Agent! for macOS

Agent! is a 100% native Swift AI desktop assistant for macOS 26.4+ Tahoe, designed as an open-source alternative to Claude Code, Cursor, Cline, and OpenClaw. It works autonomously through natural language to build apps, write code, manage files, and automate workflows — all with zero Electron overhead and deep macOS integration via Accessibility APIs. It supports all major LLM providers including OpenAI, Claude, Gemini, DeepSeek, Ollama, and more, and uniquely leverages on-device Apple Intelligence for tool-calling, token compression, and task summaries.

• Desktop Control — Control any app through natural language using Accessibility APIs and Swift automation; click, type, scroll, and navigate hands-free.
• Agentic Coding Tool — Intelligent code editing with Coding Mode and full Xcode integration for seamless app development.
• Xcode Integration — Build, run, and deploy apps with AI assistance; fix errors, manage project files, and automate version bumps inside Xcode.
• Custom Agents & Automation — Automate anything with Custom Agents powered by ScriptingBridge, shell commands, AppleScript, and accessibility actions.
• File Management — Create, read, edit, and organize files across your codebase with smart folder views and token-efficient compressed reads.
• MCP Support — Extend Agent! with Model Context Protocol servers for databases, APIs, and tools, including built-in XCF Xcode Lite integration.
• Apple Intelligence Integration — Uses on-device Apple Intelligence as a real tool-calling agent for accessibility intents, token compression, triage of direct commands, and task summaries.
• Advanced Speech Recognition — Dictate requests hands-free with on-device speech recognition or enable Voice Control for the "Agent!" command; also supports iMessage remote control.
• Multi-LLM Provider Support — Works with OpenAI, Claude, Gemini, DeepSeek, Grok, Qwen, GLM, vLLM, LMStudio, HuggingFace, and more.
• Open Source — Star and fork on GitHub; distributed as a downloadable DMG with full source available.

To get started, download the DMG from GitHub, drag Agent! to /Applications, register background services, approve in System Settings, configure your LLM API key in Settings, and type your first task in natural language.