经 AI Skill Hub 精选评估,GigaBrain本地记忆层 获评「强烈推荐」。这款MCP工具在功能完整性、社区活跃度和易用性方面表现出色,AI 评分 8.2 分,适合有一定技术背景的用户使用。
为OpenClaw、Codex App和Codex CLI提供本地优先的记忆存储层,支持信息捕获与智能回忆。帮助AI代理保持上下文连贯性,适合需要长期记忆的AI应用开发者。
GigaBrain本地记忆层 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。
为OpenClaw、Codex App和Codex CLI提供本地优先的记忆存储层,支持信息捕获与智能回忆。帮助AI代理保持上下文连贯性,适合需要长期记忆的AI应用开发者。
GigaBrain本地记忆层 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/legendaryvibecoder/gigabrain
# 方式二:手动配置 claude_desktop_config.json
{
"mcpServers": {
"gigabrain-----": {
"command": "npx",
"args": ["-y", "gigabrain"]
}
}
}
# 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 GigaBrain本地记忆层 执行以下任务... Claude: [自动调用 GigaBrain本地记忆层 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": {
"gigabrain_____": {
"command": "npx",
"args": ["-y", "gigabrain"],
"env": {
// "API_KEY": "your-api-key-here"
}
}
}
}
// 保存后重启 Claude Desktop 生效
<p align="center"> <strong>One shared memory for your AI assistants, under your control.</strong> </p>
<p align="center"> <a href="https://github.com/legendaryvibecoder/gigabrain/releases"><img src="https://img.shields.io/github/v/release/legendaryvibecoder/gigabrain?include_prereleases&style=for-the-badge" alt="GitHub release"></a> <a href="https://www.npmjs.com/package/@legendaryvibecoder/gigabrain"><img src="https://img.shields.io/npm/v/@legendaryvibecoder/gigabrain?style=for-the-badge" alt="npm version"></a> <a href="LICENSE"><img src="https://img.shields.io/badge/License-MIT-blue.svg?style=for-the-badge" alt="MIT License"></a> <a href="https://github.com/legendaryvibecoder/gigabrain/stargazers"><img src="https://img.shields.io/github/stars/legendaryvibecoder/gigabrain?style=for-the-badge" alt="GitHub Stars"></a> <img src="https://img.shields.io/badge/local--first-by%20default-brightgreen?style=for-the-badge" alt="Local-first by default"> </p>
<p align="center"> <a href="docs/configuration.md">Configuration</a> · <a href="CHANGELOG.md">Changelog</a> · <a href="CONTRIBUTING.md">Contributing</a> · <a href="SECURITY.md">Security</a> · <a href="https://github.com/legendaryvibecoder/gigabrain/discussions">Discussions</a> </p>
---
| What it means for you | |
|---|---|
| **Checkpoint control plane** | Checkpoints become immutable episodes. Durable candidates remain reviewable proposals, and decisions can produce policy-versioned receipts. |
| **Remote MCP beta** | A self-hosted Streamable HTTP connector can serve approved tools to Claude and ChatGPT. It verifies OAuth JWTs, enforces exact memory scopes, redacts local paths, and enables no writes by default. |
| **Answer-focused recall** | Recall selects evidence that can answer questions about duration, completion, or certification. Unrelated preferences rank lower. |
| **Conflict checks during import** | Gigabrain checks conflicts during import and during maintenance. Risky changes wait for review. |
| **Local host imports** | Gigabrain can inspect and import supported local data from Codex, Claude Code, Hermes, Cursor, and Windsurf. Each imported fact keeps its source. |
| **Portable handoff** | Export and import bundles use integrity hashes. Data moves only when you run the export and import commands. |
| **Privacy check for releases** | The release check scans Git files and the npm package contents. It blocks unknown binary files and redacts each finding. |
| **Secured local console** | Runtime tests cover authentication, scope rules, path limits, security headers, and dependency checks. |
The cloud inbox, transcript recovery, Git wiki, Obsidian reference set, remote bridge, and URL importer start disabled. Read the configuration guide and privacy model before you add a data source or network provider.
node:sqlite and built-in TypeScript type stripping.These commands install the package, connect a project, check the setup, and write an audit report. All supported imports stay read-only.
npm install @legendaryvibecoder/gigabrain
npx gigabrainctl init --project-root /path/to/repo
npx gigabrainctl doctor --config ~/.gigabrain/config.json --target both
npx gigabrainctl handoff --config ~/.gigabrain/config.json \
--output-dir ./gigabrain-memory-audit
init writes the configuration to ~/.gigabrain/config.json. The other commands and assistant setups use this file. Read the audit report before you enable a feature from the configuration guide.
Open the guide for your assistant: Codex · Claude Code · OpenClaw.
| Method | Path | Auth | Description |
|---|---|---|---|
GET | /gb | No | Service landing response |
GET | /gb/health | No | Health check |
POST | /gb/bench/recall | Token | Recall result plus benchmark diagnostics |
POST | /gb/control/apply | Token | **Mutating:** apply an explicit memory action |
GET | /gb/entities | Token | List world-model entities |
GET | /gb/entities/:id | Token | Entity detail (/gb/entities/detail?id=... is also accepted) |
GET | /gb/beliefs | Token | List beliefs |
GET | /gb/episodes | Token | List episodes |
GET | /gb/open-loops | Token | List open loops |
GET | /gb/contradictions | Token | List contradiction-review items |
GET | /gb/adjudications | Token | List arbitration verdicts |
GET | /gb/beliefs-as-of | Token | Bi-temporal belief snapshot |
GET | /gb/review-queue | Token | Read-only review queue |
GET | /gb/relationships | Token | Relationship graph for an entity |
GET | /gb/evolution | Token | Entity evolution by claim slot |
GET | /gb/memory/:id/timeline | Token | Event timeline for a memory |
POST | /gb/recall | Token | Memory recall for a query |
POST | /gb/recall/explain | Token | Recall diagnostics and routing explanation |
POST | /gb/suggestions | Token | **Mutating:** validate and ingest structured suggestions |
/gb and /gb/health return service status only. Every data route accepts X-GB-Token, X-OpenClaw-Token, or a Bearer token. A route denies access when its configuration has no token. The dangerous development setting GB_ALLOW_NO_AUTH=1 can bypass Node route checks only when no token is configured. It prints a warning. Use this setting only in a disposable loopback environment. OpenClaw gateway authentication can add an outer layer.
高质量MCP实现,提供essential的记忆层能力,本地架构保障隐私。活跃维护,生态适配良���,值得推荐。
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。
✅ MIT 协议 — 最宽松的开源协议之一,可自由商用、修改、分发,仅需保留版权声明。
AI Skill Hub 点评:GigaBrain本地记忆层 的核心功能完整,质量优秀。对于Claude Desktop / Claude Code 用户来说,这是一个值得纳入个人工具库的选择。建议先在非生产环境试用,再逐步推广。
| 原始名称 | gigabrain |
| 原始描述 | 开源MCP工具:Local-first memory layer for OpenClaw, Codex App, and Codex CLI: capture, recall。⭐207 · JavaScript |
| Topics | 本地记忆MCP工具AI代理上下文管理开源 |
| GitHub | https://github.com/legendaryvibecoder/gigabrain |
| License | MIT |
| 语言 | JavaScript |
收录时间:2026-05-20 · 更新时间:2026-05-30 · License:MIT · 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