# AI use cases for Omnirush Gui (omnirush-ai/omnirush-gui) Repo: [omnirush-ai/omnirush-gui](https://github.com/omnirush-ai/omnirush-gui) | Use cases: 3 | Page: https://dedupedai.com/use-cases/omnirush-ai-omnirush-gui/ A desktop coding agent app for working on your own projects, using models from your omnirush.ai account. This file holds every use case of this repo. Each one starts with a "## " heading and ends with its URL. - Run a coding agent on a local project from the desktop app: https://dedupedai.com/use-cases/omnirush-ai-omnirush-gui/run-coding-agent-on-local-project/ - Have the agent branch, commit and open a pull request: https://dedupedai.com/use-cases/omnirush-ai-omnirush-gui/agent-opens-pull-request-from-branch/ - Let the agent query local files and SQLite through MCP: https://dedupedai.com/use-cases/omnirush-ai-omnirush-gui/query-local-data-with-mcp-servers/ ## How to run a coding agent on a local project from the desktop app with Omnirush Gui Repo: [omnirush-ai/omnirush-gui](https://github.com/omnirush-ai/omnirush-gui) | Difficulty: Beginner | Time: 15 minutes | Basis: From the README Install the desktop app, sign in, and have the agent work on a project folder. **Who it is for:** A developer or solo builder who wants a coding agent on their own project and has an omnirush.ai account. **The problem:** Setting up a coding agent with model access and tool approvals takes effort. **The outcome:** The app runs prompts against your project once the account is connected. ### Steps 1. Download the build for your platform from the releases page and install it. 2. On macOS, follow the first-launch steps for the app, then open omnirush. 3. Click **Sign in to omnirush.ai** in the sidebar, then approve the device code in your browser. 4. Pick a model and an effort level for the chat; GPT 6 Astra is the default model. 5. Leave the composer's full-permissions toggle off if you want to approve each tool call. ### Prompt to paste into your agent ```text Using the omnirush-gui desktop app on this machine, open the project at in a new chat and ask the agent to list the failing tests and fix one. Report the files changed and confirm the chat shows each tool call the agent made. ``` ### Caveat The app does not run prompts until an account is connected, and there is no build for Intel Macs. Risk, credentials: On macOS the keychain asks for your login password, and first launch may require bypassing the unverified-app warning; only do this for a build you downloaded from the official releases page. 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/omnirush-ai-omnirush-gui/run-coding-agent-on-local-project/ ## How to have the agent branch, commit and open a pull request with Omnirush Gui Repo: [omnirush-ai/omnirush-gui](https://github.com/omnirush-ai/omnirush-gui) | Difficulty: Intermediate | Time: 30 minutes | Basis: From the README Let the agent clone, branch, commit, push, and open or review a pull request with gh. **Who it is for:** A developer who wants routine git and pull request steps handled by the agent, with approval on write commands. **The problem:** Routine git and pull request steps take time and are easy to get wrong by hand. **The outcome:** A pull request is open for review, with write commands approved during the session. ### Steps 1. Install the app and sign in as described in the first use case. 2. Install the GitHub CLI `gh` and sign in to it, since the agent opens pull requests with `gh`. (inferred, check the README) 3. Open the project in a chat and ask the agent to create a branch, make the change, and commit it. 4. Approve each write command when asked; destructive commands always ask. 5. Ask the agent to push the branch and open a pull request, then review the result in the app. ### Prompt to paste into your agent ```text In the omnirush-gui desktop app, open the repository at , create a branch named , make the change described in , commit it, push, and open a pull request with gh. Report the pull request URL and confirm the push succeeded. ``` ### Caveat The git and pull request steps depend on the gh CLI being available, which the README mentions but does not install for you. Risk, credentials: The agent uses your gh login to push and open pull requests, so review each write command before you approve it. 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/omnirush-ai-omnirush-gui/agent-opens-pull-request-from-branch/ ## How to let the agent query local files and SQLite through MCP with Omnirush Gui Repo: [omnirush-ai/omnirush-gui](https://github.com/omnirush-ai/omnirush-gui) | Difficulty: Intermediate | Time: 30 minutes | Basis: From the README Enable supported local MCP servers such as filesystem and SQLite for data questions. **Who it is for:** An analyst or developer whose task needs the agent to read local files or a SQLite database. **The problem:** The agent needs tools beyond the chat window to inspect local files or data. **The outcome:** The agent uses an enabled local MCP server to answer questions about your data. ### Steps 1. Install the app and sign in as described in the first use case. 2. Open Settings > MCP in the app. 3. Enable a local server from the supported list, such as filesystem or SQLite. 4. Add any skills you need from the Library in Settings. 5. Start a chat that asks a question about , then check the answer against the source file. ### Prompt to paste into your agent ```text Using omnirush-gui with its SQLite MCP server enabled in Settings > MCP, query for the row count of and list its columns. Verify the row count against the source before reporting it. ``` ### Caveat Only local MCP servers on the account's supported list work; remote and account-linked servers are not supported. 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/omnirush-ai-omnirush-gui/query-local-data-with-mcp-servers/