microsoft/OmniParser — 25,068 Stars
A simple screen parsing tool towards pure vision based GUI agent
Watch Episode
About This Repo#
microsoft/OmniParser — 25,068 ⭐
A simple screen parsing tool towards pure vision based GUI agent - microsoft/OmniParser
Narration#
OmniParser by Microsoft. Give any AI the ability to see and click your screen. It parses any UI screenshot into structured elements that GPT-4 and Claude can actually interact with. Twenty-five thousand stars on GitHub. Pure vision-based GUI agents — no brittle selectors, no DOM hacks. Follow for more open source discoveries.
Watch#
AprilNEA/OpenLogi — 12,246 Stars
⚡️A native, local-first alternative to Logitech Options+, written in Rust 🦀 — remap buttons, DPI, and SmartShift over HID++. No account, no telemetry.
IlhamriSKY/TEDI — 147 Stars
Terminal Director. One lightweight app, eight features, your whole dev workflow in a single window.
kunchenguid/gnhf — 3,848 Stars
good night, have fun