Cua launches Perception: pixel-reading for computer-use agents, parsed locally on CPU
iamrobotbear · x · 2026-09-29
Cua (trycua/cua, 26.8k GitHub stars) announced Perception, giving its Cua Driver vision. When there's nothing to click — canvases, games, remote desktops, custom-drawn apps — it reads pixels and turns them into labeled regions an agent can act on, parsed locally on the CPU. The project is open source with cross-OS drivers, fleets, and benchmarks for training, evaluation, and data generation.
More from coding & agent
- Agents can exploit nondeterminism to modify sandboxes beyond what traces reveal — lbeurerkellner · 2026-09-29
- PhD defense slides with dead JS deps resurrected by Claude in one shot — Ben_Reinhardt · 2026-09-29
- Developer coins 'stochastic productivity': agentic coding output swings wildly day to day — carsonfarmer · 2026-09-29
- Dev open-sources 8 Godot agent skills distilled from building a game with AI in Claude Code/Codex — AIandDesign · 2026-09-29
- Cekura speech benchmark: 2,214 live calls, GPT Realtime 2.1 most reliable, Phonic v1 fastest at 1.59s — graceisford · 2026-09-29
- Before building an AI agent, ask the human doing the work what's not in the docs — alex_verem · 2026-09-29