← All articlesPublished on March 23, 2026• Written byGenthropic

Build a Personal Brain: Set up your personal AI agent + brain from zero

Build a Personal Brain

Set up a private personal knowledge brain for yourself using ModusBrain and Genthropic infrastructure.

Tutorial: Set up your personal AI agent + brain from zero

By the end of this tutorial, you'll have your own AI agent running on a server you control, talking to you over Telegram, with a brain that remembers everything you tell it. About two hours end-to-end, $100 to $150 a month sustained.

This is the install I'd run if I were setting up the whole stack from scratch today.

"This is the Apple I, we're just soldering breadboards over here."

If you only want the brain layer (no agent, no Telegram, just ModusBrain as memory for an MCP client you already use), you can run ModusBrain in CLI standalone mode. If you want the whole agent shared with a team, set it up as a company brain. This tutorial is the solo, full-stack, talk-to-it-on-Telegram path.

What you're building

A personal AI agent with four core pieces:

• A brain (git repo). Your knowledge base, constantly ingesting and growing.
• A harness (OpenClaw via AlphaClaw). The runtime that gives the LLM tools, memory, and integrations.
• A chat interface (Telegram). How you talk to it.
• Skills (60+ installed via ModusBrain). Reusable capabilities the agent can invoke.

Architecture:

Telegram → AlphaClaw (harness) → OpenClaw (agent) → ModusBrain (knowledge/skills) → Supabase (embeddings/search)

The Git repo is the system of record. The whole thing is multiplayer by default: any agent that hooks into the repo works. Conflicts resolve through git.

Prerequisites

Step 1: Create two GitHub repos

You need two repos, not one.

1. Workspace repo. Agent configuration, skills, memory, crons. Example name: your-org/myagent. Private.
2. Brain repo. Knowledge base, people pages, meeting notes, all the content the agent reads and writes. Example name: your-org/myagent-brain. Private.

Both repos start empty. ModusBrain will populate the brain repo with its default structure on first install.

Step 2: Generate a fine-grained Personal Access Token

GitHub → Settings → Developer Settings → Personal Access Tokens → Fine-grained tokens.

• Name: myagent-token
• Expiration: 1 year
• Repository access: select both repos only
• Permissions: Read AND Write access to both repos (Contents, Metadata, Pull requests)

Save this token. You'll need it for the harness setup.

Step 3: Create a Telegram bot

1. Open Telegram, message @BotFather
2. Send /newbot
3. Name your bot
4. Get the bot token and save it.

Step 4: Deploy via AlphaClaw on Render

AlphaClaw is the setup harness that manages OpenClaw deployment.

1. Go to your deployment dashboard
2. Enter your workspace repo: your-org/myagent
3. Select "Use existing" if the repo already exists
4. Enter your GitHub PAT from Step 2
5. Enter your Telegram bot token from Step 3
6. Deploy

Render will build a Docker container with the harness. First deploy takes about 5 minutes.

Step 5: Add provider API keys

In the Providers settings:

• OpenAI API Key. Required for embeddings.
• Anthropic API Key. Required for Claude (main conversational model).
• Perplexity API Key. Optional, for web search.
• ZeroEntropy API Key. Recommended. ModusBrain ships with ZeroEntropy as the default embedder + reranker.

Step 6: Install ModusBrain

Once the agent runtime is active:

modusbrain install

This installs:

• About 60 skills
• About 9 skill packs
• Default brain structure
• MCP server configuration
• Supabase connection (for embeddings and search)

ModusBrain populates the brain repo with its default directory structure, skill files, and configuration.

Step 7: Set up Supabase (embeddings and search)

ModusBrain uses Supabase for vector embeddings and full-text search at scale.

7a. Enable pgvector

1. Create a Supabase project.
2. In the Supabase dashboard, go to Database → Extensions.
3. Toggle vector (pgvector extension) on.

7b. Use the Transaction Pooler Connection String

Configure the connection string in ModusBrain:

modusbrain config set database_url "postgresql://postgres.YOUR-PROJECT:YOUR-PASSWORD@aws-0-us-west-1.pooler.supabase.com:6543/postgres"

7c. Verify the connection

modusbrain doctor

Green checks will confirm schema, connectivity, pgvector extension, and embedding provider status.

Step 8: Verify and chat

1. Open Telegram
2. Message your bot
3. It will respond using OpenClaw + ModusBrain!

What you built

You now have a personal AI agent running on cloud infrastructure, talking to you on Telegram, with a ModusBrain memory that ingests and remembers everything you tell it. Every conversation gets indexed, every new entity gets its own page, and the overnight enrichment daemon dedupes and consolidates while you sleep.