Pituitary

What is Pituitary?

Point Pituitary at your repository. It indexes your specs, docs, and decision records, then catches what you can’t track by hand. What you wrote down should still be true — Pituitary makes sure it is.

How to use Pituitary?

Download the Pituitary binary from GitHub Releases and place it on your PATH. Generate a configuration file with pituitary init --path ., then build the index with pituitary index --rebuild. No API keys are required in deterministic mode.

Key features of Pituitary

• Semantic search across indexed spec sections by domain and status.
• Detect overlapping specs with similarity scores and relationship classification.
• Side-by-side tradeoff analysis of two specs.
• Trace impact of spec changes on specs, code refs, and docs.
• Find stale docs relative to accepted specs with cited evidence.
• Full composite review combining overlap, comparison, impact, drift, and remediation.

Use cases of Pituitary

• PR review: agent calls check_overlap and analyze_impact when a PR touches specs or decision records.
• Pre-merge drift check: agent calls check_doc_drift to surface stale docs before merging.