# AI use cases for Agent Launcher (agent-launch/agent-launcher) Repo: [agent-launch/agent-launcher](https://github.com/agent-launch/agent-launcher) | Use cases: 4 | Page: https://dedupedai.com/use-cases/agent-launch-agent-launcher/ Agent Launcher is a local desktop app that detects, links, configures, and runs existing coding-agent CLIs such as Claude Code, Codex CLI, and Gemini CLI from one workspace. This file holds every use case of this repo. Each one starts with a "## " heading and ends with its URL. - Run all installed coding agents from one desktop app: https://dedupedai.com/use-cases/agent-launch-agent-launcher/run-all-installed-coding-agents-from-one-app/ - Set up an OpenAI-compatible provider profile for Codex CLI: https://dedupedai.com/use-cases/agent-launch-agent-launcher/set-up-a-provider-profile-with-a-connectivity-check/ - Review local token usage and sessions across agents: https://dedupedai.com/use-cases/agent-launch-agent-launcher/review-local-token-usage-across-agents/ - Run Agent Launcher from source to test a change: https://dedupedai.com/use-cases/agent-launch-agent-launcher/run-agent-launcher-from-source-to-test-a-change/ ## How to run all installed coding agents from one desktop app with Agent Launcher Repo: [agent-launch/agent-launcher](https://github.com/agent-launch/agent-launcher) | Difficulty: Intermediate | Time: 30 minutes | Basis: From the README Link the coding-agent CLIs already on your machine and start sessions for each from one place. **Who it is for:** A developer who has several coding-agent CLIs installed on the same computer and switches between them across projects. **The problem:** Each CLI has its own commands, config folders, and session history, so keeping track of which agent runs where and in which project folder is slow. **The outcome:** All detected agents appear in one workspace, each launches in the project folder you chose, and you can resume saved sessions. ### Steps 1. Download the appropriate package from GitHub Releases (DMG and ZIP for macOS, NSIS installer for Windows, AppImage for Linux) and install it. 2. On first launch, let the guided setup detect existing CLI commands, and pick the command to link if multiple copies are present. 3. For any CLI the wizard cannot find, click the one-click install option, or install it yourself from the project's official documentation and detect it again. 4. Choose or drag in a project folder, then start a session with the selected CLI in the embedded terminal or chat view. 5. Reopen a saved session to resume it in the working directory the CLI recorded. ### Prompt to paste into your agent ```text Using the Agent Launcher repo at https://github.com/agent-launch/agent-launcher, detect the coding-agent CLIs already installed on this machine and link them, then start a session for in the project folder . Expected output: a list of linked agents and a running session in that folder. Verify that the CLI was not reinstalled or updated. ``` ### Caveat Agent Launcher links CLIs and does not reinstall or update one you already have, so you still need to install any agent it cannot find. 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/agent-launch-agent-launcher/run-all-installed-coding-agents-from-one-app/ ## How to set up an OpenAI-compatible provider profile for Codex CLI with Agent Launcher Repo: [agent-launch/agent-launcher](https://github.com/agent-launch/agent-launcher) | Difficulty: Intermediate | Time: 30 minutes | Basis: From the README Add a provider profile, let the app check it with a real request, and keep native config in sync. **Who it is for:** A developer who wants Codex CLI to use an OpenAI-compatible provider or relay instead of, or alongside, a ChatGPT account. **The problem:** Editing Codex config files, environment variables, and credentials by hand is error-prone, and a bad endpoint or key is hard to diagnose. **The outcome:** A saved profile whose endpoint, credentials, model, and account status were verified by a minimal model request, with native config files written for you. ### Steps 1. Open Agent Launcher and select Codex CLI in the agent list. 2. Add a provider profile that uses an OpenAI-compatible provider, entering the endpoint, model, and API key. 3. Run the connectivity check, which sends a real minimal model request to test the endpoint, credentials, model, network, and account status. 4. Open the native config preview and confirm that secrets are masked and that the Codex config.toml and auth.json values look correct. 5. Activate the profile and start a Codex session in your project folder. ### Prompt to paste into your agent ```text Using the Agent Launcher repo at https://github.com/agent-launch/agent-launcher, create an OpenAI-compatible provider profile named for Codex CLI with endpoint and model , then run its connectivity check. Expected output: a pass or fail result for endpoint, credentials, model, network, and account status. Verify that the masked native config preview shows no plaintext key. ``` ### Caveat Active API profiles override provider credentials for the launched process, so a profile you activate can change which account a session uses. Risk, credentials: API keys are stored as plaintext in ~/.agent-launcher/config.json and in CLI-native config files, so anyone with access to your local user account can read 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/agent-launch-agent-launcher/set-up-a-provider-profile-with-a-connectivity-check/ ## How to review local token usage and sessions across agents with Agent Launcher Repo: [agent-launch/agent-launcher](https://github.com/agent-launch/agent-launcher) | Difficulty: Beginner | Time: 15 minutes | Basis: From the README Check token counts, requests, sessions, and models for each agent from the local usage dashboard. **Who it is for:** A developer or team lead who wants to see how much each coding agent is used on a machine before deciding which profiles to keep. **The problem:** Usage numbers are spread across each CLI's own history files, so comparing agents or spotting heavy use takes manual digging. **The outcome:** A dashboard summary of locally stored token counts, request counts, sessions, and models for each agent, with optional local pricing applied. ### Steps 1. Open the usage dashboard in Agent Launcher after you have run at least one session with a linked agent. 2. Filter or read the summary for token counts, request counts, sessions, and models for each agent. 3. Add optional local pricing data if you want cost estimates alongside the token figures. 4. Open the session list to review or resume a session, or delete its underlying local record if you no longer need it. 5. Inspect installed MCP servers and Skills for each agent to see what each CLI loads. ### Prompt to paste into your agent ```text Using the Agent Launcher repo at https://github.com/agent-launch/agent-launcher, open the usage dashboard and summarize token counts, request counts, sessions, and models for over . Expected output: a short table of those figures per agent. Verify that the numbers come from local session records only and that no data was uploaded. ``` ### Caveat The dashboard summarizes locally stored data only, so agents or sessions that were never run on this machine will not appear. 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/agent-launch-agent-launcher/review-local-token-usage-across-agents/ ## How to run Agent Launcher from source to test a change with Agent Launcher Repo: [agent-launch/agent-launcher](https://github.com/agent-launch/agent-launcher) | Difficulty: Advanced | Time: 45 minutes | Basis: From the README Install dependencies, start the dev build, and run the verify and build checks on a local copy. **Who it is for:** A contributor who wants to modify Agent Launcher or check a fix before opening a pull request. **The problem:** Changes to the desktop app need a working local build and the project's checks before they are reviewed. **The outcome:** A running development build and passing verify, lint, format, and build steps on your local copy of the repo. ### Steps 1. Clone the repo from https://github.com/agent-launch/agent-launcher and confirm Node.js 22 or newer and the pnpm version in package.json are installed. 2. Run `pnpm install` in the repo folder. 3. Run `pnpm dev` to start the app in development mode. 4. Run `pnpm verify`, `pnpm lint`, and `pnpm format:check`, then `pnpm build`. 5. Read CONTRIBUTING.md for architecture, code rules, tests, commits, and pull requests before you open a pull request. ### Prompt to paste into your agent ```text Using the Agent Launcher repo at https://github.com/agent-launch/agent-launcher, install dependencies with `pnpm install` and run `pnpm verify`, then report the result for branch . Expected output: pass or fail for each check. Verify that `pnpm build` completes without errors before proposing any change. ``` ### Caveat The README lists these commands but does not describe the test suite in detail, so read CONTRIBUTING.md before changing code. 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/agent-launch-agent-launcher/run-agent-launcher-from-source-to-test-a-change/