Private memory for you. Shared memory for your team. Available to every MCP-compatible AI tool you use.
Now with Team Edition — private personal layers plus a shared team layer, in one Worker.
Claude, ChatGPT, Cursor, Codex, and the other AI tools you use do not naturally share context. You end up repeating the same projects, decisions, and preferences in every app.
Second Brain gives those tools one persistent memory system. It runs in your own Cloudflare account, stays under your control, and retrieves the right context by meaning rather than exact wording.
The desktop app is the easiest way to start. It builds your Second Brain and connects your AI tools in about two minutes—no terminal or Cloudflare setup required.
#3 Product of the Day on Product Hunt
- Recalls by meaning. Ask a natural-language question and find the right memory even when you used different words when saving it.
- Works across tools and devices. Every client talks to the same Worker, so there is nothing to copy or synchronize between apps.
- Keeps you in control. Browse, edit, append, connect, share, export, or permanently remove any memory from the dashboard.
- Builds useful context. Automatic classification, duplicate detection, relationships, time-aware ranking, and optional weekly insights help the brain stay useful as it grows.
- Captures from where you already work. Use MCP clients, the CLI, browser extension, Obsidian, Notion, calendars, email, iOS Shortcuts, or the web dashboard.
- Stays in your account. Memories, vectors, credentials, and application resources live in your own Cloudflare account.
Second Brain can now be a team's memory without stopping being yours.
- Every person gets a Personal workspace that nobody else can read, plus a Shared layer visible to the team.
- Memories are private by default and only enter the Shared layer when someone deliberately shares them.
- Sharing moves one canonical memory rather than making a copy. Its author remains visible, and only the author or an admin can edit, delete, or un-share it.
- Admins can manage members, access, capture defaults, and integrations without gaining access to anyone's personal workspace.
- Existing v2 memories become the owner's private memories during upgrade. Nothing is exposed to a team automatically.
| Layer | Who can read it | Who can edit or delete it |
|---|---|---|
| Personal | Only you | Only you |
| Shared | Everyone on the team | The author or an admin |
The same Worker supports personal and team use; there is no separate team deployment. In the API, CLI, and MCP tools, the Shared layer is represented by the stable workspace value company. See the Team Setup guide for member management, capture policies, sharing, and upgrades.
v3.0.0 scope: each brain has one shared team. The API and MCP layer include optional team parameters and a list_teams tool so multi-team support can ship later without breaking changes; the dashboard and admin flows do not create or switch between multiple teams yet. See CHANGELOG.md.
Second Brain runs as a Cloudflare Worker backed by D1, Vectorize, Workers AI, and KV. Every app and AI client connects to that Worker through REST or the Model Context Protocol (MCP).
- Capture: Save a decision, preference, project update, note, or source from any connected client.
- Organize: Second Brain classifies it, checks for duplicates and contradictions, creates relationships, and indexes it for semantic search.
- Recall: Ask in natural language. Second Brain retrieves relevant memories, follows useful connections, and returns source-backed context to the tool you are using.
If Vectorize is unavailable, captures and keyword recall continue working. Your memories remain usable while semantic indexing is restored. Keyword recall works for Japanese, Chinese, and other scripts written without spaces, and for full-width text. The shipped embedding models read English best; the desktop app's Settings can switch a brain to a multilingual reading.
| Tool | What it does |
|---|---|
remember |
Store ideas, decisions, preferences, and project context |
append |
Add a timestamped update to an existing memory |
update |
Replace an existing memory |
recall |
Find memories by meaning rather than exact wording |
list_recent |
Browse recently saved memories |
list_teams |
List shared teams you belong to (names and ids). In v3.0.0 this is one team; used by MCP clients for future multi-team support |
get |
Read one memory by ID |
forget |
Permanently delete a memory |
set_status |
Mark a memory canonical, draft, or deprecated |
link |
Add an explicit relationship between two memories |
unlink |
Remove a relationship between two memories |
connections |
List the memories connected to a memory |
share |
Move a memory between the Personal and Shared layers |
On a team brain, memory tools accept a workspace of personal or company when you want to choose a layer explicitly. company is the wire value for the Shared team layer. Without workspace, captures use the member and team defaults, while recall searches everything that person is allowed to see.
Optional team (workspace id) and MCP list_teams / GET /team/workspaces are wired for a future multi-team release. In v3.0.0 you can omit them — each brain has one shared team and the primary team is used automatically.
CLI example:
brain remember --workspace company "We ship on Thursdays"
brain recall --workspace company "when do we ship?"All three setup methods deploy the same Second Brain into your Cloudflare account.
Download the latest release, open it, choose a password, and sign in to Cloudflare. The app provisions the Worker and its resources, then helps connect your AI clients, CLI, browser extension, Obsidian, and Notion.
The macOS build is signed and notarized by Apple. Windows release builds are code-signed; see the code signing policy.
Use Deploy to Cloudflare to provision the Worker yourself without cloning the repository.
Your AUTH_TOKEN is the password for your Second Brain—the same value every client asks for. Use either:
-
A memorable phrase, such as
coffee-lover-2026 -
A randomly generated token:
openssl rand -base64 32
When Cloudflare shows the configuration form, enter:
| FIELD | VALUE |
|---|---|
| AUTH_TOKEN | The token you created |
| DIMENSION | 384 |
| METRIC | cosine |
After deployment, connect compatible clients to:
https://YOUR-WORKER-URL/mcp
Use OAuth where the client supports it, or an Authorization: Bearer <token> header for static clients. Query-string token authentication was removed in v3 because URLs can leak through browser history and logs.
Having connection issues? See Connect to AI Clients → Troubleshooting (Opera warnings, Cursor OAuth, Claude Code tool visibility).
For developers who want full command-line control:
npm install
npm run vectors:create
npm run deployFollow the Setup Guide for prerequisites, resource creation, deployment verification, and troubleshooting. Then use Connect to AI Clients for client-specific instructions.
Develop locally:
npm run dev # start the Worker locally
npm test # run the test suiteSee Local Development for mixed local/remote Wrangler configuration and sharing a local brain through a tunnel.
Verify the deployment (replace YOUR-WORKER-URL and YOUR-TOKEN):
curl -X POST https://YOUR-WORKER-URL/capture \
-H "Authorization: Bearer YOUR-TOKEN" \
-H "Content-Type: application/json" \
-d '{"content":"second brain is working","source":"test"}'A successful response looks like {"ok":true,"id":"..."}.
- AI clients: Claude, ChatGPT, Cursor, Codex, and other MCP-compatible clients
- CLI:
second-brain-cf-cli - Browser: Chrome extension or
integrations/bookmarklet.js - Notes: Second Brain Sync for Obsidian and Notion
- Calendar and email: Google, Outlook, iCloud, and Gmail integrations
- iPhone and iPad: Voice, text, and share-sheet shortcuts in
integrations/ios-shortcuts/ - Claude Code: session hooks that recall project context on start and save the conversation on exit —
integrations/claude-code-hooks/ - Dashboard: Capture, recall, browse, graph, share, back up, and restore from the built-in web interface
See Capture from Anywhere for setup and usage instructions.
Team Edition adds Personal and Shared memory layers, per-person authentication, sharing and attribution, author locks, team administration, capture policies, team-aware recall and graphs, and a private-by-default upgrade from v2.
It also hardens tenant isolation across REST, MCP, integrations, imports, insights, graph traversal, and vector search, backed by expanded unit, integration, and UI coverage.
See GitHub Releases for release notes and previous versions.
- Wiki home: Documentation index and quick links
- Setup Guide: Desktop, one-click, and manual deployment
- Team Setup: Team mode, member access, sharing rules, capture defaults, and offboarding
- Connect to AI Clients: ChatGPT, Claude, Claude Code, Codex, Cursor, and other MCP clients
- Cursor Instructions: MCP setup and Cursor Rules for automatic recall and remember
- Capture from Anywhere: CLI, browser extension, bookmarklet, iOS Shortcuts, and Notion
- Notion Integration: Connect, synchronize, and troubleshoot Notion
- Web UI: Dashboard and mobile interface
- How It Works: Retrieval, ranking, classification, duplicates, and architecture
- API Reference: REST endpoints and MCP tools
- How to Upgrade: Upgrade an existing deployment
- Frequently Asked Questions: Design, privacy, costs, and common questions
- Obsidian Plugin: Installation, configuration, and sync modes
- Local Development: Run the Worker locally and share it for testing
Second Brain uses Cloudflare Workers, D1 SQLite, Vectorize, Workers AI, KV, the Model Context Protocol, and TypeScript. It runs within Cloudflare's free tier at personal scale.
Your application resources and data stay in your Cloudflare account. The project maintainers cannot see your memories or credentials. Integrations contact only the services you choose to connect.
Windows release builds of the Second Brain desktop app are code-signed.
Free code signing is provided by SignPath.io, with a certificate from SignPath Foundation.
| Role | Members |
|---|---|
| Authors | Rahil P (@rahilp) |
| Reviewers | Rahil P (@rahilp) |
| Approvers | Rahil P (@rahilp) |
Release binaries are built from this repository by GitHub Actions. Every signing request is reviewed and manually approved before a signed release is published.
Privacy statement: This program will not transfer information to other networked systems unless the user or the person installing or operating it specifically requests that action. During setup, the desktop app communicates with Cloudflare to create resources in the user's account. Afterwards, it communicates with that deployment and with integrations the user explicitly connects. Memories and credentials are never sent to the project maintainers.