Code-only workflow
--code-only is an extract flag. It skips semantic document and media extraction. It is not a flag you need to pass to the assistant skill.
Include documents with a local model
Install the Ollama extra and run an Ollama model suitable for your content. Select an installed model inOLLAMA_MODEL, then:
--token-budget or lower --max-concurrency.
Understand the boundaries
- Local structural parsing does not send code to a model.
- A cloud coding assistant still controls where its own prompts and context go.
- A headless semantic backend receives the documents or media you ask it to process.
- PR commands contact GitHub, and model-assisted CLI triage can call your configured provider.
- Query logging is off by default in the current implementation; configuration describes the opt-in controls.
Next steps
Try it in Graphify
We build and host the graph for you, and review your pull requests with it. The Free plan (up to 3 repositories) needs no card. Pro and Teams start with a 14-day trial, card required.
Extract without an IDE
Build graphs in scripts and CI.
Ask better graph questions
Use query, path, and explain.