multimodal

Past 30d, sorted by best first

09/18	8	ysr666/dsh-vision-router v2.2.0 DSH Vision Router enables image-to-tool calling for text-only DeepSeek Harness agents using built-in vision chains and pixel-level tools without Python. JavaScript 1121☆ 46d old #javascript #multimodal #vision #dsh-plugin #deepseek-harness
09/16	5	screenpipe/screenpipe app-v2.7.42 A local screen, audio, and activity recording tool that powers AI agents with searchable context from your work. TypeScript 21618☆ 821d old #javascript #typescript #ai #llm #machine-learning
10/10	4	Code-Amadeus/Amadeus v0.16.1-alpha.0 Real-time multimodal desktop AI agent for talk, embodied interaction, and action control via a provider runtime and work-flow based artifacts. Python 375☆ 79d old #python #electron #multimodal #ai-agent #desktop-agent