LangChain

LangChain is a composable framework to build LLM applications. It can be combined with LangGraph which is a stateful, orchestration framework that brings added control to agent workflows. You can deploy your LangChain or LangGraph projects to Blaxel with minimal code edition (and zero configuration), enabling you to use Serverless Deployments, Agentic Observability, Policies, and more.

​

Get started with LangChain on Blaxel

To get started with LangChain/LangGraph on Blaxel:

• if you already have a LangChain or LangGraph agent, adapt your code with Blaxel SDK commands to connect to MCP servers, LLMs and other agents.
• initialize an example project in LangChain by using Blaxel CLI command bl create-agent-app, select the LangChain hello world, and deploy it using bl deploy
• clone one of our LangChain example templates and deploy it by connecting to your git provider via the Blaxel console.

​

Develop a LangChain agent using Blaxel features

While building your agent in LangChain, use Blaxel SDK to connect to resources already hosted on Blaxel:

• MCP servers
• LLMs
• other agents

​

Connect to MCP servers

Connect to MCP servers using the Blaxel SDK to access pre-built or custom tool servers hosted on Blaxel. This eliminates the need to manage server connections yourself, with credentials stored securely on the platform.

Run the following command to retrieve tools in LangChain format:

from blaxel.tools import bl_tools

await bl_tools(['mcp-server-name']).to_langchain()

​

Connect to LLMs

Connect to LLMs hosted on Blaxel using the SDK to avoid managing model API connections yourself. All credentials remain securely stored on the platform.

from blaxel.models import bl_model

model = await bl_model("model-api-name").to_langchain()

​

Connect to other agents

Connect to other agents hosted on Blaxel from your code by using the Blaxel SDK. This allows for multi-agent chaining without managing connections yourself. This command is independent of the framework used to build the agent.

from blaxel.agents import bl_agent

response = await bl_agent("agent-name").run(input);

​

Host your agent on Blaxel

You can deploy your agent on Blaxel, enabling you to use Serverless Deployments, Agentic Observability, Policies, and more. This command is independent of the framework used to build the agent.

Either run the following CLI command from the root of your agent repository.

bl deploy

Or connect a GitHub repository to Blaxel for automatic deployments every time you push on main.