ghcrawl Cluster Operator

Purpose

Operate ghcrawl as a local-first GitHub issue and pull request crawler: inspect the SQLite store, pull GitHub data, refresh summaries and embeddings, build clusters, and extract cluster evidence through deterministic CLI commands.

The default stance is conservative and cost-aware. Inspect first, then run mutating or API-spend commands only when the operator asked for fresh data or enrichment.

When to use

• Inspecting ghcrawl repository state, local runs, thread counts, clusters, or durable cluster decisions.
• Pulling GitHub issue/PR data into a local ghcrawl store.
• Running OpenAI-backed summaries, structured key summaries, embeddings, and clustering.
• Explaining a cluster with members, events, canonical selections, exclusions, and local evidence.
• Operating maintainer edits such as excluding a member from a durable cluster or setting a canonical item.

Workflow