Initial project scaffold: Open Brain self-hosted knowledge infrastructure

Node.js/TypeScript server with MCP endpoint for AI assistant integration,
Discord bot for thought capture and slash commands, PostgreSQL + pgvector
for semantic search, and OpenRouter for embeddings/metadata extraction.
Dockerized for deployment behind Caddy.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
This commit is contained in:
YOUNG
2026-03-06 14:53:41 -06:00
commit e90ea1591b
16 changed files with 3332 additions and 0 deletions

15
.env.example Normal file
View File

@@ -0,0 +1,15 @@
# Database (host.docker.internal = host machine from inside Docker)
DATABASE_URL=postgresql://brain_user:password@host.docker.internal:5432/brain
# OpenRouter (AI gateway for embeddings + metadata extraction)
OPENROUTER_API_KEY=sk-or-...
# Discord bot
DISCORD_BOT_TOKEN=
DISCORD_CAPTURE_CHANNEL_ID=
# MCP endpoint authentication (generate with: openssl rand -hex 32)
MCP_ACCESS_KEY=
# Server port
PORT=3100

4
.gitignore vendored Normal file
View File

@@ -0,0 +1,4 @@
node_modules/
dist/
.env
*.log

15
Dockerfile Normal file
View File

@@ -0,0 +1,15 @@
FROM node:22-alpine AS builder
WORKDIR /app
COPY package.json package-lock.json ./
RUN npm ci
COPY tsconfig.json ./
COPY src/ ./src/
RUN npm run build
FROM node:22-alpine
WORKDIR /app
COPY package.json package-lock.json ./
RUN npm ci --omit=dev
COPY --from=builder /app/dist ./dist
EXPOSE 3100
CMD ["node", "dist/index.js"]

10
docker-compose.yml Normal file
View File

@@ -0,0 +1,10 @@
services:
open-brain:
build: .
container_name: open-brain
restart: unless-stopped
ports:
- "3100:3100"
env_file: .env
extra_hosts:
- "host.docker.internal:host-gateway"

2171
package-lock.json generated Normal file

File diff suppressed because it is too large Load Diff

34
package.json Normal file
View File

@@ -0,0 +1,34 @@
{
"name": "open-brain",
"version": "1.0.0",
"description": "Self-hosted personal knowledge infrastructure with MCP and Discord",
"main": "dist/index.js",
"scripts": {
"build": "tsc",
"start": "node dist/index.js",
"dev": "tsx src/index.ts"
},
"repository": {
"type": "git",
"url": "https://git.option.design/will/open-brain.git"
},
"keywords": [],
"author": "",
"license": "ISC",
"type": "commonjs",
"dependencies": {
"@hono/node-server": "^1.19.11",
"@modelcontextprotocol/sdk": "^1.27.1",
"discord.js": "^14.25.1",
"hono": "^4.12.5",
"pg": "^8.20.0",
"pgvector": "^0.2.1",
"zod": "^4.3.6"
},
"devDependencies": {
"@types/node": "^25.3.5",
"@types/pg": "^8.18.0",
"tsx": "^4.21.0",
"typescript": "^5.9.3"
}
}

377
project_plan.MD Normal file
View File

@@ -0,0 +1,377 @@
Open Brain — Self-Hosted Implementation Plan
Context
Build a self-hosted personal knowledge infrastructure ("Open Brain") on a DigitalOcean VPS. Based on the guide at promptkit.natebjones.com, adapted to replace Supabase with self-hosted components running in Docker behind Caddy.
What it does: A single PostgreSQL database that any AI assistant can read from and write to via MCP (Model Context Protocol). Thoughts can also be captured and queried through a Discord bot. Every thought gets a vector embedding for
semantic search and structured metadata (type, topics, people, action items) extracted by an LLM.
Two input paths:
- Discord #capture channel — type a thought, bot ingests it
- MCP capture_thought tool — any connected AI can save a thought directly
Three output paths:
- MCP tools — AI assistants call search_thoughts, list_thoughts, thought_stats
- Discord slash commands — /brain search, /brain recent, /brain stats
- Direct SQL via SSH — admin/debug access
---
Decisions
┌──────────────────┬──────────────────────────────────────────────────────────────────────┐
│ Decision │ Choice │
├──────────────────┼──────────────────────────────────────────────────────────────────────┤
│ Database │ Existing PostgreSQL on VPS + pgvector extension │
├──────────────────┼──────────────────────────────────────────────────────────────────────┤
│ Schema │ Includes user_id column (future-proofing for multi-user) │
├──────────────────┼──────────────────────────────────────────────────────────────────────┤
│ Runtime │ Node.js / TypeScript │
├──────────────────┼──────────────────────────────────────────────────────────────────────┤
│ Deployment │ Dockerized (Dockerfile + docker-compose.yml) │
├──────────────────┼──────────────────────────────────────────────────────────────────────┤
│ Messaging │ Discord bot (new bot, existing server) with capture + query commands │
├──────────────────┼──────────────────────────────────────────────────────────────────────┤
│ AI gateway │ OpenRouter (text-embedding-3-small + gpt-4o-mini) │
├──────────────────┼──────────────────────────────────────────────────────────────────────┤
│ Routing │ Subdomain brain.option.design via host-level Caddy │
├──────────────────┼──────────────────────────────────────────────────────────────────────┤
│ Security │ 64-char hex key on MCP endpoint + Caddy rate limiting (30 req/min) │
├──────────────────┼──────────────────────────────────────────────────────────────────────┤
│ MCP write access │ Enabled — capture_thought tool included │
├──────────────────┼──────────────────────────────────────────────────────────────────────┤
│ Backups │ Not included — user will handle separately │
├──────────────────┼──────────────────────────────────────────────────────────────────────┤
│ Repo │ https://git.option.design/will/open-brain.git │
└──────────────────┴──────────────────────────────────────────────────────────────────────┘
---
Architecture
Internet (HTTPS)
|
Caddy (host-level, auto-TLS)
rate_limit: 30 req/min per IP
|
brain.option.design → localhost:3100
|
┌─────────────────────────────┐
│ Docker: open-brain │
│ │
│ Hono HTTP Server (:3100) │
│ ├── POST /mcp ─┼──→ AI clients (Claude Desktop,
│ │ (MCP StreamableHTTP) │ ChatGPT, Claude Code, Cursor)
│ │ Auth: x-brain-key │ call this endpoint over HTTPS
│ │ │
│ └── Discord.js bot ─┼──→ Discord #capture channel
│ (outbound WebSocket) │ (bot connects OUT to Discord,
│ ├── message capture │ no inbound traffic needed)
│ └── slash commands │
│ /brain search │
│ /brain recent │
│ /brain stats │
│ │
│ Shared ingest pipeline │
│ ├── getEmbedding() ─┼──→ OpenRouter API
│ └── extractMetadata() ─┼──→ OpenRouter API
└──────────────┬───────────────┘
PostgreSQL + pgvector (host)
└── brain database
└── thoughts table
How each actor accesses the system
┌───────────────────────────────────┬─────────────────────────────────┬──────────────────────────────────────────────┬──────────────────────────┐
│ Actor │ Path │ Auth │ Direction │
├───────────────────────────────────┼─────────────────────────────────┼──────────────────────────────────────────────┼──────────────────────────┤
│ Claude Desktop / ChatGPT / Cursor │ HTTPS → Caddy → :3100/mcp │ MCP key (configured once in client settings) │ Client calls your server │
├───────────────────────────────────┼─────────────────────────────────┼──────────────────────────────────────────────┼──────────────────────────┤
│ Claude Code │ Same as above │ MCP key (configured via claude mcp add) │ Client calls your server │
├───────────────────────────────────┼─────────────────────────────────┼──────────────────────────────────────────────┼──────────────────────────┤
│ Discord (you typing in #capture) │ Discord servers → bot WebSocket │ Discord login │ Bot connects outward │
├───────────────────────────────────┼─────────────────────────────────┼──────────────────────────────────────────────┼──────────────────────────┤
│ Discord slash commands │ Same WebSocket │ Discord login │ Bot connects outward │
├───────────────────────────────────┼─────────────────────────────────┼──────────────────────────────────────────────┼──────────────────────────┤
│ You via SSH │ SSH → psql │ SSH key (existing) │ Direct DB access │
└───────────────────────────────────┴─────────────────────────────────┴──────────────────────────────────────────────┴──────────────────────────┘
Note: The MCP endpoint at brain.option.design is public-facing (reachable from the internet) because AI clients like Claude Desktop and ChatGPT call it from their own servers. It is protected by a 64-character hex key over HTTPS and
rate-limited at 30 requests/minute per IP. Without the correct key, all requests are rejected with 401.
---
Implementation Steps
Step 1: PostgreSQL + pgvector
Verify pgvector is installed on the existing PostgreSQL; install if needed. Create database, user, and schema.
File: sql/schema.sql
CREATE EXTENSION IF NOT EXISTS vector;
CREATE TABLE thoughts (
id UUID DEFAULT gen_random_uuid() PRIMARY KEY,
user_id TEXT NOT NULL DEFAULT 'default',
content TEXT NOT NULL,
embedding VECTOR(1536),
metadata JSONB DEFAULT '{}'::jsonb,
source TEXT NOT NULL DEFAULT 'mcp', -- 'discord' or 'mcp'
created_at TIMESTAMPTZ DEFAULT now(),
updated_at TIMESTAMPTZ DEFAULT now()
);
CREATE INDEX ON thoughts USING hnsw (embedding vector_cosine_ops);
CREATE INDEX ON thoughts USING gin (metadata);
CREATE INDEX ON thoughts (created_at DESC);
CREATE INDEX ON thoughts (user_id);
-- Auto-update trigger for updated_at
CREATE OR REPLACE FUNCTION update_updated_at() RETURNS TRIGGER AS $$
BEGIN NEW.updated_at = now(); RETURN NEW; END;
$$ LANGUAGE plpgsql;
CREATE TRIGGER thoughts_updated_at BEFORE UPDATE ON thoughts
FOR EACH ROW EXECUTE FUNCTION update_updated_at();
-- Semantic search function
CREATE OR REPLACE FUNCTION match_thoughts(
query_embedding VECTOR(1536),
match_threshold FLOAT DEFAULT 0.7,
match_count INT DEFAULT 10,
filter JSONB DEFAULT '{}'::jsonb
) RETURNS TABLE (
id UUID, content TEXT, metadata JSONB,
similarity FLOAT, created_at TIMESTAMPTZ
) LANGUAGE plpgsql AS $$
BEGIN
RETURN QUERY
SELECT t.id, t.content, t.metadata,
1 - (t.embedding <=> query_embedding) AS similarity,
t.created_at
FROM thoughts t
WHERE 1 - (t.embedding <=> query_embedding) > match_threshold
ORDER BY t.embedding <=> query_embedding
LIMIT match_count;
END;
$$;
Deploy: SSH to VPS, run psql -d brain -f sql/schema.sql
Step 2: Node.js/TypeScript Project
Project structure:
open-brain/
├── Dockerfile
├── docker-compose.yml
├── package.json
├── tsconfig.json
├── .env.example
├── .gitignore
├── sql/
│ └── schema.sql
└── src/
├── index.ts — Hono server entry, starts HTTP + Discord bot
├── db.ts — pg client with pgvector, query helpers
├── ai.ts — OpenRouter: getEmbedding() + extractMetadata()
├── discord.ts — Discord.js bot: message capture + slash commands
├── mcp.ts — MCP server with 4 tool definitions
├── ingest.ts — Shared pipeline: embed → extract metadata → store
└── types.ts — TypeScript interfaces (Thought, Metadata)
Key dependencies:
- @modelcontextprotocol/sdk — MCP protocol server
- hono + @hono/node-server — HTTP framework on Node.js
- discord.js — Discord gateway bot
- pg + pgvector — PostgreSQL client with vector support
- zod — schema validation for MCP tool inputs
Step 3: Shared Ingest Pipeline (src/ingest.ts)
Both Discord and MCP capture_thought use the same pipeline:
Input text
→ getEmbedding(text) — OpenRouter text-embedding-3-small → 1536-dim vector
→ extractMetadata(text) — OpenRouter gpt-4o-mini → structured JSON
→ INSERT into thoughts table — content + embedding + metadata + source tag
→ Return confirmation — "Captured as [type] — [topics]"
Metadata schema extracted by LLM:
{
"type": "observation | task | idea | reference | person_note",
"topics": ["tag1", "tag2"],
"people": ["name1"],
"action_items": ["todo1"],
"dates_mentioned": ["YYYY-MM-DD"]
}
Step 4: MCP Server (src/mcp.ts)
Exposed at POST /mcp via StreamableHTTP transport. Authenticated with x-brain-key header or ?key= query param.
┌─────────────────┬───────────────────────────────────────────────────────────────────────────────┬────────────────────────────────────────────────────┐
│ Tool │ Input │ What it does │
├─────────────────┼───────────────────────────────────────────────────────────────────────────────┼────────────────────────────────────────────────────┤
│ search_thoughts │ query: string, limit?: number, threshold?: number │ Embed query → cosine similarity search in pgvector │
├─────────────────┼───────────────────────────────────────────────────────────────────────────────┼────────────────────────────────────────────────────┤
│ list_thoughts │ limit?: number, type?: string, topic?: string, person?: string, days?: number │ Filter thoughts by metadata fields, return recent │
├─────────────────┼───────────────────────────────────────────────────────────────────────────────┼────────────────────────────────────────────────────┤
│ thought_stats │ (none) │ Aggregate counts by type, topic, recent activity │
├─────────────────┼───────────────────────────────────────────────────────────────────────────────┼────────────────────────────────────────────────────┤
│ capture_thought │ content: string │ Run full ingest pipeline, return confirmation │
└─────────────────┴───────────────────────────────────────────────────────────────────────────────┴────────────────────────────────────────────────────┘
Each tool is defined with Zod schemas and registered on the MCP server. The AI client discovers them automatically on connection.
Step 5: Discord Bot (src/discord.ts)
Setup (manual, one-time):
1. Create Discord Application at discord.com/developers/applications
2. Create Bot user, enable MESSAGE CONTENT privileged intent
3. Generate and copy bot token → goes in .env
4. Invite to server with permissions: Read/Send Messages, Read Message History, Use Slash Commands
5. Designate #capture channel, copy channel ID → goes in .env
Message capture behavior:
- Listens for messages in configured channel only
- Ignores bot messages and system messages
- Runs ingest pipeline on valid messages
- Replies with: Captured as [type] — [topic1], [topic2]
Slash commands:
- /brain search <query> — semantic search, returns top results
- /brain recent [count] — list recent thoughts
- /brain stats — show aggregate stats
Step 6: OpenRouter Integration (src/ai.ts)
Two API calls to https://openrouter.ai/api/v1/:
- getEmbedding(text): POST /embeddings, model text-embedding-3-small → returns 1536-dim float array
- extractMetadata(text): POST /chat/completions, model gpt-4o-mini, system prompt requesting JSON matching the metadata schema above
Estimated cost: ~$0.100.30/month at 20 thoughts/day.
Step 7: Docker Setup
Dockerfile — Multi-stage: Node.js 22 Alpine, install deps, compile TypeScript, run compiled JS in slim image.
docker-compose.yml:
services:
open-brain:
build: .
container_name: open-brain
restart: unless-stopped
ports:
- "3100:3100"
env_file: .env
extra_hosts:
- "host.docker.internal:host-gateway"
host.docker.internal lets the container reach the host's PostgreSQL. May require updating pg_hba.conf to allow connections from Docker's bridge subnet (typically 172.17.0.0/16).
Step 8: Caddy Configuration
Add to existing Caddyfile on the VPS:
brain.option.design {
rate_limit {remote.host} 30r/m
reverse_proxy localhost:3100
}
DNS: Add A record for brain.option.design → VPS IP. Caddy auto-provisions TLS certificate.
Note: Caddy's rate limiting requires the caddy-ratelimit plugin. If not available, we can implement rate limiting in the Node.js app instead (simpler, no Caddy plugin needed).
Step 9: AI Client Configuration
MCP URL: https://brain.option.design/mcp
┌────────────────┬───────────────────────────────────────────────────────────────────────────────────────────────────────────────┐
│ Client │ How to connect │
├────────────────┼───────────────────────────────────────────────────────────────────────────────────────────────────────────────┤
│ Claude Desktop │ Settings → Connectors → Add remote MCP server → paste URL with ?key=ACCESS_KEY │
├────────────────┼───────────────────────────────────────────────────────────────────────────────────────────────────────────────┤
│ Claude Code │ claude mcp add --transport http open-brain https://brain.option.design/mcp --header "x-brain-key: ACCESS_KEY" │
├────────────────┼───────────────────────────────────────────────────────────────────────────────────────────────────────────────┤
│ ChatGPT │ Developer Mode → Apps & Connectors → Create → paste URL with ?key=ACCESS_KEY │
├────────────────┼───────────────────────────────────────────────────────────────────────────────────────────────────────────────┤
│ Cursor │ Add to .cursor/mcp.json with URL and key header │
└────────────────┴───────────────────────────────────────────────────────────────────────────────────────────────────────────────┘
---
Environment Variables (.env)
# Database (host.docker.internal = host machine from inside Docker)
DATABASE_URL=postgresql://brain_user:password@host.docker.internal:5432/brain
# OpenRouter (AI gateway for embeddings + metadata extraction)
OPENROUTER_API_KEY=sk-or-...
# Discord bot
DISCORD_BOT_TOKEN=...
DISCORD_CAPTURE_CHANNEL_ID=...
# MCP endpoint authentication (generate with: openssl rand -hex 32)
MCP_ACCESS_KEY=...
# Server port
PORT=3100
---
Verification
1. Database: SSH to VPS → psql -d brain -c "SELECT count(*) FROM thoughts;" → returns 0
2. Discord capture: Send "Sarah is thinking about leaving her job to start consulting" in #capture → bot replies: Captured as person_note — career, consulting
3. Discord query: Type /brain search career → bot returns the thought about Sarah
4. Discord stats: Type /brain stats → bot shows 1 thought, type: person_note
5. MCP capture: In Claude Code, say "Remember that I prefer dark mode in all apps" → thought stored in DB
6. MCP search: Ask Claude "What do you know about my preferences?" → returns the dark mode thought
7. MCP list: Ask Claude "Show me recent thoughts" → returns both thoughts
8. Rate limit: Rapid-fire 30+ requests → subsequent requests get throttled
---
Current Status as of 3/6/2026 2:51:00 PM CST
---
● The project is fully scaffolded and compiles cleanly. Here's a summary of what was built:
Files Created
┌────────────────────┬─────────────────────────────────────────────────────────────────────┐
│ File │ Purpose │
├────────────────────┼─────────────────────────────────────────────────────────────────────┤
│ sql/schema.sql │ PostgreSQL schema with pgvector, match_thoughts() function, indexes │
├────────────────────┼─────────────────────────────────────────────────────────────────────┤
│ src/types.ts │ TypeScript interfaces for Thought, ThoughtMetadata, etc. │
├────────────────────┼─────────────────────────────────────────────────────────────────────┤
│ src/db.ts │ PostgreSQL client — insert, search, list, stats queries │
├────────────────────┼─────────────────────────────────────────────────────────────────────┤
│ src/ai.ts │ OpenRouter API — getEmbedding() + extractMetadata() │
├────────────────────┼─────────────────────────────────────────────────────────────────────┤
│ src/ingest.ts │ Shared ingest pipeline — embed + extract + store │
├────────────────────┼─────────────────────────────────────────────────────────────────────┤
│ src/mcp.ts │ MCP server with 4 tools (search, list, stats, capture) │
├────────────────────┼─────────────────────────────────────────────────────────────────────┤
│ src/discord.ts │ Discord bot — message capture + /brain slash commands │
├────────────────────┼─────────────────────────────────────────────────────────────────────┤
│ src/index.ts │ Hono HTTP server entry point, MCP auth, starts Discord bot │
├────────────────────┼─────────────────────────────────────────────────────────────────────┤
│ Dockerfile │ Multi-stage Docker build (Node 22 Alpine) │
├────────────────────┼─────────────────────────────────────────────────────────────────────┤
│ docker-compose.yml │ Container config with host.docker.internal for PostgreSQL │
├────────────────────┼─────────────────────────────────────────────────────────────────────┤
│ .env.example │ Template for environment variables │
├────────────────────┼─────────────────────────────────────────────────────────────────────┤
│ .gitignore │ Excludes node_modules, dist, .env │
└────────────────────┴─────────────────────────────────────────────────────────────────────┘
Next Steps (on your VPS)
1. Create Discord bot at discord.com/developers — get bot token, enable MESSAGE CONTENT intent, invite to server
2. Create .env from .env.example with your real credentials
3. Run schema on PostgreSQL: psql -d brain -f sql/schema.sql (ensure pgvector extension is available)
4. Add DNS A record for brain.option.design → VPS IP
5. Add Caddy block for brain.option.design → localhost:3100
6. Deploy: docker compose up -d --build
7. Connect AI clients using the MCP URL
Want me to commit this to the repo, or would you like to review anything first?

58
sql/schema.sql Normal file
View File

@@ -0,0 +1,58 @@
CREATE EXTENSION IF NOT EXISTS vector;
CREATE TABLE IF NOT EXISTS thoughts (
id UUID DEFAULT gen_random_uuid() PRIMARY KEY,
user_id TEXT NOT NULL DEFAULT 'default',
content TEXT NOT NULL,
embedding VECTOR(1536),
metadata JSONB DEFAULT '{}'::jsonb,
source TEXT NOT NULL DEFAULT 'mcp',
created_at TIMESTAMPTZ DEFAULT now(),
updated_at TIMESTAMPTZ DEFAULT now()
);
CREATE INDEX IF NOT EXISTS thoughts_embedding_idx ON thoughts USING hnsw (embedding vector_cosine_ops);
CREATE INDEX IF NOT EXISTS thoughts_metadata_idx ON thoughts USING gin (metadata);
CREATE INDEX IF NOT EXISTS thoughts_created_at_idx ON thoughts (created_at DESC);
CREATE INDEX IF NOT EXISTS thoughts_user_id_idx ON thoughts (user_id);
-- Auto-update trigger for updated_at
CREATE OR REPLACE FUNCTION update_updated_at() RETURNS TRIGGER AS $$
BEGIN
NEW.updated_at = now();
RETURN NEW;
END;
$$ LANGUAGE plpgsql;
DROP TRIGGER IF EXISTS thoughts_updated_at ON thoughts;
CREATE TRIGGER thoughts_updated_at
BEFORE UPDATE ON thoughts
FOR EACH ROW EXECUTE FUNCTION update_updated_at();
-- Semantic search function
CREATE OR REPLACE FUNCTION match_thoughts(
query_embedding VECTOR(1536),
match_threshold FLOAT DEFAULT 0.7,
match_count INT DEFAULT 10,
filter JSONB DEFAULT '{}'::jsonb
) RETURNS TABLE (
id UUID,
content TEXT,
metadata JSONB,
similarity FLOAT,
created_at TIMESTAMPTZ
) LANGUAGE plpgsql AS $$
BEGIN
RETURN QUERY
SELECT
t.id,
t.content,
t.metadata,
(1 - (t.embedding <=> query_embedding))::FLOAT AS similarity,
t.created_at
FROM thoughts t
WHERE 1 - (t.embedding <=> query_embedding) > match_threshold
ORDER BY t.embedding <=> query_embedding
LIMIT match_count;
END;
$$;

85
src/ai.ts Normal file
View File

@@ -0,0 +1,85 @@
import { ThoughtMetadata } from "./types";
const OPENROUTER_URL = "https://openrouter.ai/api/v1";
function getApiKey(): string {
const key = process.env.OPENROUTER_API_KEY;
if (!key) throw new Error("OPENROUTER_API_KEY not set");
return key;
}
export async function getEmbedding(text: string): Promise<number[]> {
const res = await fetch(`${OPENROUTER_URL}/embeddings`, {
method: "POST",
headers: {
Authorization: `Bearer ${getApiKey()}`,
"Content-Type": "application/json",
},
body: JSON.stringify({
model: "openai/text-embedding-3-small",
input: text,
}),
});
if (!res.ok) {
const err = await res.text();
throw new Error(`OpenRouter embedding error (${res.status}): ${err}`);
}
const data: any = await res.json();
return data.data[0].embedding;
}
const METADATA_SYSTEM_PROMPT = `You are a metadata extraction engine. Given a thought or note, extract structured metadata as JSON.
Return ONLY valid JSON matching this schema:
{
"type": one of "observation", "task", "idea", "reference", "person_note",
"topics": array of 1-4 short topic tags,
"people": array of people mentioned (empty if none),
"action_items": array of action items (empty if none),
"dates_mentioned": array of dates in YYYY-MM-DD format (empty if none)
}
Choose the most appropriate type:
- observation: general notes, things noticed
- task: something to do, reminders
- idea: creative thoughts, possibilities
- reference: facts, links, technical info
- person_note: notes about a specific person`;
export async function extractMetadata(text: string): Promise<ThoughtMetadata> {
const res = await fetch(`${OPENROUTER_URL}/chat/completions`, {
method: "POST",
headers: {
Authorization: `Bearer ${getApiKey()}`,
"Content-Type": "application/json",
},
body: JSON.stringify({
model: "openai/gpt-4o-mini",
messages: [
{ role: "system", content: METADATA_SYSTEM_PROMPT },
{ role: "user", content: text },
],
response_format: { type: "json_object" },
temperature: 0,
}),
});
if (!res.ok) {
const err = await res.text();
throw new Error(`OpenRouter metadata error (${res.status}): ${err}`);
}
const data: any = await res.json();
const content = data.choices[0].message.content;
const parsed = JSON.parse(content);
return {
type: parsed.type || "observation",
topics: parsed.topics || [],
people: parsed.people || [],
action_items: parsed.action_items || [],
dates_mentioned: parsed.dates_mentioned || [],
};
}

125
src/db.ts Normal file
View File

@@ -0,0 +1,125 @@
import { Pool } from "pg";
import pgvector from "pgvector/pg";
import { ThoughtMetadata, ThoughtMatch, Thought } from "./types";
const pool = new Pool({
connectionString: process.env.DATABASE_URL,
});
pool.on("connect", async (client) => {
await pgvector.registerTypes(client);
});
export async function insertThought(
content: string,
embedding: number[],
metadata: ThoughtMetadata,
source: "discord" | "mcp"
): Promise<string> {
const result = await pool.query(
`INSERT INTO thoughts (content, embedding, metadata, source)
VALUES ($1, $2, $3, $4)
RETURNING id`,
[content, pgvector.toSql(embedding), JSON.stringify(metadata), source]
);
return result.rows[0].id;
}
export async function searchThoughts(
embedding: number[],
limit: number = 10,
threshold: number = 0.7
): Promise<ThoughtMatch[]> {
const result = await pool.query(
`SELECT * FROM match_thoughts($1, $2, $3)`,
[pgvector.toSql(embedding), threshold, limit]
);
return result.rows;
}
export async function listThoughts(options: {
limit?: number;
type?: string;
topic?: string;
person?: string;
days?: number;
}): Promise<Thought[]> {
const conditions: string[] = [];
const params: unknown[] = [];
let paramIndex = 1;
if (options.type) {
conditions.push(`metadata->>'type' = $${paramIndex++}`);
params.push(options.type);
}
if (options.topic) {
conditions.push(`metadata->'topics' ? $${paramIndex++}`);
params.push(options.topic);
}
if (options.person) {
conditions.push(`metadata->'people' ? $${paramIndex++}`);
params.push(options.person);
}
if (options.days) {
conditions.push(`created_at > now() - interval '${Number(options.days)} days'`);
}
const where = conditions.length > 0 ? `WHERE ${conditions.join(" AND ")}` : "";
const limit = Math.min(options.limit || 20, 100);
const result = await pool.query(
`SELECT id, user_id, content, metadata, source, created_at, updated_at
FROM thoughts ${where}
ORDER BY created_at DESC
LIMIT ${limit}`,
params
);
return result.rows;
}
export async function getThoughtStats(): Promise<{
total: number;
by_type: Record<string, number>;
by_source: Record<string, number>;
recent_topics: string[];
last_captured: Date | null;
}> {
const [totalRes, typeRes, sourceRes, topicsRes, lastRes] = await Promise.all([
pool.query(`SELECT count(*)::int AS total FROM thoughts`),
pool.query(
`SELECT metadata->>'type' AS type, count(*)::int AS count
FROM thoughts GROUP BY metadata->>'type' ORDER BY count DESC`
),
pool.query(
`SELECT source, count(*)::int AS count
FROM thoughts GROUP BY source ORDER BY count DESC`
),
pool.query(
`SELECT DISTINCT jsonb_array_elements_text(metadata->'topics') AS topic
FROM thoughts
WHERE created_at > now() - interval '7 days'
LIMIT 20`
),
pool.query(
`SELECT created_at FROM thoughts ORDER BY created_at DESC LIMIT 1`
),
]);
const by_type: Record<string, number> = {};
for (const row of typeRes.rows) {
if (row.type) by_type[row.type] = row.count;
}
const by_source: Record<string, number> = {};
for (const row of sourceRes.rows) {
by_source[row.source] = row.count;
}
return {
total: totalRes.rows[0].total,
by_type,
by_source,
recent_topics: topicsRes.rows.map((r) => r.topic),
last_captured: lastRes.rows[0]?.created_at || null,
};
}

177
src/discord.ts Normal file
View File

@@ -0,0 +1,177 @@
import {
Client,
GatewayIntentBits,
Events,
REST,
Routes,
SlashCommandBuilder,
ChatInputCommandInteraction,
Message,
} from "discord.js";
import { ingestThought, formatIngestResult } from "./ingest";
import { searchThoughts, listThoughts, getThoughtStats } from "./db";
import { getEmbedding } from "./ai";
import { ThoughtMatch, Thought } from "./types";
const CAPTURE_CHANNEL_ID = process.env.DISCORD_CAPTURE_CHANNEL_ID || "";
const commands = [
new SlashCommandBuilder()
.setName("brain")
.setDescription("Interact with your Open Brain")
.addSubcommand((sub) =>
sub
.setName("search")
.setDescription("Search your brain semantically")
.addStringOption((opt) =>
opt.setName("query").setDescription("What to search for").setRequired(true)
)
)
.addSubcommand((sub) =>
sub
.setName("recent")
.setDescription("List recent thoughts")
.addIntegerOption((opt) =>
opt.setName("count").setDescription("Number of thoughts (default 10)").setRequired(false)
)
)
.addSubcommand((sub) =>
sub.setName("stats").setDescription("Show brain statistics")
),
];
async function registerSlashCommands(token: string, clientId: string) {
const rest = new REST({ version: "10" }).setToken(token);
await rest.put(Routes.applicationCommands(clientId), {
body: commands.map((c) => c.toJSON()),
});
console.log("[discord] Slash commands registered globally");
}
async function handleSearch(interaction: ChatInputCommandInteraction) {
await interaction.deferReply();
const query = interaction.options.getString("query", true);
const embedding = await getEmbedding(query);
const results = await searchThoughts(embedding, 5, 0.7);
if (results.length === 0) {
await interaction.editReply("No matching thoughts found.");
return;
}
const text = results
.map((r: ThoughtMatch, i: number) => {
const date = new Date(r.created_at).toLocaleDateString();
return `**${i + 1}.** [${r.metadata.type}] ${r.content}\n> Topics: ${r.metadata.topics.join(", ") || "none"} | ${(r.similarity * 100).toFixed(0)}% match | ${date}`;
})
.join("\n\n");
await interaction.editReply(text.slice(0, 2000));
}
async function handleRecent(interaction: ChatInputCommandInteraction) {
await interaction.deferReply();
const count = interaction.options.getInteger("count") || 10;
const results = await listThoughts({ limit: count });
if (results.length === 0) {
await interaction.editReply("No thoughts captured yet.");
return;
}
const text = results
.map((r: Thought, i: number) => {
const date = new Date(r.created_at).toLocaleDateString();
return `**${i + 1}.** [${r.metadata.type}] ${r.content}\n> ${r.metadata.topics.join(", ") || "no topics"} | ${r.source} | ${date}`;
})
.join("\n\n");
await interaction.editReply(text.slice(0, 2000));
}
async function handleStats(interaction: ChatInputCommandInteraction) {
await interaction.deferReply();
const stats = await getThoughtStats();
const typeLines = Object.entries(stats.by_type)
.map(([type, count]) => ` ${type}: ${count}`)
.join("\n");
const text = [
`**Total thoughts:** ${stats.total}`,
"",
"**By type:**",
typeLines || " (none)",
"",
`**Recent topics (7 days):** ${stats.recent_topics.join(", ") || "(none)"}`,
"",
`**Last captured:** ${stats.last_captured ? new Date(stats.last_captured).toLocaleString() : "(never)"}`,
].join("\n");
await interaction.editReply(text);
}
async function handleMessage(message: Message) {
if (message.author.bot) return;
if (message.channel.id !== CAPTURE_CHANNEL_ID) return;
if (!message.content.trim()) return;
try {
const result = await ingestThought(message.content, "discord");
await message.reply(formatIngestResult(result));
} catch (err) {
console.error("[discord] Ingest error:", err);
await message.reply("Failed to capture thought. Check server logs.");
}
}
export async function startDiscordBot(): Promise<Client> {
const token = process.env.DISCORD_BOT_TOKEN;
if (!token) throw new Error("DISCORD_BOT_TOKEN not set");
if (!CAPTURE_CHANNEL_ID) throw new Error("DISCORD_CAPTURE_CHANNEL_ID not set");
const client = new Client({
intents: [
GatewayIntentBits.Guilds,
GatewayIntentBits.GuildMessages,
GatewayIntentBits.MessageContent,
],
});
client.once(Events.ClientReady, async (c) => {
console.log(`[discord] Bot ready as ${c.user.tag}`);
await registerSlashCommands(token, c.user.id);
});
client.on(Events.MessageCreate, handleMessage);
client.on(Events.InteractionCreate, async (interaction) => {
if (!interaction.isChatInputCommand()) return;
if (interaction.commandName !== "brain") return;
try {
const sub = interaction.options.getSubcommand();
switch (sub) {
case "search":
await handleSearch(interaction);
break;
case "recent":
await handleRecent(interaction);
break;
case "stats":
await handleStats(interaction);
break;
}
} catch (err) {
console.error("[discord] Command error:", err);
const reply = interaction.deferred
? interaction.editReply("An error occurred.")
: interaction.reply("An error occurred.");
await reply;
}
});
await client.login(token);
return client;
}

62
src/index.ts Normal file
View File

@@ -0,0 +1,62 @@
import { serve } from "@hono/node-server";
import { Hono } from "hono";
import { WebStandardStreamableHTTPServerTransport } from "@modelcontextprotocol/sdk/server/webStandardStreamableHttp.js";
import { createMcpServer } from "./mcp";
import { startDiscordBot } from "./discord";
const app = new Hono();
const PORT = parseInt(process.env.PORT || "3100", 10);
const MCP_ACCESS_KEY = process.env.MCP_ACCESS_KEY || "";
function authenticate(req: Request): boolean {
if (!MCP_ACCESS_KEY) return false;
const headerKey = req.headers.get("x-brain-key");
if (headerKey === MCP_ACCESS_KEY) return true;
const url = new URL(req.url);
const paramKey = url.searchParams.get("key");
return paramKey === MCP_ACCESS_KEY;
}
// Health check
app.get("/", (c) => c.json({ status: "ok", service: "open-brain" }));
// MCP endpoint — stateless: new transport per request, connect server, handle, close
app.all("/mcp", async (c) => {
if (!authenticate(c.req.raw)) {
return c.json({ error: "Unauthorized" }, 401);
}
const server = createMcpServer();
const transport = new WebStandardStreamableHTTPServerTransport({
sessionIdGenerator: undefined,
});
await server.connect(transport);
try {
return await transport.handleRequest(c.req.raw);
} finally {
await server.close();
}
});
// Start everything
async function main() {
if (!MCP_ACCESS_KEY) {
console.error("MCP_ACCESS_KEY is not set. Generate one with: openssl rand -hex 32");
process.exit(1);
}
serve({ fetch: app.fetch, port: PORT }, () => {
console.log(`[server] Open Brain listening on port ${PORT}`);
});
try {
await startDiscordBot();
} catch (err) {
console.error("[discord] Failed to start bot:", err);
console.error("[discord] The MCP server will continue running without Discord.");
}
}
main();

37
src/ingest.ts Normal file
View File

@@ -0,0 +1,37 @@
import { getEmbedding, extractMetadata } from "./ai";
import { insertThought } from "./db";
import { IngestResult } from "./types";
export async function ingestThought(
content: string,
source: "discord" | "mcp"
): Promise<IngestResult> {
const [embedding, metadata] = await Promise.all([
getEmbedding(content),
extractMetadata(content),
]);
const id = await insertThought(content, embedding, metadata, source);
return {
id,
type: metadata.type,
topics: metadata.topics,
people: metadata.people,
action_items: metadata.action_items,
};
}
export function formatIngestResult(result: IngestResult): string {
let msg = `Captured as ${result.type}`;
if (result.topics.length > 0) {
msg += `${result.topics.join(", ")}`;
}
if (result.people.length > 0) {
msg += `\nPeople: ${result.people.join(", ")}`;
}
if (result.action_items.length > 0) {
msg += `\nAction items: ${result.action_items.join(", ")}`;
}
return msg;
}

109
src/mcp.ts Normal file
View File

@@ -0,0 +1,109 @@
import { McpServer } from "@modelcontextprotocol/sdk/server/mcp.js";
import { z } from "zod";
import { searchThoughts, listThoughts, getThoughtStats } from "./db";
import { getEmbedding } from "./ai";
import { ingestThought, formatIngestResult } from "./ingest";
import { ThoughtMatch, Thought } from "./types";
export function createMcpServer(): McpServer {
const server = new McpServer({
name: "open-brain",
version: "1.0.0",
});
server.tool(
"search_thoughts",
"Search your brain using semantic similarity. Use this when looking for specific topics, people, or concepts.",
{
query: z.string().describe("What to search for"),
limit: z.number().optional().default(10).describe("Max results (default 10)"),
threshold: z.number().optional().default(0.7).describe("Similarity threshold 0-1 (default 0.7)"),
},
async ({ query, limit, threshold }) => {
const embedding = await getEmbedding(query);
const results = await searchThoughts(embedding, limit, threshold);
if (results.length === 0) {
return { content: [{ type: "text" as const, text: "No matching thoughts found." }] };
}
const text = results
.map((r: ThoughtMatch, i: number) => {
const date = new Date(r.created_at).toLocaleDateString();
const meta = r.metadata;
return `${i + 1}. [${meta.type}] ${r.content}\n Topics: ${meta.topics.join(", ") || "none"} | Similarity: ${(r.similarity * 100).toFixed(0)}% | ${date}`;
})
.join("\n\n");
return { content: [{ type: "text" as const, text }] };
}
);
server.tool(
"list_thoughts",
"List recent thoughts with optional filters. Use this to browse or filter by type, topic, person, or time range.",
{
limit: z.number().optional().default(20).describe("Max results (default 20)"),
type: z.string().optional().describe("Filter by type: observation, task, idea, reference, person_note"),
topic: z.string().optional().describe("Filter by topic tag"),
person: z.string().optional().describe("Filter by person name"),
days: z.number().optional().describe("Only thoughts from the last N days"),
},
async ({ limit, type, topic, person, days }) => {
const results = await listThoughts({ limit, type, topic, person, days });
if (results.length === 0) {
return { content: [{ type: "text" as const, text: "No thoughts found matching those filters." }] };
}
const text = results
.map((r: Thought, i: number) => {
const date = new Date(r.created_at).toLocaleDateString();
const meta = r.metadata;
return `${i + 1}. [${meta.type}] ${r.content}\n Topics: ${meta.topics.join(", ") || "none"} | Source: ${r.source} | ${date}`;
})
.join("\n\n");
return { content: [{ type: "text" as const, text: `${results.length} thoughts:\n\n${text}` }] };
}
);
server.tool(
"thought_stats",
"Get aggregate statistics about your brain: total thoughts, breakdown by type, recent topics, and more.",
{},
async () => {
const stats = await getThoughtStats();
const typeBreakdown = Object.entries(stats.by_type)
.map(([type, count]) => ` ${type}: ${count}`)
.join("\n");
const sourceBreakdown = Object.entries(stats.by_source)
.map(([source, count]) => ` ${source}: ${count}`)
.join("\n");
const text = [
`Total thoughts: ${stats.total}`,
"",
"By type:",
typeBreakdown || " (none)",
"",
"By source:",
sourceBreakdown || " (none)",
"",
`Recent topics (7 days): ${stats.recent_topics.join(", ") || "(none)"}`,
"",
`Last captured: ${stats.last_captured ? new Date(stats.last_captured).toLocaleString() : "(never)"}`,
].join("\n");
return { content: [{ type: "text" as const, text }] };
}
);
server.tool(
"capture_thought",
"Save a new thought to the brain. Use this when the user wants to remember something, save a note, or store information for later.",
{
content: z.string().describe("The thought or note to capture"),
},
async ({ content }) => {
const result = await ingestThought(content, "mcp");
return {
content: [{ type: "text" as const, text: formatIngestResult(result) }],
};
}
);
return server;
}

34
src/types.ts Normal file
View File

@@ -0,0 +1,34 @@
export interface ThoughtMetadata {
type: "observation" | "task" | "idea" | "reference" | "person_note";
topics: string[];
people: string[];
action_items: string[];
dates_mentioned: string[];
}
export interface Thought {
id: string;
user_id: string;
content: string;
embedding: number[] | null;
metadata: ThoughtMetadata;
source: "discord" | "mcp";
created_at: Date;
updated_at: Date;
}
export interface ThoughtMatch {
id: string;
content: string;
metadata: ThoughtMetadata;
similarity: number;
created_at: Date;
}
export interface IngestResult {
id: string;
type: string;
topics: string[];
people: string[];
action_items: string[];
}

19
tsconfig.json Normal file
View File

@@ -0,0 +1,19 @@
{
"compilerOptions": {
"target": "ES2022",
"module": "commonjs",
"lib": ["ES2022"],
"outDir": "./dist",
"rootDir": "./src",
"strict": true,
"esModuleInterop": true,
"skipLibCheck": true,
"forceConsistentCasingInFileNames": true,
"resolveJsonModule": true,
"declaration": true,
"declarationMap": true,
"sourceMap": true
},
"include": ["src/**/*"],
"exclude": ["node_modules", "dist"]
}