Blaxel Agents Hosting lets you bring your agent code and deploys it as a serverless auto-scalable endpoint — no matter your development framework. Follow these steps to get your AI agent up and running on Blaxel.

​
1. Create configuration files

At the root of your project repository, create a blaxel.toml file and a .env file for your sensitive environment variables. Example blaxel.toml: 
type = "agent"

[runtime]
generation = "mk3"
memory = 4096

[env]
MY_NON_SENSITIVE_ENV = "MY_NON_SENSITIVE_ENV"

​
2. Update host and port in your code

Ensure your app listens on the host and port provided by Blaxel. Update your code accordingly: 
const port = parseInt(process.env.BL_SERVER_PORT || "80");
const host = process.env.BL_SERVER_HOST || "0.0.0.0";

​
3. Deploy your agent

When deploying, there are two possible scenarios:

​
Option A: You already have a Dockerfile

Blaxel will automatically use it to build your agent. Just run: 
bl deploy

​
Option B: No Dockerfile

If you don’t want to create one, add the following scripts to your package.json:
Depending on your setup, not all scripts are required. For TypeScript projects, all four are commonly used.
  • start: Runs the server locally via TypeScript without needing a build step (useful for dev).
  • build: Builds the project (triggered automatically during deployment).
  • prod: Starts the server in production from the dist folder (requires a build first).
  • dev: Same as start, but with hot-reload for instant updates while developing.
Then run: 
bl deploy

​
4. (Optional) Enable telemetry

If you need telemetry, just import it in your app’s entrypoint: 
import "@blaxel/telemetry";

​
5. (Optional) Run locally with Blaxel CLI

If you want to run your agent locally and start using the SDK, make sure the start and dev scripts are defined, then run: 
bl serve
# or
bl serve --hotreload
✅ That’s it! You’re ready to start integrating Blaxel features using the Blaxel SDK.

​
Resources

Want the complete guide on developing and deploying agents on Blaxel? Check out the following resources:

Give compute to your agent with the TypeScript SDK

Complete guide for using the TypeScript SDK to develop an agent using Blaxel services.

Give compute to your agent with the Python SDK

Complete guide for using the Python SDK to develop an agent using Blaxel services.

Deploy your agent code to Blaxel

Complete guide for deploying AI agents on Blaxel.

Manage environment variables

Complete guide for managing variables and secrets when deploying on Blaxel.