Own your prompts

.prompt files with YAML frontmatter and Liquid templating. Version-controlled, reviewable in PRs, deployed with your code. Switch providers by changing one line. No subscription needed to manage your own prompts.

See everything that happens

Every LLM call, HTTP request, and step traced automatically. Token counts, costs, latency, full prompt/response pairs. JSON in logs/runs/. Zero config. Claude Code analyzes your traces and fixes issues — because the data is in your file system.

Test AI like software

LLM-as-judge evaluators with confidence scores. Inline evaluators for production retry loops. Offline evaluators for dataset testing. Deterministic assertions and subjective quality judges.

Use any model

Anthropic, OpenAI, Azure, Vertex AI, Bedrock. One API. Structured outputs, streaming, tool calling — all work the same regardless of provider.

Scale without worrying

Temporal under the hood. Automatic retries with exponential backoff. Workflow history. Replay on failure. Child workflows. Parallel execution with concurrency control. You don't think about Temporal until you need it — then it's already there.

Keep secrets secret

AI apps need a lot of API keys. Sharing .env files is risky, and coding agents shouldn't see your secrets. Output encrypts credentials with AES-256-GCM, scoped per environment and workflow, managed through the CLI. No external vault subscription needed.

Quick Start

Prerequisites

• Node.js 20+
• Docker Desktop
• An LLM API key (e.g. Anthropic)

Create your project

npx @outputai/cli init
cd <project-name>

Add your API key to .env:

ANTHROPIC_API_KEY=sk-ant-...

Start developing

npx output dev

This starts the full development environment:

• Temporal server for workflow orchestration
• API server for workflow execution
• Worker with hot reload for your workflows
• Temporal UI at http://localhost:8080

Run your first workflow

npx output workflow run blog_evaluator paulgraham_hwh

Inspect the execution:

npx output workflow debug <workflow-id>

For the full getting started guide, see the documentation.

Core Concepts

Workflows

Orchestration layer — deterministic coordination logic, no I/O.

// src/workflows/research/workflow.ts
workflow({
  name: 'research',
  fn: async (input) => {
    const data = await gatherSources(input);
    const analysis = await analyzeContent(data);
    const quality = await checkQuality(analysis);
    return quality.passed ? analysis : await reviseContent(analysis, quality);
  }
});

Steps

Where I/O happens — API calls, LLM requests, database queries. Each step runs once and its result is cached for replay.

// src/workflows/research/steps.ts
step({
  name: 'gatherSources',
  fn: async (input) => {
    const results = await searchApi(input.topic);
    return { sources: results };
  }
});

Prompts

.prompt files with YAML configuration and Liquid templating.

---
provider: anthropic
model: claude-sonnet-4-20250514
temperature: 0
---

<system>You are a research analyst.</system>
<user>Analyze the following sources about {{ topic }}: {{ sources }}</user>

Evaluators

LLM-as-judge evaluation with confidence scores and reasoning.

// src/workflows/research/evaluators.ts
evaluator({
  name: 'checkQuality',
  fn: async (content) => {
    const { output } = await generateText({
      prompt: 'evaluate_quality',
      variables: { content },
      output: Output.object({
        schema: z.object({
          isQuality: z.boolean(),
          confidence: z.number().describe('0-100'),
          reasoning: z.string()
        })
      })
    });

    return new EvaluationBooleanResult({
      value: output.isQuality,
      confidence: output.confidence,
      reasoning: output.reasoning
    });
  }
});

SDK Packages

| Package | Description | |---------|-------------| | @outputai/core | Workflow, step, and evaluator primitives | | @outputai/llm | Multi-provider LLM with prompt management | | @outputai/http | HTTP client with tracing | | @outputai/cli | CLI for project init, dev environment, and workflow management |

Example Workflows

See test_workflows/ for complete examples:

• Simple — Basic workflow with steps
• HTTP — API integration with HTTP client
• Prompt — LLM generation with prompts
• Evaluation — Quality evaluation workflows
• Stream Text — Streaming text generation

Configuration

LLM Providers

ANTHROPIC_API_KEY=sk-ant-...
OPENAI_API_KEY=sk-...
AZURE_OPENAI_API_KEY=...
AZURE_OPENAI_ENDPOINT=...
AWS_ACCESS_KEY_ID=...        # For Amazon Bedrock
AWS_SECRET_ACCESS_KEY=...
AWS_REGION=us-east-1

Temporal

For local development, output dev handles everything. For production, use Temporal Cloud or self-hosted Temporal:

TEMPORAL_ADDRESS=your-namespace.tmprl.cloud:7233
TEMPORAL_NAMESPACE=your-namespace
TEMPORAL_API_KEY=your-api-key

Tracing

# Local tracing (writes JSON to disk; default under "logs/runs/")
OUTPUT_TRACE_LOCAL_ON=true

# Remote tracing (upload to S3 on run completion)
OUTPUT_TRACE_REMOTE_ON=true
OUTPUT_REDIS_URL=redis://localhost:6379
OUTPUT_TRACE_REMOTE_S3_BUCKET=my-traces

Contributing

We welcome contributions! Please read CONTRIBUTING.md first — all contributions require an approved issue and maintainer assignment before work begins.

git clone https://github.com/growthxai/output.git
cd output
pnpm install && npm run build:packages

npm run dev           # Start dev environment
npm test              # Run tests
npm run lint          # Lint code
./run.sh validate     # Validate everything

Project structure:

• sdk/ — SDK packages (core, llm, http, cli)
• api/ — API server for workflow execution
• test_workflows/ — Example workflows

License

Apache 2.0 — see LICENSE file.

Acknowledgments

Built with Temporal, Vercel AI SDK, Zod, LiquidJS.