DEDUPED Hot AI repos, turned into use cases Get 5 a day

How to push an agent branch and open a PR or MR with Grasp

Let a run push a branch and open a pull or merge request through gh, glab, or SSH.

Credentials. Git tokens and SSH private keys must be stored only in workspace credentials settings, since they are injected per run and must never be committed to the repository.

Who it is forA developer who wants the agent's approved change to reach the repository as a reviewable PR or MR without manual steps.

The problemMoving an approved agent change into a pull request is repetitive and easy to forget after review.

The outcomeA branch pushed by the sandboxed agent and a PR or MR opened after the human confirm step.

What you need first

  • A Linux host with Git, Docker, and Docker Compose installed
  • An API key for at least one supported agent backend, or a ~/.codex/auth.json login for codex
  • Optional Git credentials if agents should push branches or open PRs or MRs

Steps

  1. Run ./start.sh -d and sign in to the Web UI
  2. In the setup wizard or Project Credentials, save Git credentials for the repository (optional)
  3. Use a workflow that ends with a delivery step after the human confirm gate
  4. Start a run and approve the change at the gate
  5. Check the repository for the pushed branch and the opened PR or MR

Prompt for your agent

Using the Grasp repo (cocofhu/grasp), run a delivery workflow for <repository URL> that pushes a branch and opens a PR after human confirmation. Verify the branch name and PR link, and report both.

Caveat. The README says agents can open PRs or MRs via gh, glab, or SSH but does not document which CLI must be configured for each Git host, so confirm that before running.

Share: X LinkedIn Hacker News Email Copy link

Disclaimer

Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked "Seen in the wild", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email [email protected] and we will look at it promptly. Full disclaimer page