Skip to main content

Documentation Index

Fetch the complete documentation index at: https://onecli.sh/docs/llms.txt

Use this file to discover all available pages before exploring further.

Get onecli running and connect your agent to external services.

Start with Docker

The fastest way to run OneCLI locally (no external database or config needed):
1

Start onecli

docker run --pull always -p 10254:10254 -p 10255:10255 -v onecli-data:/app/data ghcr.io/onecli/onecli
This starts both the web dashboard (port 10254) and the gateway (port 10255) in a single container with embedded storage.
2

Add credentials via the dashboard

Open localhost:10254, create an agent, and add credentials for the services your agent uses (Google, GitHub, Slack, etc.).
3

Connect your agent

Install the OneCLI CLI and launch your agent through it:
curl -fsSL onecli.sh/cli/install | sh
onecli auth login --api-key oc_your_api_key
onecli run -- claude
This configures proxy settings, CA certificates, and agent skills automatically. See the Coding Agents guide for details.
That’s it. Your agent’s HTTP calls now have credentials injected automatically.

Or with Docker Compose

git clone https://github.com/onecli/onecli.git
cd onecli/docker
docker compose up

What happens next

You now have OneCLI set up. From here:
  • Read How it works to understand the full architecture
  • Set up Coding Agents (Claude Code, Cursor, Codex)
  • Explore the SDKs for Docker-based agent integration

Troubleshooting

Make sure Docker is running and ports 10254/10255 are available. Check logs with docker logs <container-id>.
If you’re accessing OneCLI through an SSH tunnel, reverse proxy, or on a remote server, OAuth callbacks may redirect to an unreachable address (e.g. http://127.0.0.1:10254).Set NEXT_PUBLIC_APP_URL to the URL you actually use in your browser:
# In your .env file or docker-compose.yml
NEXT_PUBLIC_APP_URL=http://localhost:8080
For SSH tunnel setups, forwarding to the same local port avoids this entirely:
ssh -L 10254:127.0.0.1:10254 user@host