AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.
AutoGPT Platform
Welcome to the AutoGPT Platform - a powerful system for creating and running AI agents to solve business problems. This platform enables you to harness the power of artificial intelligence to automate tasks, analyze data, and generate insights for your organization.
Just want to run AutoGPT? The quickest way is the single-container image on Docker Hub,
significantgravitas/autogpt. See the self-hosting guide. The steps below build and run every service from this checkout with Docker Compose.
Getting Started
Prerequisites
- Docker
- Docker Compose V2 (comes with Docker Desktop, or can be installed separately)
makeand Python 3 (used to generate your local secrets)
Running the System
To run the AutoGPT Platform, follow these steps:
Clone this repository to your local machine and navigate to the
autogpt_platformdirectory within the repository:git clone https://github.com/Significant-Gravitas/AutoGPT.git cd AutoGPT/autogpt_platformRun the following command:
make init-envThis command copies each
.env.defaultfile to.env(inautogpt_platform,backendandfrontend) where no.envexists yet, and generates the secrets those files leave blank:ENCRYPTION_KEY,UNSUBSCRIBE_SECRET_KEY,INTERNAL_API_KEYandBETTER_AUTH_SECRET. The backend refuses to start withoutENCRYPTION_KEY. It never overwrites an existing file or value, so it is safe to re-run. You can then modify the.envfiles to add your own environment variables.Without
make, runinstaller/setup-autogpt.sh(Linux/macOS) orinstaller\setup-autogpt.bat(Windows) instead. They do the same and then start the services.Run the following command:
docker compose up -dThis command will start all the necessary backend services defined in the
docker-compose.ymlfile in detached mode.After all the services are in ready state, open your browser and navigate to
http://localhost:3000to access the AutoGPT Platform frontend.
Running Just Core services
You can now run the following to enable just the core services.
# For help
make help
# Run the services the backend needs (Postgres, Redis, RabbitMQ, ClamAV, FalkorDB) and apply migrations
make start-core
# Stop every running service in the stack
make stop-core
# View logs from core services
make logs-core
# Run formatting and linting for backend and frontend
make format
# Run migrations for backend database
make migrate
# Run backend server
make run-backend
# Run frontend development server
make run-frontend
Docker Compose Commands
Here are some useful Docker Compose commands for managing your AutoGPT Platform:
docker compose up -d: Start the services in detached mode.docker compose stop: Stop the running services without removing them.docker compose rm: Remove stopped service containers.docker compose build: Build or rebuild services.docker compose down: Stop and remove containers and networks. Add-vto also delete the named volumes (workspace files, marketplace media, FalkorDB memory, and the ClamAV database); the database indata/db/datasurvives both.docker compose watch: Watch for changes in your services and automatically update them.
Sample Scenarios
Here are some common scenarios where you might use multiple Docker Compose commands:
Updating and restarting a specific service:
docker compose build rest_server docker compose up -d --no-deps rest_serverThis rebuilds the
rest_serverservice and restarts it without affecting other services.Viewing logs for troubleshooting:
docker compose logs -f rest_server websocket_serverThis shows and follows the logs for both
rest_serverandwebsocket_serverservices.Stopping the entire system for maintenance:
docker compose stop docker compose rm -f docker compose pull --ignore-buildable docker compose up -d --buildThis stops all services, removes containers, pulls the latest images, and restarts the system.
--ignore-buildableskips the services this repo builds from source; without itpulltries to fetch them from a registry they were never published to and fails.Developing with live updates:
docker compose watchThis watches for changes in your code and automatically updates the relevant services.
Checking the status of services:
docker compose psThis shows the current status of all services defined in your docker-compose.yml file.
These scenarios demonstrate how to use Docker Compose commands in combination to manage your AutoGPT Platform effectively.
Persisting Data
Your data already persists across restarts:
- PostgreSQL keeps its data in
autogpt_platform/data/db/dataon the host. - Workspace files, marketplace media, and FalkorDB memory use the named volumes
workspace-data,store-media-data, andfalkordb_data. - The three Redis nodes are a cache and are not persisted; do not add volumes to them.
Back up data/db/data (with the stack stopped) together with your .env files: backend/.env holds the ENCRYPTION_KEY your stored integration credentials are encrypted with.
API Client Generation
The platform includes scripts for generating and managing the API client:
pnpm fetch:openapi: Fetches the OpenAPI specification from the backend service (requires backend to be running on port 8006)pnpm generate:api-client: Generates the TypeScript API client from the OpenAPI specification using Orvalpnpm generate:api: Runs both fetch and generate commands in sequence
Manual API Client Updates
If you need to update the API client after making changes to the backend API:
Ensure the backend services are running:
docker compose up -dGenerate the updated API client:
pnpm generate:api
This will fetch the latest OpenAPI specification and regenerate the TypeScript client code.