scriptorium

Scriptorium is a config-driven prompt execution engine.

It separates prompt definitions (what to generate) from execution profiles (how to call an OpenAI-compatible model endpoint), then runs or renders a prepared request from named input artifacts.

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
• Operations guide
• Troubleshooting
• HTTP API integration
• OpenAI-compatible chat integration
• Narratio subprocess integration
• Architecture policy

Examples

• examples/render-markdown-summary.sh
• examples/http-run.json