Run Locally

• AgentOS on FastAPI
• Postgres + pgvector

​

Prerequisites

• Docker Desktop installed and running
• An OpenAI API key for models and embeddings

​

Run your agent platform

1

Clone the template

git clone https://github.com/agno-agi/agentos-railway.git agent-platform
cd agent-platform

Make the codebase yours by pushing it to a repository you own. To start with a clean Git history, run these commands inside the cloned agent-platform directory:

rm -rf .git
git init
git add .
git commit -m "Initial commit"
git branch -M main
git remote add origin https://github.com/your-org/your-repo.git
git push -u origin main

rm -rf .git removes the template’s Git history. Replace the repository URL before running the final two commands.

2

Configure your environment

cp example.env .env

Open .env and set OPENAI_API_KEY. Everything else has sensible defaults.

3

Start the platform

docker compose up -d --build

This runs two containers: a FastAPI app on port 8000 and a Postgres database on port 5432. The first build takes a few minutes.

4

Verify it's running

Open http://localhost:8000/docs.You’ll see the OpenAPI spec: every agent action exposed as a REST endpoint.

5

Verify the MCP interface

./scripts/mcp_check.sh

This checks the MCP handshake, tool discovery, and one agent run against the local platform.

​

Connect the AgentOS UI

1. Open os.agno.com and sign in.
2. Click Connect OS, enter http://localhost:8000 as the URL, and name it Local AgentOS.
3. Click Connect.

“Build an agent that tracks AI news and writes a daily brief” → Agent Builder creates the agent through AgentOS Studio.

“How healthy is the platform?” → Platform Manager answers from eval history, deployment checks, and schedules.

“What did Anthropic publish about agents recently?” → WebSearch returns a summary with citations.

​

Summary

​

Next