Flue

Setup

Install Braintrust alongside the Flue runtime, CLI, then set your API keys. Install @flue/runtime and @flue/cli together so their versions stay aligned.

Install packages

pnpm add braintrust @flue/runtime @flue/cli

npm install braintrust @flue/runtime @flue/cli

Set environment variables

.env

BRAINTRUST_API_KEY=<your-braintrust-api-key>

Register the Braintrust observer

Initialize Braintrust in your Flue app entry, then pass braintrustFlueObserver to Flue’s observe(...) API. The observer receives Flue runtime events and reports workflow events as traces to Braintrust.

Configure your Flue project

Flue loads its app entry from src/app.ts, discovered through a flue.config.ts at the project root. Running flue init --target node generates this config:

flue.config.ts

import { defineConfig } from "@flue/cli/config";

export default defineConfig({ target: "node" });

Initialize Braintrust and observe Flue

Call initLogger and observe(braintrustFlueObserver) at the entrypoint of your application, so Braintrust is ready before any workflow runs:

src/app.ts

import { observe } from "@flue/runtime";
import { flue } from "@flue/runtime/routing";
import { braintrustFlueObserver, initLogger } from "braintrust";
import { Hono } from "hono";

initLogger({
  projectName: "my-flue-app", // Replace with your project name
  apiKey: process.env.BRAINTRUST_API_KEY,
});

observe(braintrustFlueObserver);

// This example uses Hono, but you could also be deploying Flue using other frameworks
const app = new Hono();
app.route("/", flue());

export default app;

Run your app

Run Flue normally. The app entry subscribes Braintrust to Flue activity.

What Braintrust traces

Braintrust captures:

Workflow run spans (workflow:<name>), with the run input and result.
Operation spans (flue.prompt, flue.skill, and flue.compact) for agent operations.
LLM turn spans (llm:<model>), with messages as input, the model and request parameters as metadata, and the response as output.
Tool call spans (tool:<name>), with the tool arguments as input and the tool result as output.
Subtask spans (task:<agent>), with the subtask prompt as input and its result as output.
Context compaction spans (compaction:<reason>), with message counts before and after compaction.
Token usage and cost metrics (prompt, completion, total, cached, cache-creation, and estimated cost) on LLM turns.
Errors captured on every span.

AI providers

SDKs

Developer tools

Setup

Register the Braintrust observer

What Braintrust traces

Resources

​Setup

​Register the Braintrust observer

​What Braintrust traces

​Resources

Setup

Register the Braintrust observer

What Braintrust traces

Resources