Gergy puts AI coding agents to work for you. Describe what you want to build, attach your files, and let Claude, Codex, Copilot, or Gemini handle the execution — from scaffolding a new app to refactoring an existing codebase.
Desktop app · File uploads & screenshots · Optional voice control · macOS & Windows
Build full-stack apps, automate refactors, generate tests, fix bugs across repos — all from a single desktop interface.
Claude, Codex, Copilot, or Gemini — install one (or all four) and switch between them freely. One desktop app, any AI coding agent you prefer.
Open a chat window, describe what you want to build, and drag in reference files, mockups, or screenshots. Gergy hands everything to the AI and manages the execution for you.
Talk to your AI agent instead of typing. Say the wake word, describe your task, and watch it execute — with a live animated avatar that speaks back to you.
Every request becomes a tracked session with full conversation history. Resume where you left off, review past work, or hand off context to a different AI agent.
Each agent brings different strengths. Gergy lets you switch between them without changing how you work — same chat, same project, different engine under the hood.
Deep reasoning & tool use
The default adapter. Claude's extended context and native tool calling make it ideal for complex, multi-step projects that read and write files.
Code-native intelligence
High-reasoning execution in a sandboxed workspace. Codex's native code understanding and execution make it uniquely suited for agentic coding tasks.
GitHub subscription included
Use your existing GitHub Copilot subscription. No additional API key required — streaming JSON responses with minimal setup.
Multimodal frontier model
Google's latest multimodal model with massive context and structured JSON streaming. Outstanding for research, analysis, and vision tasks.
Gergy works with any supported AI agent already installed on your machine. Pick one and follow the steps — it takes under two minutes.
Deep reasoning & tool use
npm install -g @anthropic-ai/claude-code
claude
Code-native intelligence
npm install -g @openai/codex
codex login
codex --version
GitHub subscription included
npm install -g @github/copilot
copilot auth login
copilot --version
Multimodal frontier model
npm install -g @google/gemini-cli
gemini
Install one AI coding agent, launch Gergy, and start building. The setup wizard handles the rest.
Pick any supported agent — claude, codex, copilot, or gemini. Gergy auto-detects what's installed on your machine.
On first launch, a guided wizard helps you pick your preferred agent, choose an avatar, and optionally enable voice control.
Open a chat window, explain your goal in plain language, and attach any reference files, mockups, or screenshots the AI should work with.
Gergy creates a project folder, runs the AI agent, streams live progress, and opens a preview when your app is ready to view.
Download the desktop app, install your preferred AI coding agent, and start automating your development workflow.
Open the .dmg and drag Gergy.app to Applications. If macOS says the app is damaged or unverified, open Terminal and run:
xattr -cr /Applications/Gergy.app
Then double-click the app to launch normally.
Edge or SmartScreen may warn the file is unrecognized. Click Keep in the download bar, then Keep anyway in the SmartScreen prompt to proceed with installation.
Requires at least one AI coding agent installed on your system. Use the install guide above to set up Claude, Codex, Copilot, or Gemini.