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.
Download for Mac or Windows
Deploy to Cloudflare · Read the documentation
What it does
- 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.
See it in action
Team Edition
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.
How it works
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.
Memory tools
| 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_prompt_capsule |
Read a deterministic core or project context projection for a gateway-controlled prompt prefix |
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?"
Prompt Capsules
Prompt Capsules are deterministic, read-only projections for gateways and
custom agents that can place stable context before a changing user request.
They complement query-specific recall; they do not inject every memory into
every prompt.
A Capsule entry is an ordinary canonical memory with one target tag and one
slot tag. Core entries use capsule:core; project entries use
capsule:project:. Slots are emitted in this fixed order:
- Core:
identity,preferences,constraints,principles - Project:
current-state,decisions,open-questions
Tag the slot as capsule-slot: and keep at most one canonical entry per
slot. Draft and deprecated entries are ignored. Ambiguous slots are omitted
without choosing a winner; malformed rows are skipped. The response reports
duplicate_slots and invalid_entries, and complete is false. Other valid
slots remain available, including on the shared layer.
An entry must carry status:canonical to be part of a Capsule. The easiest way
is to include status:canonical in the tags at remember or capture time (it is
stored after whitespace trimming, and the classifier then leaves it alone);
otherwise the definition starts as draft and requires set_status canonical.
Classification, including /classify-pending, never publishes a capsule. A
write that contradicts a protected memory is demoted to draft even when the
caller requested canonical. To take an entry out of a Capsule, set its
status to draft or deprecated. MCP update accepts an optional tags array:
pass the complete replacement definition, for example
["capsule:core", "capsule-slot:preferences"], along with the entry id and
content. Naming either capsule namespace replaces both namespaces; a lone
slot tag is not a complete definition. Omit tags to preserve existing tags.
MCP and REST capture/update accept at most 64 tags of 128 characters each.
Shared-layer recovery: members can publish their own shared definitions, but cannot edit a teammate's entry.