scriptorium

Scriptorium is a narrow prompt-execution application for rendering prompt requests, running them against OpenAI-compatible chat-completions endpoints, and serving the same run workflow over HTTP.

It keeps prompt definitions, execution profiles, schemas, and input artifacts as separate files so prompts can be reviewed and reused without baking model runtime settings into application code.

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 command renders the prepared prompt and effective runtime settings without calling an LLM.

Documentation

• CLI reference
• Configuration reference
• HTTP API reference
• Operations guide
• Troubleshooting
• Consumer integration overview
• Go library package
• Subprocess integration
• OpenAI-compatible chat integration
• Architecture policy

Examples

• examples/config.yml
• examples/config.full.yml
• examples/render-markdown-summary.sh
• examples/http-run.json
• examples/go-library/prepare