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

How to run parallel agent changes in separate Git worktrees with Lody

Give each session its own Git worktree and review diffs and pull request status beside the chat.

Who it is forA developer or reviewer who wants several agents changing the same repo at once without their edits mixing.

The problemParallel agent edits in one checkout can mix changes, making diffs hard to review and attribute.

The outcomeEach session works in its own worktree, and per-turn or full-session diffs can be inspected beside the conversation.

What you need first

  • A terminal where npx runs, on the machine you want to connect
  • A Lody account, since the daemon start command opens a sign-in link
  • At least one coding agent already set up on that machine, such as Claude Code, Codex, or another ACP-compatible Agent
  • A workspace name you can use with the CLI

Steps

  1. Start two or more sessions against the same repository so each gets its own Git worktree.
  2. Open each session in its own tab with its files, diffs, and terminal.
  3. Inspect per-turn or full-session diffs beside each conversation and add line-level comments where needed.
  4. Follow the pull request status and CI for the branch the session produced.
  5. Fork a session into another worktree when you want to explore a different approach.

Prompt for your agent

In the LodyAI/Lody repo, start two sessions in the workspace <workspace-name> against the repository <owner/repo>, each with its own Git worktree and a different task <task-a> and <task-b>. Output the worktree and diff summary for each session. Verify that the two sessions show separate diffs in their own tabs.

Caveat. The README says the worktree and GitHub review features are part of the product, but it does not say which repository hosts are supported beyond GitHub, so confirm your setup before relying on it.

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 The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong.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