From e81ae075e2d119fe1f1ed1cd0eba88ee927115e5 Mon Sep 17 00:00:00 2001 From: eliaseffects Date: Wed, 5 Aug 2026 12:26:02 -0400 Subject: [PATCH] Add DeepSight: device-native vision for text-only LLMs --- README.md | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/README.md b/README.md index cd47cec..94484c8 100644 --- a/README.md +++ b/README.md @@ -134,4 +134,5 @@ Many papers here are organized and identified using a visualization tool develop - [Fazm](https://github.com/m13v/fazm) - Open-source voice-controlled AI agent for macOS using accessibility APIs and ScreenCaptureKit - [Lumen](https://github.com/omxyz/lumen) - Vision-first browser agent with self-healing deterministic replay. Screenshot → model → action loop over CDP, multi-provider support. - [computer agents](https://computer-agents.com) -- [Terminator](https://github.com/mediar-ai/terminator) - Playwright-like automation for Windows desktop apps using native accessibility APIs \ No newline at end of file +- [Terminator](https://github.com/mediar-ai/terminator) - Playwright-like automation for Windows desktop apps using native accessibility APIs +- [DeepSight](https://github.com/Reality-Shifting-Tech/deepsight) - Device-native vision for text-only LLMs. Zero tokens, no GPU, no image data leaves the machine. 16 tools: look/OCR/zoom/locate + live screen capture + desktop automation \ No newline at end of file