Getting Started

Prerequisites

• Node.js 20 or later
• An Anthropic, OpenAI, or Ollama endpoint (for LLM steps)

Installation

Install the CLI globally:

npm install -g @blacklake-systems/depth-cli

Or run directly with npx:

npx @blacklake-systems/depth-cli run workflow.ts

To use Depth as a library in your own project:

npm install @blacklake-systems/depth-sdk

Set your API key

For Anthropic models:

export ANTHROPIC_API_KEY=sk-ant-...

For OpenAI models:

export OPENAI_API_KEY=sk-...

Ollama requires no API key — it runs locally on http://localhost:11434.

Write your first workflow

Create a file called hello.ts:

import { workflow, step } from '@blacklake-systems/depth-sdk';

export default workflow('hello', async (ctx) => {
  const greeting = await step(ctx, 'generate-greeting', async () => {
    return await ctx.llm('anthropic:claude-sonnet-4-6', {
      prompt: 'Write a single sentence welcoming someone to durable AI workflows.',
    });
  });

  console.log('\n  Result:', greeting);
  return { greeting };
});

Run the workflow

depth run hello.ts

Output:

  depth · hello

  Starting run run_abc123

  ✓ generate-greeting
  Total cost: $0.0003

  Result: Welcome to durable AI workflows...

Run it again — steps replay

Run the same command a second time. The step has already completed, so its output is returned from the database without re-calling the LLM:

  depth · hello

  Resuming run run_abc123

  ↩ generate-greeting (replayed)
  Total cost: $0.0000

Pass input to a workflow

depth run hello.ts --input '{"topic": "governance"}'

Input is available as the second argument to your workflow function:

export default workflow('hello', async (ctx, input: { topic: string }) => {
  const greeting = await step(ctx, 'generate-greeting', async () => {
    return await ctx.llm('anthropic:claude-sonnet-4-6', {
      prompt: `Write a single sentence about ${input.topic}.`,
    });
  });
  return { greeting };
});

See run history

depth list
depth status <run_id>