slm setup # Choose mode (A/B/C)
slm doctor # Verify everything is working
slm warmup # Pre-download embedding model (~500MB, optional)
pip install superlocalmemory
pip install -U superlocalmemory slm restart
M4 (broker):
export SLM_MESH_HOST=192.168.1.100
export SLM_MESH_SHARED_SECRET=my-secret-key
slm init # Starts SLM at http://192.168.1.100:8765
M5 (client):
export SLM_MESH_PEER_URL=http://192.168.1.100:8765
export SLM_MESH_SHARED_SECRET=my-secret-key
slm init # Syncs M4's agents every 30s, proxies messages to M4
| Variable | Default | Purpose |
|---|---|---|
SLM_MESH_HOST | 127.0.0.1 | Host this SLM listens on (set to IP for remote) |
SLM_MESH_PEER_URL | unset | Full URL of remote SLM (e.g., http://192.168.1.100:8765) |
SLM_MESH_SHARED_SECRET | unset | Auth secret (required when remote) |
SLM_MESH_DISCOVERY | on | mDNS discovery (on/off) |
SLM_MESH_WS_PORT | 7900 | WebSocket port for mesh (internal use) |
```bash
SLM works everywhere — from IDEs to CI pipelines to Docker containers. Both the MCP server and the agent-native CLI are first-class, so the same backend serves IDE-side integrations and scripted automations.
| Need | Use | Example |
|---|---|---|
| IDE integration | MCP | Auto-configured for 17+ IDEs via slm connect |
| Shell scripts | CLI + --json | slm recall "auth" --json \| jq '.data.results[0]' |
| CI/CD pipelines | CLI + --json | slm remember "deployed v2.1" --json in GitHub Actions |
| Agent frameworks | CLI + --json | OpenClaw, Codex, Goose, nanobot |
| Human use | CLI | slm recall "auth" (readable text output) |
Agent-native JSON output on every command:
```bash
| Command | What It Does |
|---|---|
slm remember "..." | Store a memory |
slm recall "..." | Search memories |
slm forget "..." | Delete matching memories |
slm trace "..." | Recall with per-channel score breakdown |
slm status | System status |
slm health | Math layer health (Fisher, Sheaf, Langevin) |
slm doctor | Pre-flight check (deps, worker, Ollama, database) |
slm mode a/b/c | Switch operating mode |
slm setup | Interactive first-time wizard |
slm warmup | Pre-download embedding model |
slm migrate | V2 to V3 migration |
slm dashboard | Launch 17-tab web dashboard |
slm mcp | Start MCP server (for IDE integration) |
slm connect | Configure IDE integrations |
slm hooks install | Wire auto-memory into Claude Code hooks |
slm profile list/create/switch | Profile management |
slm decay | Run memory lifecycle review |
slm quantize | Run smart compression cycle |
slm consolidate --cognitive | Extract patterns from memory clusters |
slm soft-prompts | View auto-learned patterns |
slm reap | Clean orphaned SLM processes |
---
| Removed | Impact |
|---|---|
| Cross-encoder reranking | **-30.7pp** |
| Fisher-Rao metric | **-10.8pp** |
| All math layers | **-7.6pp** |
| BM25 channel | **-6.5pp** |
| Sheaf consistency | -1.7pp |
| Entity graph | -1.0pp |
Full ablation details in the Wiki.
---
{
"mcpServers": {
"superlocalmemory": {
"command": "slm",
"args": ["mcp"]
}
}
}
33 MCP tools by default (+42 optional behind SLM_MCP_ALL_TOOLS=1) + 7 resources. Works with any MCP-compatible client — we ship templated configs for Claude Code, Cursor, Windsurf, VS Code Copilot, Continue, Cody, ChatGPT Desktop, Gemini CLI, JetBrains, Zed, and Antigravity (15 IDE configs in ide/configs/). V3.3: Adaptive lifecycle, smart compression, and pattern learning.
| Category | Score | vs. Mem0 (64.2%) |
|---|---|---|
| Single-Hop | 72.0% | +3.0pp |
| Multi-Hop | 70.3% | +8.6pp |
| Temporal | 80.0% | +21.7pp |
| **Open-Domain** | **85.0%** | **+35.0pp** |
| **Aggregate** | **74.8%** | **+10.6pp** |
Mode A achieves 85.0% on open-domain questions — the highest of any system in the evaluation, including cloud-powered ones.
SuperLocalMemory V3.4 是一款专为 AI 开发者设计的“无限记忆”解决方案。它旨在解决当前 AI 模型(如 Claude Code、Cursor、Windsurf 等)容易遗忘上下文的问题。通过支持 MCP 协议,SuperLocalMemory 可以作为任何兼容 MCP 的 AI 客户端的持久化记忆层,确保您的 AI 助手能够拥有跨会话的长期记忆,实现真正的个性化与连续性。
本项目具备先进的自适应记忆生���周期管理,记忆会随使用频率自然强化或随忽视而淡化,无需手动清理。系统内置智能压缩技术(Smart Compression),可根据记忆重要性动态调整 embedding 精度,低优先级记忆可实现高达 32 倍的压缩。此外,通过认知整合(Cognitive Consolidation)功能,系统能自动从相关记忆簇中提取模式,实现深层知识沉淀。
运行本项目需要 Node.js 14+(用于 npm 包管理)以及 Python 3.11+(作为 V3 引擎运行时)。所有的 Python 依赖项会在执行 `npm install` 时自动安装。本项目设计轻量化,无需 Docker 或外部 Broker,支持在 WiFi 和局域网(LAN)环境下直接运行,非常适合本地化部署。
推荐使用 npm 进行全局安装:执行 `npm install -g superlocalmemory` 后,通过 `slm setup` 选择运行模式,并使用 `slm doctor` 验证环境。如果需要预下载 embedding 模型(约 500MB),可运行 `slm warmup`。对于 Python 用户,可以直接通过 `pip install superlocalmemory` 进行安装,并使用 `slm restart` 管理服务。
本项目提供双重交互界面:通过 MCP 协议实现 IDE(如 Cursor)的无缝集成,实现自动化的上下文感知;通过原生 CLI 工具实现脚本化自动化。开发��可以根据需求在 IDE 侧进行交互式对话,或在 CI/CD 流水线、Docker 容器中使用 CLI 进行程序化操作,确保记忆能力覆盖从开发到部署的全流程。
系统通过环境变量进行配置。`SLM_MESH_HOST` 用于指定监听地址(远程访问需设为 IP);`SLM_MESH_PEER_URL` 用于配置远程 SLM 的完整 URL;`SLM_MESH_SHARED_SECRET` 是远程通信时的身份验证密钥;`SLM_MESH_DISCOVERY` 控制服务发现功能。通过这些配置,您可以轻松构建跨设备的分布式记忆网络。
SLM 提供强大的 CLI 命令集:使用 `slm remember` 存储记忆,`slm recall` 进行搜索,`slm forget` 删除匹配记忆。进阶用户可以使用 `slm trace` 查看带有分通道评分(per-channel score)的检索详情,并通过 `slm status` 和 `slm health` 实时监控系统运行状态。无论是 IDE 集成还是脚本调用,均能获得一致的后端支持。
通过消融实验(Ablation Study)数据可见,系统的核心性能高度依赖于其复杂的数学架构。Cross-encoder reranking 对准确率贡献最大(+30.7pp),其次是 Fisher-Rao 指标、数学层、BM25 通道以及 Sheaf consistency。这种多层级的架构确保了即使在处理复杂实体图(Entity graph)时,也能保持极高的检索精度与逻辑一致性。
在 Mode A(零云端模式)的基准测试中,SuperLocalMemory 在 Open-Domain 任务上达到了 85.0% 的准确率,显著超越了 Mem0(64.2%)。特别是在多跳推理(Multi-Hop)和时序逻辑(Temporal)方面表现优异,证明了其在处理复杂、长周期上下文时的卓越性能,是追求本地化与高精度记忆的首选。
该工具实现了本地AI记忆的突破,具有较高的检索准确率和零LLM能力,值得关注。
该工具使用 AGPL-3.0 协议,商用场景请仔细阅读协议条款,必要时咨询法律意见。
AI Skill Hub 为第三方内容聚合平台,本页面信息基于公开数据整理,不对工具功能和质量作任何法律背书。
建议在沙箱或测试环境中充分验证后,再部署至生产环境,并做好必要的安全评估。
⚠️ AGPL 3.0 — 最严格的 Copyleft,网络服务端使用也需开源,SaaS 使用受限。
经综合评估,超级本地记忆工具 在MCP工具赛道中表现稳健,质量良好。如果你已有明确的使用需求,可以直接上手体验;如果还在评估阶段,建议对比同类工具后再做决策。
| 原始名称 | superlocalmemory |
| 原始描述 | 开源MCP工具:World's first local-only AI memory to break 74% retrieval and 60% zero-LLM on Lo。⭐157 · Python |
| Topics | mcpagent-memoryagent-reliabilityai-agentsclaude-codecursor |
| GitHub | https://github.com/qualixar/superlocalmemory |
| License | AGPL-3.0 |
| 语言 | Python |
收录时间:2026-05-24 · 更新时间:2026-05-26 · License:AGPL-3.0 · AI Skill Hub 不对第三方内容的准确性作法律背书。
选择 Agent 类型,复制安装指令后粘贴到对应客户端