Projects

Open-source agent systems for programmable workflows, desktop interaction, and automated research. Select a project to read about its methods, results, and implementation.

OpenProgram — Self-Programming AI Agent Framework

A self-programming AI agent framework for programmable workflows, visual desktop operation, and automated research.
openprogram.io

SoMem — Self-Organized Document Memory

Persistent agent memory built from editable Markdown documents with references to immutable conversation records. Separate Writer and Reader roles organize and retrieve evidence.
GitHub

GUI-Lens — Precise GUI Grounding via Coarse-to-Fine Cropping

Training-free GUI grounding for off-the-shelf vision-language models. OCR and detected interface components provide coordinate references; iterative cropping refines the target before a click.
GitHub · Paper