[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-80266":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":9,"htmlUrl":10,"language":11,"languages":10,"totalLinesOfCode":10,"stars":12,"forks":13,"watchers":14,"openIssues":15,"contributorsCount":16,"subscribersCount":16,"size":16,"stars1d":17,"stars7d":18,"stars30d":19,"stars90d":16,"forks30d":16,"starsTrendScore":20,"compositeScore":21,"rankGlobal":10,"rankLanguage":10,"license":22,"archived":23,"fork":23,"defaultBranch":24,"hasWiki":25,"hasPages":23,"topics":26,"createdAt":10,"pushedAt":10,"updatedAt":44,"readmeContent":45,"aiSummary":46,"trendingCount":16,"starSnapshotCount":16,"syncStatus":47,"lastSyncTime":48,"discoverSource":49},80266,"second-brain-cloudflare","rahilp\u002Fsecond-brain-cloudflare","rahilp","One memory layer, every AI tool. Store anything once — recall it in Claude, ChatGPT, Cursor, or any MCP client. Self-hosted on Cloudflare's free tier.","https:\u002F\u002Fwww.thesecondbrain.dev",null,"TypeScript",261,40,3,5,0,14,27,170,42,4.84,"MIT License",false,"main",true,[27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43],"ai-memory","claude","claude-ai","claude-code","cloudflare","cloudflare-workers","d1","ios-shortcuts","mcp","model-context-protocol","obsidian-plugin","personal-knowledge-management","second-brain","semantic-search","typescript","vectorize","workers","2026-06-12 02:04:00","# Second Brain\n\n[![License: MIT](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLicense-MIT-blue.svg)](LICENSE)\n[![Built with Cloudflare Workers](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FBuilt%20with-Cloudflare%20Workers-F38020?logo=cloudflare&logoColor=white)](https:\u002F\u002Fworkers.cloudflare.com\u002F)\n[![MCP Compatible](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FMCP-Compatible-8B5CF6)](https:\u002F\u002Fmodelcontextprotocol.io\u002F)\n\nYou use Claude for some things, ChatGPT for others, Cursor for code. But your context — your projects, decisions, preferences — doesn’t move with you. You re-explain yourself constantly.\n\nSecond Brain fixes that. One shared memory, available in every AI tool you use.\n\nAnd unlike the built-in memory inside any single app, this one is yours. It lives in your own account. No platform controls it, and no platform can take it away.\n\n[![Second Brain Demo](https:\u002F\u002Fimg.youtube.com\u002Fvi\u002Fh0JqRM0UxHE\u002Fhqdefault.jpg)](https:\u002F\u002Fyoutu.be\u002Fh0JqRM0UxHE)\n\n[![Deploy to Cloudflare](https:\u002F\u002Fdeploy.workers.cloudflare.com\u002Fbutton)](https:\u002F\u002Fdeploy.workers.cloudflare.com\u002F?url=https:\u002F\u002Fgithub.com\u002Frahilp\u002Fsecond-brain-cloudflare)\n\n-----\n\n## How it works\n\nConnect Second Brain to whichever AI tools you use. Then tell it things once. It finds them later by meaning, so asking “what did I decide about the pricing model?” surfaces the right note even if you never used those exact words when you saved it.\n\n|Tool         |What it does                                                |\n|-------------|------------------------------------------------------------|\n|`remember`   |Store anything: ideas, decisions, project context           |\n|`append`     |Add updates to an existing entry without creating duplicates|\n|`update`     |Replace an entry's content entirely                         |\n|`recall`     |Finds memories by meaning, not exact wording                |\n|`list_recent`|Browse recent memories by date                              |\n|`forget`     |Delete an entry                                             |\n\n-----\n\n## Save from anywhere\n\nMemory is only useful if it actually gets filled. Second Brain connects to the tools and moments where context naturally lives.\n\n- **Obsidian** -- notes sync automatically via the [community plugin](https:\u002F\u002Fgithub.com\u002Frahilp\u002Fsecond-brain-obsidian-plugin)\n- **iOS** -- Brain Dump, Text Brain Dump, and Save to Brain shortcuts in one tap\n- **Browser** -- bookmarklet saves any page or selection instantly\n- **Any AI client** -- use `remember` mid-conversation, right when something matters\n\n---\n\n## Setup\n\n> **Before you deploy:** You’ll be asked to set an `AUTH_TOKEN`. This is the password your AI clients use to connect.\n> \n> **Quick option:** Use a memorable phrase like `coffee-lover-2026`\n> \n> **Secure option:** Run `openssl rand -base64 32` in your terminal and paste the result\n> \n> **Save it.** You’ll need it in the next step.\n\n1. **Click Deploy** — everything provisions automatically\n1. **Set your token** — you’ll be prompted during deploy\n1. **Connect your AI tools** — [instructions here](..\u002F..\u002Fwiki\u002FConnect-to-AI-Clients)\n\nThat’s it. Your memory is live and ready across every tool you connect.\n\n```bash\n# Verify it's working (replace with your worker URL and token)\ncurl -X POST https:\u002F\u002F\u003Cyour-worker-url>\u002Fcapture \\\n  -H \"Authorization: Bearer coffee-lover-2026\" \\\n  -H \"Content-Type: application\u002Fjson\" \\\n  -d '{\"content\": \"second brain is working\", \"source\": \"test\"}'\n# → {\"ok\":true,\"id\":\"...\"}\n```\n\n-----\n\n## Documentation\n\n- [Setup Guide](..\u002F..\u002Fwiki\u002FSetup-Guide) — deploy, token setup, connecting AI clients\n- [How It Works](..\u002F..\u002Fwiki\u002FHow-It-Works) — semantic search, chunking, duplicate detection\n- [Connect to AI Clients](..\u002F..\u002Fwiki\u002FConnect-to-AI-Clients) — Claude Desktop, Claude Code, claude.ai, iOS\n- [Capture from Anywhere](..\u002F..\u002Fwiki\u002FCapture-from-Anywhere) — browser bookmarklet, iOS Shortcuts, share sheet\n- [Web UI](..\u002F..\u002Fwiki\u002FWeb-UI) — dashboard and mobile interface\n- [Obsidian Plugin](..\u002F..\u002Fwiki\u002FObsidian-Plugin) — install, configure, sync modes\n- [API Reference](..\u002F..\u002Fwiki\u002FAPI-Reference) — \u002Fcapture, \u002Fappend, \u002Fupdate, \u002Flist, \u002Fcount, \u002Ftags, \u002Fstats, \u002Fchat, \u002Fmcp endpoints\n\n-----\n\n## Integrations\n\n- **Obsidian** — [second-brain-obsidian-plugin](https:\u002F\u002Fgithub.com\u002Frahilp\u002Fsecond-brain-obsidian-plugin) · available in [Obsidian Community Plugins](https:\u002F\u002Fcommunity.obsidian.md\u002Fplugins\u002Fsecond-brain-sync)\n- **iOS** — Brain Dump, Text Brain Dump, and Save to Brain shortcuts in [`integrations\u002Fios-shortcuts\u002F`](integrations\u002Fios-shortcuts\u002F)\n- **Browser** — bookmarklet in [`integrations\u002Fbookmarklet.js`](integrations\u002Fbookmarklet.js)\n\n-----\n\n## Stack\n\nCloudflare Workers · D1 SQLite · Vectorize · Workers AI · MCP TypeScript SDK · MIT License\n\nAll free tier at personal scale. Your data stays in your own Cloudflare account.\n\n-----\n\n[MIT License](LICENSE) · [Discussions](https:\u002F\u002Fgithub.com\u002Frahilp\u002Fsecond-brain-cloudflare\u002Fdiscussions)\n","Second Brain 是一个基于 Cloudflare 构建的记忆层工具，旨在为各种 AI 工具（如 Claude、ChatGPT 和 Cursor）提供统一的知识存储和检索服务。项目采用 TypeScript 开发，并利用了 Cloudflare Workers 和 D1 数据库等技术，确保用户的数据能够安全地存储在个人账户中，不受平台限制。其核心功能包括记忆条目的创建、更新、删除以及基于语义的搜索，支持通过 Obsidian 插件、iOS 快捷方式、浏览器书签等多种方式保存信息。非常适合需要跨多个 AI 平台共享上下文信息的个人或团队使用，有助于提高工作效率和知识管理能力。",2,"2026-06-11 04:00:06","CREATED_QUERY"]