Show HN: PerceptAI – Give AI agents eyes on any screen, not just browsers
4 comments
Claude can already do this: https://code.claude.com/docs/en/computer-use
Claude Computer Use requires Anthropic's API
and runs in a sandboxed Docker container.
PerceptAI runs locally on your machine, works with any LLM backend, costs $0 to run, and is fully open source.
Different use case this is infrastructure for developers building their own agents, not an end-user tool.
PerceptAI runs locally on your machine, works with any LLM backend, costs $0 to run, and is fully open source.
Different use case this is infrastructure for developers building their own agents, not an end-user tool.
And the dozen or so AutoHotkey MCPs.
75% of real computer work happens in desktop apps, legacy software, and tools with zero APIs. Agents are completely blind to all of it.
PerceptAI uses EasyOCR + Groq Vision to read any screen and PyAutoGUI to act on it. One plain English instruction executes autonomously with self-healing and memory.
Demo: percept-ai-phi.vercel.app GitHub: github.com/Neeraj04-CY/PerceptAi
Would love feedback from anyone building agents.