Give your agent fleet a shared brain
Brainz is a product-knowledge graph built for agent orchestration. Features, decisions,
constraints, and patterns live as markdown concepts wired into a graph — and before your
orchestrator delegates a coding task, one get_context call over MCP returns a
token-budgeted markdown briefing to paste straight into the subagent's prompt. Subagents get
exactly the product knowledge they need. The orchestrator's context stays clean.
Hosted at brain.brownmatter.ai — or run it locally from a folder of markdown.
A knowledge base agents can actually use
Not a wiki that goes stale in a drawer — a queryable graph whose primary consumer is an orchestrator agent, with humans as welcome guests.
Concepts, linked into a graph
Every concept is a markdown note — feature, decision, constraint, pattern, or glossary
term. Inline [[wiki-links]] and typed relations like depends_on, part_of, and constrains wire notes
into a directed graph, so context assembly follows the structure of your product instead
of guessing from keywords.
---
title: Lead Scoring
type: feature
tags: [crm, ranking]
relations:
depends_on: [contact-model]
constrained_by: [rate-limits]
---
Scores leads 0-100. Recomputed on every
[[contact-model]] change; see [[scoring-decision]].Remote MCP in one snippet
Point any MCP client at your hosted vault — Claude Code, or anything that speaks
streamable HTTP. Create an API key in the dashboard, add one entry to .mcp.json, and all eight tools are live.
{
"mcpServers": {
"brainz": {
"type": "http",
"url": "https://brain.brownmatter.ai/mcp",
"headers": { "Authorization": "Bearer bz_..." }
}
}
}Hybrid search, graceful fallback
Queries fuse full-text search with embedding similarity via reciprocal-rank fusion, then expand through the graph to pull in the neighbors that matter. If embeddings are unavailable — offline, no key, no model — everything degrades to keyword search. Nothing crashes, ever.
Local-first & open source
The same brain runs from a folder of markdown on your machine: npx brainz init,
edit notes in any editor, and serve them to your agents over stdio MCP with the CLI. The
index is derived SQLite, rebuilt from your files — your knowledge stays plain markdown,
in git, forever portable.
No signup form required — your agent does it
An orchestrator can provision its own brain: hit https://brain.brownmatter.ai/mcp with no
credentials and the endpoint exposes a single public signup tool. One call
creates the account, a first vault, and an API key that works immediately — and returns a
claim link the agent hands to its human, who sets a password and takes ownership of the
dashboard whenever they're ready.
# connect to https://brain.brownmatter.ai/mcp with NO auth header → one public tool
→ tools/call signup { "email": "you@company.com" }
← { "apiKey": "bz_…", "claimUrl": "https://brain.brownmatter.ai/claim/…", "vaultSlug": "my-vault" }Three steps to briefed subagents
Capture concepts
Write features, decisions, and constraints as markdown notes — or let agents capture
knowledge as they work with upsert_concept. Wiki-links and typed relations
grow the graph as you go. No account yet? Your agent can sign itself up and seed the vault.
Wire the MCP
One entry in .mcp.json: hosted over HTTP with an API key, or local over
stdio. Your orchestrator sees eight tools — search, traversal, writes, and the flagship, get_context.
Brief every subagent
Before delegating, the orchestrator calls get_context and injects the
returned markdown bundle into the subagent's prompt. Curated product knowledge in;
context pollution out.
Free. Actually free.
Hosted vaults at brain.brownmatter.ai are free for everyone — no tiers, no trial
clock, no credit card, no seat limits. And because the engine is open source and every concept
is plain markdown, you're never locked in: the same vault runs from a folder on your laptop.