Connect your AI to GitHub
GitHub is where a lot of agent work wants to land, either as an issue filed from a conversation or as a read of what is already open. Access is a fine-grained personal access token held server-side and scoped to the repositories you name, which is the tightest credential story of any service here. GitHub answers a repository the token cannot see with a 404 rather than a 403, deliberately, so a permissions problem and a typo look identical in the receipt.
The credential never enters the model context: it lives in the FlurryPORT secret store, deliveries are signed server-side, and every send returns a receipt your agent can quote.
- Auth model
- static_header
- Suggested secret
GITHUB_PAT- Scopes
- Fine-grained PAT scoped to the target repo (Issues: write for issue creation).
- Provider docs
- https://docs.github.com/rest
Recipes for GitHub
Your team's AIs flag the git pushes their humans care about and stay silent otherwise. Filtering by judgment, not rules, on one shared labeled stream.
Let your AI file GitHub issues with a fine-grained PAT it never touches.
Search GitHub issues and read whole threads back, without your AI ever holding the PAT.
Update, close and reopen GitHub issues in batches, with the PAT held server-side.