# AI use cases for Orca (stablyai/orca) Repo: [stablyai/orca](https://github.com/stablyai/orca) | Use cases: 5 | Page: https://dedupedai.com/use-cases/stablyai-orca/ Orca is a desktop app, with a mobile companion, for running several CLI coding agents side by side, each in its own git worktree, and tracking them in one place. This file holds every use case of this repo. Each one starts with a "## " heading and ends with its URL. - Compare agent results across parallel worktrees: https://dedupedai.com/use-cases/stablyai-orca/compare-agent-results-in-parallel-worktrees/ - Review AI diffs line by line and send feedback back: https://dedupedai.com/use-cases/stablyai-orca/review-and-annotate-ai-diffs/ - Check on and steer agents from your phone: https://dedupedai.com/use-cases/stablyai-orca/monitor-and-steer-agents-from-phone/ - Run coding agents on a remote machine over SSH: https://dedupedai.com/use-cases/stablyai-orca/run-agents-on-a-remote-machine-over-ssh/ - Script worktree and UI steps with the Orca CLI: https://dedupedai.com/use-cases/stablyai-orca/script-agent-workflows-with-orca-cli/ ## How to compare agent results across parallel worktrees with Orca Repo: [stablyai/orca](https://github.com/stablyai/orca) | Difficulty: Intermediate | Time: 30 minutes | Basis: From the README Send one prompt to several agents in separate worktrees, then compare results and merge the best one. **Who it is for:** A developer facing a task with several reasonable approaches who wants to see how different coding agents handle it before choosing one. **The problem:** Running several agents on the same repo by hand causes file conflicts, and it is hard to keep track of which output came from which agent. **The outcome:** Each agent works in its own isolated git worktree, you compare the results side by side, and you merge the one you prefer. ### Steps 1. Install Orca with `brew install --cask stablyai/orca/orca` on macOS, or download a build from https://onorca.dev/download for your system. 2. Open your repository in Orca. 3. Start one agent per worktree, such as Claude Code, Codex, and OpenCode, using the same prompt. 4. Review each worktree's changes and compare the results. 5. Merge the winning worktree into your branch with git. ### Prompt to paste into your agent ```text In the stablyai/orca repo context, use Orca's Parallel Worktrees to run the prompt in across three agents, each in its own git worktree. Output a short comparison of the three diffs, naming the one to merge. Verify that each worktree is isolated by checking that the three branches differ and that the original checkout is unchanged. ``` ### Caveat Each agent still needs its own working access, and Orca does not replace the agent's own setup or sign-in. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/stablyai-orca/compare-agent-results-in-parallel-worktrees/ ## How to review AI diffs line by line and send feedback back with Orca Repo: [stablyai/orca](https://github.com/stablyai/orca) | Difficulty: Beginner | Time: 15 minutes | Basis: From the README Comment on any diff line in Orca and return the notes to the agent to fix before you commit. **Who it is for:** A developer who reviews code an agent produced and wants to give specific feedback without switching to another tool. **The problem:** Agent output often needs small corrections, and writing those corrections in a chat window loses the exact line context. **The outcome:** You leave comments on specific diff lines, the agent receives them, and you review and commit the revised changes inside Orca. ### Steps 1. Install Orca with `brew install --cask stablyai/orca/orca` on macOS, or download a build from https://onorca.dev/download for your system. 2. Open the worktree where the agent made its changes. 3. Add comments to the diff lines that need work. 4. Send the comments back to the agent. 5. Review the updated diff and commit when it is correct. ### Prompt to paste into your agent ```text In the stablyai/orca repo, open the worktree at and send the diff annotations to the agent. Output the revised diff with each annotated line addressed. Verify that every annotated line changed or has a written reply. ``` ### Caveat Orca's diff annotations are sent to the agent you run in Orca, so review quality depends on that agent's own behavior. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/stablyai-orca/review-and-annotate-ai-diffs/ ## How to check on and steer agents from your phone with Orca Repo: [stablyai/orca](https://github.com/stablyai/orca) | Difficulty: Intermediate | Time: 30 minutes | Basis: From the README Get notified when an agent finishes and send follow-up prompts from iOS or Android. **Who it is for:** A developer who starts long agent runs at the desk and wants to follow up while away from the computer. **The problem:** Agents can finish or stall while you are away, and you have no quick way to see that or reply. **The outcome:** You receive a notification when an agent finishes and can send a follow-up prompt from your phone. ### Steps 1. Install Orca on your desktop with `brew install --cask stablyai/orca/orca` on macOS, or from https://onorca.dev/download. 2. Install the mobile companion from the App Store for iOS, or download the APK at https://www.onorca.dev/download/android for Android. 3. Pair the mobile app with your desktop app by following the mobile docs at https://www.onorca.dev/docs/mobile. 4. Start an agent on the desktop and leave it running. 5. When the notification arrives, open the agent on your phone and send a follow-up. ### Prompt to paste into your agent ```text Using the stablyai/orca mobile companion, check the agent running in and send the follow-up message . Output the agent's latest status. Verify that the status shown on the phone matches the desktop app. ``` ### Caveat The phone app works through a paired desktop host, so the desktop app must be running for it to monitor agents. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/stablyai-orca/monitor-and-steer-agents-from-phone/ ## How to run coding agents on a remote machine over SSH with Orca Repo: [stablyai/orca](https://github.com/stablyai/orca) | Difficulty: Advanced | Time: 60 minutes | Basis: From the README Use Orca's SSH worktrees to run agents, terminals, and file edits on a larger remote box. **Who it is for:** A developer whose local machine is too small or slow for heavy agent work and who has access to a bigger remote server. **The problem:** Long agent runs and builds slow down a laptop, and moving work between the laptop and a server by hand is tedious. **The outcome:** Agents, git operations, and terminals run on the remote box while you edit files and watch progress from Orca on your desktop. ### Steps 1. Install Orca with `brew install --cask stablyai/orca/orca` on macOS, or download a build from https://onorca.dev/download for your system. 2. Confirm you can already connect to the remote machine over SSH. 3. Add the remote machine as an SSH worktree in Orca using the SSH docs at https://www.onorca.dev/docs/ssh. 4. Start an agent in the remote worktree. 5. Check progress, edit files, and run git commands from Orca while the agent works. ### Prompt to paste into your agent ```text In the stablyai/orca repo, create an SSH worktree on and start an agent there with the task . Output the agent's final summary and the list of changed files. Verify that the changed files exist on the remote host and not on the local machine. ``` ### Caveat Orca's SSH worktree setup depends on the remote machine being reachable over SSH, which you must already have working. Risk, credentials: The remote machine needs SSH access, so keep keys and host credentials out of prompts and out of shared repo files. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/stablyai-orca/run-agents-on-a-remote-machine-over-ssh/ ## How to script worktree and UI steps with the Orca CLI with Orca Repo: [stablyai/orca](https://github.com/stablyai/orca) | Difficulty: Advanced | Time: 45 minutes | Basis: From the README Let an agent create worktrees and drive the Orca UI through the CLI for repeatable workflows. **Who it is for:** A developer or platform engineer who wants the same agent setup repeated across tasks or repos without clicking through the app each time. **The problem:** Setting up worktrees and interacting with the app by hand for every task is slow and easy to get wrong. **The outcome:** A script or agent creates worktrees, takes snapshots, and fills in UI fields through the Orca CLI, and the results are repeatable. ### Steps 1. Install Orca with `brew install --cask stablyai/orca/orca` on macOS, or download a build from https://onorca.dev/download for your system. 2. Read the CLI overview at https://www.onorca.dev/docs/cli/overview to confirm the commands available in your version. 3. Create a worktree with `orca worktree create`. 4. Use the `snapshot`, `click`, and `fill` commands named in the README to inspect and fill the UI in the new worktree. (inferred, check the README) 5. Save the sequence as a script and rerun it for the next task. ### Prompt to paste into your agent ```text Using the stablyai/orca CLI, create a worktree for the task and take a snapshot of its UI. Output the snapshot summary and the worktree path. Verify that the worktree exists in git worktree list before reporting success. ``` ### Caveat The README names only a few CLI commands and links to the CLI docs for the full set, so check the docs before scripting anything beyond them. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/stablyai-orca/script-agent-workflows-with-orca-cli/