I wanted a Cursor-style agent that runs on my own model, so I built one

说明与用途

OpenPilot 是一个桌面应用，允许用户在任何 OpenAI 兼容模型上运行类似 Cursor 的编码代理，完全控制文件访问和命令执行。

问题

The author wanted a Cursor-like coding agent that could run on a locally hosted or self‑hosted model, but no open‑source tool met that requirement.

结果

OpenPilot enables users to run a Cursor‑style coding agent on any OpenAI‑compatible model, with full control over file access, command execution, and optional web search, while providing persistent memory and token usage metrics.

工作流

• 1. Download the latest build from GitHub Releases or run from source.
• 2. On first launch, connect a model by providing base URL, API key, and model name.
• 3. Choose a workspace folder that the agent may modify.
• 4. Optionally add a TinyFish key for web search.
• 5. Describe a task in the chat (e.g., "add a README and a failing test for this function").
• 6. Observe tool cards and approve or deny actions as prompted.

证据

I looked around for an open-source tool that worked the way I had in mind and couldn't find one that fit. So I built it.

来源

OpenPilot is a desktop app, built with Electron. You give it a model, a folder, and a task.

来源

You stay in control. Tool calls show up as cards in the chat, and sensitive actions wait for you to approve or deny them.

来源

Windows is the main target right now. macOS builds exist but are early and unsigned. There's no Linux build yet.

来源