scriptorium/README.md

Scriptorium

Scriptorium is a prompt-execution application with a command-line interface and an HTTP service. It prepares prompt requests, runs them against OpenAI-compatible model endpoints, and returns generated output with validation metadata.

The application uses Promptkit v0.1.0 for prompt, profile, schema, preparation, generation, and validation behavior. Scriptorium owns executable configuration, CLI and HTTP mapping, process behavior, output presentation, and HTTP artifact-containment policy.

Quickstart

From the repository root:

go run ./cmd/scriptorium render \
  --config ./examples/config.yml \
  --prompt generic.markdown_summary \
  --input transcript=./examples/fixtures/transcript.md \
  --input glossary=./examples/fixtures/glossary.yml \
  --format json

This renders the prepared prompt and effective runtime settings without calling a model. For complete invocation and output behavior, see the CLI reference.

Documentation

• CLI reference
• Configuration reference
• HTTP API reference
• Operations guide
• Consumer integration overview
• Migration from the former Go package
• Subprocess integration
• Architecture policy
• Promptkit framework formats
• Promptkit Go consumer guide

Examples

• Minimal configuration and complete configuration
• Prompt definitions, execution profiles, schemas, and synthetic input fixtures
• Render script
• HTTP request