Developer and data

AI agents that use GitHub

UtilitySpaces gives an AI agent scoped access to GitHub through its own encrypted connection, not your password. The agent can call 6 named GitHub tools, and the 2 that write wait for a person's approval unless an admin has set the connection to run without asking. Every call is written to a hash-chained audit log with its arguments and its result.

What an agent can do in GitHub

Browse repositories, read and file issues, comment, and track pull requests. An agent calls these by name, and matching is exact.

Every tool a GitHub connection exposes, and whether it writes, which waits for approval by default
Tool	What it does	Waits for approval by default
List repositories	List repositories accessible to the token.	No — read only
Get repository	Get a single repository's details.	No — read only
List issues	List issues in a repository.	No — read only
Create issue	Open a new issue in a repository.	Yes — it writes
Comment on issue	Add a comment to an issue or pull request.	Yes — it writes
List pull requests	List pull requests in a repository.	No — read only

4 read tools, 2 write tools. Generated from the connector catalogue the product runs on, so it cannot list a tool that does not exist.

What teams hand an agent in GitHub

Engineering teams hand an agent the repository reading: listing issues with List issues, checking what pull requests are waiting with List pull requests, and summarising both for the inbox. Create issue and Comment on issue are the writes, and both wait for a person to approve them unless an admin has let this connection write without asking.

Write a daily digest of open pull requests and new issues across the team's repositories into the inbox each morning.
Create an issue when a bug report from support or chat includes steps to reproduce, with the thread summarised in (after a person approves it)
Comment on an issue or pull request when a related decision is made elsewhere, so the discussion stays in one place (after a person approves it)

Before you let it write, or keep out: Think before letting a connection that reaches public repositories write without asking: a Comment on issue post from the token's account is visible to anyone watching, and the connector cannot edit or delete it once posted.

What waits for a person

Reads run on their own. These do not — each one waits in Approvals for an owner or admin unless an admin has set this connection to run writes without asking, and every call toGitHub, approved, rejected or unattended, is logged.

Create issue POST
Comment on issue POST

What connecting GitHub takes

GitHub uses an API key you create in GitHub and paste in once. A workspace admin sets the connection up; the fields are:

Personal Access Token

Credentials are encrypted and bound to your workspace, never read back, and every outbound call passes one guarded fetch — the connector security posture sets out exactly how, and the security page covers the platform around it.

Where GitHub fits

Give an agent GitHub work by writing a message in the inbox, or put its tools in a scheduled flow. What the run cost is on the cost breakdown.

Other developer and data integrations: GitLab, Sentry. Or see every application agents can connect to.

See it doing your actual work

Open a demo workspace, connect one app, and give an agent a real job. No card, no sales call.

Try the demo See pricing

We reply to every message within one business day.