Self-hosted AI agent

Ork is a source-available AI agent for persistent teammates. Each bot can use a browser and a shell, keep routines as Markdown, and pause for approval when work crosses a boundary you set. Self-hosting means that stack runs on a machine you control.

The license scope separates the Apache-2.0 baseline from new Ork work under PolyForm Noncommercial or a paid commercial license. Run Ork on your own infrastructure. This page is the setup you need to run it. The full self-hosting guide on GitHub covers backups, upgrades, secrets, restricted networks, and production Compose.

Diagram of an Ork deployment. Web, desktop, and mobile clients talk to an API. A worker and Postgres sit beside it. The computer defaults to Docker, with E2B, Daytona, CreateOS, or Boat optional. Model prompts go to the provider you configure. — An Ork deployment. Postgres, bot files, and the audit log stay on the machine you run. Prompts still go to the model provider you choose.

What self-hosting gives you

Data ownership

Postgres, bot files, browser profiles, and the audit log stay on the deployment you run. Content you send to a model provider is processed by that provider under its terms. You choose the provider and the keys.

Model choice

Connect OpenAI, Anthropic, Google, OpenRouter, or Vercel AI Gateway. You can also use an OpenAI-compatible endpoint or a local model server such as Ollama, LM Studio, llama.cpp, or MLX. Each bot can use a different model.

Cost control

Permitted noncommercial use is free. Commercial use of new Ork work requires a paid license. You pay the model provider you connect and any remote computer provider you choose. Local Docker computers are the default, so a single machine does not need an E2B, Daytona, CreateOS, or Boat account.

Self-host only, for now

These work on your own deployment and are not yet on Ork Cloud. Each turns on from .env.

Telegram, WhatsApp, iMessage and SMS, Feishu and Lark. Add the platform's credentials: TELEGRAM_BOT_TOKEN, WHATSAPP_*, SENDBLUE_* (iMessage and SMS), or LARK_*.
Image and video generation. MEDIA_GENERATION_PROVIDER=fal, MEDIA_GENERATION_API_KEY, and an image or video model (MEDIA_GENERATION_IMAGE_MODEL, MEDIA_GENERATION_VIDEO_MODEL).
Purchases with Stripe Link. PAYMENT_WALLET_PROVIDER=link. Each purchase waits for your approval in Link.
Cursor cloud agents. CLOUD_AGENT_PROVIDER=cursor, CURSOR_API_KEY, and CLOUD_AGENT_SPACE_ID.
Ticket board. TICKET_BOARD_ENABLED=true.
Local models and local MCP servers. ORKBOT_LOCAL_MODELS, and MCP_STDIO_ENABLED with MCP_STDIO_ALLOWED_COMMANDS.

The full guide lists every setting for each one.

Requirements

Published images. Docker Engine 26 or newer (API 1.45 or newer, for bot home volume subpaths), the Compose plugin, curl, and OpenSSL. No Node.js install.
Source checkout. Node.js 22.22.2 or newer on the 22.x line, Node.js 24.x, or Node.js 26 or newer, plus pnpm 9 and Docker. Node.js 23.x and 25.x are not supported.

Install with published images

From an empty directory on the machine that should run Ork:

mkdir -p orkbot && cd orkbot &&
curl -fsSLO https://raw.githubusercontent.com/orkbot-run/ork/main/infra/compose/install-images.sh &&
bash install-images.sh --prepare-only

The prepare step downloads Compose and creates .env with random secrets. Configure the registered Accounts client in that file, then run bash install-images.sh. Existing settings are kept. The default image tag is edge for linux/amd64 and linux/arm64.

Open http://127.0.0.1:5173 and sign in through Accounts. Connect a model in the app. Local Docker computers are on by default. Workspace ownership grants no server-administration permissions.

The new bot form in Ork, filled with a demo bot named Inbox. — Creating a bot in the Ork app. The name, title, and description here are demo data.

Bot settings with the model menu open on a demo Inbox bot. — Each bot can use a different model. This menu lists models for the credentials connected on that deployment.

A routine editor for a weekday inbox check, with the instruction written as text. — A routine is readable text with a schedule. You can edit it in the app.

An approval card asking whether a demo bot may send an email, with allow once, always allow, and deny. — When work crosses a boundary you set, the bot stops on an approval card. The action is also written to the audit log.

For an agent-assisted install, use the setup prompt.

Run it on a server

In Ork setup, sign in to Accounts, choose the self-hosted option and enter the server's HTTPS address. Copy the generated command to a private directory on the Linux server. It pins the installer and its files to one source revision.

Point the domain at the server and allow inbound TCP 80 and 443 first. On Debian or Ubuntu, the installer can install Docker and its prerequisites, configure HTTPS and check Accounts sign-in. Local Docker computers need no remote sandbox account. Existing settings and data stay in place.

For an installer already downloaded from the same pinned source, a one-use code can be entered on stdin:

bash install-images.sh --server --url https://server.example.com --code-stdin

Paste the code and press Enter. It expires after 15 minutes. If a reverse proxy already uses ports 80 or 443, add --external-proxy and route it to 127.0.0.1:5173. Otherwise the installer adds Caddy for HTTPS. It reports success after checking the public certificate, API and Accounts availability. Then open the HTTPS address and sign in with Accounts.

The Linux setup guide covers retries and existing proxies. The production guide covers operator-managed deployments and host hardening.

If downloads are blocked, use the restricted-network guide. Secret names and recovery are in the secrets checklist.

Install from source

Use this path to develop Ork. The published images above are enough to run it.

git clone https://github.com/orkbot-run/ork.git orkbot
cd orkbot
cp .env.example .env

Set POSTGRES_PASSWORD and POSTGRES_APP_PASSWORD to two URI-safe random values (for example openssl rand -hex 16) and put them in DATABASE_MIGRATION_URL and DATABASE_URL. Set BETTER_AUTH_SECRET, ENCRYPTION_KEY, and SCREEN_PROXY_SECRET to independent long random values. Docker sandboxes also need a dedicated SANDBOX_SUPERVISOR_TOKEN. Keep these in .env, not in git.

For host-side development with Docker Desktop, set SANDBOX_CONTROL_VIA_LOOPBACK=true in .env. The supervisor then publishes its control service on a loopback port, because Docker Desktop container addresses are not reachable from the host. Leave this unset when the supervisor runs inside Compose.

docker compose --env-file .env \
  -f infra/compose/docker-compose.yml \
  -f infra/compose/docker-compose.postgres-host.yml \
  up postgres -d
pnpm install
pnpm db:generate
pnpm db:migrate
pnpm sandbox:build
pnpm dev

The Postgres overlay publishes loopback 127.0.0.1:5433 for host-side tools. Open http://127.0.0.1:5173. docker compose down -v deletes Postgres data.

Desktop and mobile

With a server already running, the Tauri app's Existing instance option takes its https:// address. HTTP is accepted only for loopback and private LAN addresses. This computer installs the published images with Docker Compose on that machine.

Run on your Mac with the desktop app. This computer installs Ork on that Mac. A Mac Mini can stay on as the always-on box.

In the mobile app, tap Use a custom server on the sign-in screen and enter the same HTTPS origin as WEB_ORIGIN.

Full reference

FAQ

What do I need to self-host Ork?

Published images need Docker Engine 26 or newer, the Compose plugin, curl, and OpenSSL. You do not need Node.js for that path. A source checkout needs Node.js 22.22.2 or newer on the 22.x line, Node.js 24.x, or Node.js 26 or newer, plus pnpm 9 and Docker. Node.js 23.x and 25.x are not supported.

Where does my data live?

How do model choice and cost work?

You connect your own model keys, or a local or OpenAI-compatible model server, and you can pick a different model per bot. Permitted noncommercial use is free. Commercial use of new Ork work requires a paid license. You pay the model and computer providers you use. Local Docker computers are the default and do not need a hosted sandbox account.

Is hosted Ork available?

Run Ork from source on your own infrastructure. A hosted Ork service has not been announced.

How does this compare with OpenClaw?

Both run on hardware you control. Ork is source-available. OpenClaw uses MIT. After a Docker or desktop install, Ork is a chat for persistent teammates. OpenClaw's getting-started guide adds a wizard, a Gateway you run in the terminal or install as a background service, and a separate step to connect a chat app.

Get started

Self-host with the steps above, or start on Ork Cloud.

Ork Cloud View on GitHub