Skip to content

Engineering & deploys

AI agents that work in your GitHub repository.

Connect GitHub and OpenHelm's agents work in the product's own repository. The blog publisher commits each new post and pushes it, and the incident job commits its fixes. Where you would rather look first, a job opens a pull request instead of pushing. Agents can also read your issues to see what users have already reported.

What agents do with GitHub. Recurring jobs, checked every run.

  • Publish blog posts as commits

    Write a post against the keyword plan, commit it to the repository and push. A chained job then confirms the post is live and logs it in the Content Log.

  • Commit bug fixes

    When a Sentry issue or a customer email reports a defect, the engineering agent commits the fix to the repository, runs the tests and takes it through deployment.

  • Pull requests where you want review

    Set a job to open a pull request rather than push, and the change waits in Reviews until you approve it. Useful for anything beyond a routine post.

  • Read issues for context

    Before working on a reported problem, an agent can read the related GitHub issues for reproduction steps and whatever your team has already said about it.

Connect GitHub. A few minutes, once.

  1. Connect GitHub

    Add GitHub under Connections in the OpenHelm app and complete the hosted sign-in, or mint a connect link programmatically with POST /v1/connections/links.

  2. Describe the job in plain English

    Tell OpenHelm what you want done and how often. It drafts a plan with a schedule, the tools it will use, and a clear definition of done.

  3. Approve the plan

    No job fires until you have reviewed the plan. Set the autonomy level to control whether writes execute directly or queue for your approval.

  4. It runs, self-checks and reports

    Runs execute in isolated cloud sandboxes on schedule. An independent evaluator scores each run against the goal, and results arrive as logs, emails or data-table rows.

Or provision it over the API (see the Connections API docs):

POST /v1/connections/links
curl https://api.openhelm.ai/v1/connections/links \
  -H "Authorization: Bearer oh_live_..." \
  -H "Content-Type: application/json" \
  -d '{ "provider": "<provider id>", "name": "GitHub" }'
# Returns a short-lived hosted link. Open it once to authorise,
# then poll GET /v1/connections until it shows as authenticated.

Questions

Will agents push straight to my main branch?

Only where you allow it. Each job states how its work reaches the repository: a direct push for low-risk changes such as a new post, or a pull request that waits for you. Every change is an ordinary commit, so you can see exactly what an agent did and revert it like any other.

How does OpenHelm connect to GitHub?

Through a scoped OAuth grant: you sign in to GitHub once via a hosted connect flow, in the OpenHelm app or via a connect link minted with POST /v1/connections/links. OpenHelm stores no passwords, the grant is limited to what your jobs need, and you can revoke it at any time.

Can the jobs run on a schedule without me?

Yes, that is the point. Jobs run once, on an interval, or on a cron expression. A scheduler fires them, a watchdog times out anything hung, and a separate evaluator checks each run actually advanced the goal. You approve the plan before anything runs for the first time.

Is my GitHub data safe?

Each run executes in an isolated cloud sandbox with scoped, revocable credentials and no middle-layer copy of your data. Every action is logged per run, results come back with evidence, and the agent never fabricates data it could not verify.

Give your product a team that never clocks off.

Start free in the browser, or run it on your Mac with your own Claude Code or Codex plan.