GPU Brain gives every agent a durable brain it can search, read, write, and link in seconds — markdown memory through hosted MCP, CLI, and API.
A hosted memory layer your agents can search, read, and write to in seconds.
Agents can search memory before answering, so important context is retrieved instead of reconstructed from chat history.
Natural-language recall, exact keyword matches, tags, collections, and page types work together so agents can find the right source fast.
Connect Claude, Cursor, OpenClaw-style agents, and other MCP clients to search, read, write, tag, link, and inspect memory.
Create relationships between notes, people, companies, and decisions so memory becomes a graph instead of a pile of files.
Humans can browse, edit, and audit the same markdown pages that agents search and update.
Import folders, create pages, inspect links, run local MCP, or proxy stdio MCP to the hosted endpoint from the terminal.
Read memory, do the work, write back what should survive.
The agent checks durable memory before it answers, plans, or starts work.
It opens the pages, tags, links, and timelines that explain the current situation.
Responses, plans, and tool calls use the same memory through MCP, CLI, or REST.
New decisions, facts, links, and timeline events are saved for the next agent turn.
One memory layer for local terminal workflows and remote agents.
# Search your brain
curl -X POST https://gpubrain.app.nz/api/search \
-H "Authorization: Bearer gb_your_key" \
-d '{"query": "notes about fundraising"}'
# Add a note
curl -X POST https://gpubrain.app.nz/api/pages \
-H "Authorization: Bearer gb_your_key" \
-d '{"slug": "ideas/fundraising", "title": "Fundraising notes", "body": "..."}'
# Hosted MCP JSON-RPC
curl -X POST https://gpubrain.app.nz/mcp \
-H "Authorization: Bearer gb_your_key" \
-H "Content-Type: application/json" \
-d '{"jsonrpc":"2.0","id":1,"method":"tools/list","params":{}}'
# MCP for Claude, Cursor, or local agents
{
"mcpServers": {
"gpubrain": {
"command": "gpubrain-cli",
"args": ["mcp", "--api-url", "https://gpubrain.app.nz"],
"env": { "GPUBRAIN_API_KEY": "gb_your_key" }
}
}
}
How teams use GPU Brain to give their agents memory that lasts.
How the read-write memory loop changes everyday agent behavior.
SearchWhy tiny static models are a good fit for always-on retrieval.
EngineeringHow the Go search layer connects markdown, vectors, keywords, and future GPU paths.
100 free credits on signup. Pro starts at $8 USD/month or $80 USD/year.
Create free account