To run your agent on Beamlit, you must package it by using the Beamlit SDK so Beamlit can identify the core resources to deploy: the main agent code, the standalone tools/functions it can use, and the model APIs it can query. This is what allows Beamlit to enable its features when your agent is deployed, such as secure connections to third-party systems or private networks, smart global placement of workflows, and much more.

Read this guide first on how to use the Beamlit SDK to develop a custom agent to deploy.

​
Deploy an agent

An agent can be uploaded into Beamlit from a variety of origins.

  • Using the Beamlit CLI to deploy a custom agent: this method is detailed on this page below.
  • From our pre-built template: you can use the Beamlit web console to assemble an agent using models and functions already deployed on Beamlit. It will use a default LangChain ReAct agent.
  • From a Github repository (coming soon!)

​
Serve locally

You can serve the agent locally in order to make the agent.py / agent.ts main function available on a local endpoint.

Run the following command to serve the agent:

bl serve

Calling the provided endpoint will execute the agent locally while sandboxing the core agent logic, function calls and model API calls exactly as it would be when deployed on Beamlit. Add the flag --hotreload to get live changes.

bl serve --hotreload

​
Deploy on development

You can deploy the agent in order to make the agent.py / agent.ts main function callable on a global endpoint. Deploying on Beamlit’s development environment gives a separated endpoint to carry out tests.

Run the following command to build and deploy a local agent to the development environment on Beamlit:

bl deploy --env development

​
Deploy on production

You can deploy the agent in order to make the agent.py / agent.ts main function callable on a global endpoint. When deploying to Beamlit’s production environment, you get a dedicated production endpoint that enforces your deployment policies.

Run the following command to build and deploy a local agent to the production environment on Beamlit:

bl deploy --env production

Query agents

Learn how to run consumers’ inference requests on your agent.