开放大脑MCP框架 是 AI Skill Hub 本期精选MCP工具之一。已获得 3.3k 颗 GitHub Star，综合评分 8.0 分，整体质量较高。我们强烈推荐将其纳入你的 AI 工具库，帮助提升工作效率。
开放大脑MCP框架 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。
开放大脑MCP框架 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/NateBJones-Projects/OB1
# 方式二：手动配置 claude_desktop_config.json
{
"mcpServers": {
"----mcp--": {
"command": "npx",
"args": ["-y", "ob1"]
}
}
}
# 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 开放大脑MCP框架 执行以下任务... Claude: [自动调用 开放大脑MCP框架 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": {
"____mcp__": {
"command": "npx",
"args": ["-y", "ob1"],
"env": {
// "API_KEY": "your-api-key-here"
}
}
}
}
// 保存后重启 Claude Desktop 生效
<p align="center"> <img src=".github/ob1-logo-wide.png" alt="Open Brain" width="600"> </p>
The infrastructure layer for your thinking. One database, one AI gateway, one chat channel. Any AI you use can plug in. No middleware, no SaaS chains, no Zapier.
This isn't a notes app. It's a database with vector search and an open protocol — built so that every AI tool you use shares the same persistent memory of you. Claude, ChatGPT, Cursor, Claude Code, whatever ships next month. One brain. All of them.
Open Brain was created by Nate B. Jones. Follow the Substack for updates, discussion, and the companion prompt pack. Join the Discord for real-time help and community.
Never built an Open Brain? Start here:
If you hit a wall: We built a FAQ that covers the most common questions and gotchas. And if you need real-time help, we created dedicated AI assistants that know this system inside and out: a Claude Skill, a ChatGPT Custom GPT, and a Gemini GEM. Use whichever one matches the AI tool you already use.
Build these in order. Each one teaches new concepts through something you'll actually use. By the end, your agent manages your household, your schedule, your meals, your professional network, and your career — all interconnected.
| # | Extension | What You Build | Difficulty |
|---|---|---|---|
| 1 | [Household Knowledge Base](extensions/household-knowledge/) | Home facts your agent can recall instantly | Beginner |
| 2 | [Home Maintenance Tracker](extensions/home-maintenance/) | Scheduling and history for home upkeep | Beginner |
| 3 | [Family Calendar](extensions/family-calendar/) | Multi-person schedule coordination | Intermediate |
| 4 | [Meal Planning](extensions/meal-planning/) | Recipes, meal plans, shared grocery lists | Intermediate |
| 5 | [Professional CRM](extensions/professional-crm/) | Contact tracking wired into your thoughts | Intermediate |
| 6 | [Job Hunt Pipeline](extensions/job-hunt/) | Application tracking and interview pipeline | Advanced |
Extensions compound. Your CRM knows about thoughts you've captured. Your meal planner checks who's home this week. Your job hunt contacts automatically become professional network contacts. This is what happens when your agent can see across your whole system.
Standalone capabilities that make your Open Brain smarter.
| Recipe | What It Does | Contributor |
|---|---|---|
| [Auto-Capture Protocol](recipes/auto-capture/) | Stores ACT NOW items and session summaries in Open Brain at session close using the reusable Auto-Capture skill | [@jaredirish](https://github.com/jaredirish) |
| [Panning for Gold](recipes/panning-for-gold/) | Mine brain dumps and voice transcripts for actionable ideas — battle-tested across 13+ sessions | [@jaredirish](https://github.com/jaredirish) |
| [Aiception (formerly Claudeception)](recipes/claudeception/) | Self-improving system that creates new skills from work sessions — skills that create other skills | [@jaredirish](https://github.com/jaredirish) |
| [Schema-Aware Routing](recipes/schema-aware-routing/) | LLM-powered routing that distributes unstructured text across multiple database tables | [@claydunker-yalc](https://github.com/claydunker-yalc) |
| [Fingerprint Dedup Backfill](recipes/fingerprint-dedup-backfill/) | Backfill content fingerprints and safely remove duplicate thoughts | [@alanshurafa](https://github.com/alanshurafa) |
| [Source Filtering](recipes/source-filtering/) | Filter thoughts by source and backfill missing metadata for early imports | [@matthallett1](https://github.com/matthallett1) |
| [Life Engine](recipes/life-engine/) | Self-improving personal assistant — calendar, habits, health, proactive briefings via Telegram or Discord | [@justfinethanku](https://github.com/justfinethanku) |
| [Life Engine Video](recipes/life-engine-video/) | Add-on that renders Life Engine briefings as short animated videos with voiceover | [@justfinethanku](https://github.com/justfinethanku) |
| [Daily Digest](recipes/daily-digest/) | Automated daily summary of recent thoughts delivered via email or Slack | OB1 Team |
| [Bring Your Own Context](recipes/bring-your-own-context/) | Portable context workflow that packages extraction prompts, profile generation, and remote MCP deployment into one entrypoint | [@jonathanedwards](https://github.com/jonathanedwards) |
| [Work Operating Model Activation](recipes/work-operating-model-activation/) | Conversation-first workflow that turns tacit work patterns into structured Open Brain records and agent-ready operating files | [@jonathanedwards](https://github.com/jonathanedwards) |
| [World Model Diagnostic Activation](recipes/world-model-diagnostic-activation/) | Ship-now activation path for a 20-minute world-model readiness diagnostic that compounds through core Open Brain capture | [@jonathanedwards](https://github.com/jonathanedwards) |
| [Research-to-Decision Workflow](recipes/research-to-decision-workflow/) | Composition recipe that chains canonical skills into operator and investor research, synthesis, meeting, and memo workflows | [@NateBJones](https://github.com/NateBJones) |
| [OpenClaw Agent Memory for OB1](recipes/openclaw-agent-memory/) | Canonical recipe for using OB1 Agent Memory as the governed continuity layer for OpenClaw workflows | OB1 Team |
| [OpenClaw Code Review Memory](recipes/openclaw-code-review-memory/) | Flagship workflow for compounding repo-specific review lessons, maintainer corrections, and false positives | OB1 Team |
| [OpenClaw TaskFlow Work Log](recipes/openclaw-taskflow-work-log/) | Durable handoff recipe for long-running OpenClaw TaskFlows across agents, models, and channels | OB1 Team |
MCP server extensions, alternative deployment targets, and capture sources beyond Slack.
| Integration | What It Does | Contributor |
|---|---|---|
| [Kubernetes Deployment](integrations/kubernetes-deployment/) | Fully self-hosted K8s deployment with PostgreSQL + pgvector — no Supabase required | [@velo](https://github.com/velo) |
| [Agent Memory API](integrations/agent-memory-api/) | Runtime-neutral recall, write-back, review, inspector, and recall-trace API for OB1 Agent Memory | OB1 Team |
| [OpenClaw Agent Memory](integrations/openclaw-agent-memory/) | OpenClaw plugin and publishing package for using OB1 Agent Memory from OpenClaw workflows | OB1 Team |
| [Slack Capture](integrations/slack-capture/) | Quick-capture thoughts via Slack messages with auto-embedding and classification | Core |
| [Discord Capture](integrations/discord-capture/) | Discord bot that captures messages into Open Brain, mirroring the Slack pattern | Core |
Tables and sidecars that extend the base thoughts model without replacing it.
| Schema | What It Does | Contributor |
|---|---|---|
| [Agent Memory](schemas/agent-memory/) | Provenance, review, use-policy, source-reference, relation, recall-trace, and audit sidecars for agent workflow memory | OB1 Team |
aiskill88点评：新兴MCP生态中的重要基础设施，3.3k星标认可度高。记忆层架构设计先进，但文档和生态成熟度需关注。适合前沿AI应用探索者。
该工具使用 NOASSERTION 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。
📄 NOASSERTION — 请查阅原始协议条款了解具体使用限制。
经综合评估，开放大脑MCP框架 在MCP工具赛道中表现稳健，质量优秀。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 | OB1 |
| 原始描述 | 开源MCP工具：Open Brain — The infrastructure layer for your thinking. One database, one AI ga。⭐3.3k · TypeScript |
| Topics | 记忆层MCP协议AI智能体开源框架TypeScript |
| GitHub | https://github.com/NateBJones-Projects/OB1 |
| License | NOASSERTION |
| 语言 | TypeScript |
收录时间：2026-05-22 · 更新时间：2026-05-22 · License：NOASSERTION · 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