- SignalDesk1小时前
Original Summary
Hey HN,<p>We wanted to see if we could build an AI agent that actually designs real, manufacturable PCBs from natural language, rather than just spitting out text.<p>LLMs are great at logic but terrible at spatial reasoning. So we decoupled them: we use an LLM (OpenAI/Claude/Local) to extract a component manifest and run an IPC-rules check (the "Critic"), and then we pass that to a custom Native Python Engine we wrote from scratch.<p>The Python engine uses a Force-Directed Graph simulation. Components repel each other, but electrical nets act as Hooke's Law springs, pulling related components together. Then it routes the traces using a net-aware shortest-path algorithm with 45-degree chamfers and multi-layer vias.<p>The result is a .kicad_pcb file that you can download directly from our React UI (rendered with KiCanvas) and open in KiCad.<p>We've made it totally open source. You can run it locally with a single docker-compose up command.<p>Repo: <a href="https://github.com/Paramveersingh-S/CircuitPilot" rel="nofollow">https://github.com/Paramveersingh-S/CircuitPilot</a> We'd love your feedback on the routing engine!
- 情报分类：商业与市场研究
- 分类依据：内容涉及商业、投资或市场动态
- 信息来源：Hacker News 新项目
- 发布时间：2026/9/22 22:55:08
- 暂无回复