Autonomous self-evolving agents. Vision-grounded layered memory and self-written skills for LLM agents that operate your computer.
Enable AI to control your desktop, mobile and HMI devices
Opensource, on-device voice + vision layer for AI agents. Bring any model or coding agent; the whole speech loop (VAD, STT, TTS, barge-in) runs locally. An open alternative to ElevenLabs Agents, Gemini Live, and OpenAI Realtime.
React Native Duolingo clone with a real-time AI voice teacher. Built with Expo, Stream Voice Agents, Clerk auth, and NativeWind for a complete, interactive mobile learning experience.
A local browser automation agent based on Microsoft Fara-7B model optimized for LM Studio inference.
React Native Linguaquest with a real-time AI voice teacher. Built with Expo, Stream Voice Agents, Clerk auth, and NativeWind for a complete, interactive mobile learning experience.
Production-grade multi-modal AI platform — 17 real-time vision & audio tabs, 22 SDK modules, 7-tier LLM cascade, 37+ endpoints. Built for Vision Possible Hackathon by WeMakeDevs x Stream.
Real-time AI agent for querying live courtroom video with sub-500ms latency. Multimodal search combining video intelligence, speech-to-text, and hybrid search. Built with Stream, Twelve Labs, Deepgram, and Gemini Live API.
React Native Duolingo clone with a real-time AI voice teacher. Built with Expo, Stream Voice Agents, Clerk auth, and NativeWind for a complete, interactive mobile learning experience.
Autonomous AI agent playtests 2048 in Chromium via Playwright: GPT-4o vision reads the board from screenshots, LangGraph orchestrates sessions, and each campaign gets a structured playtesting report with metrics and turn logs. Python 3.12+
Video Analysis Tool - Agents that write vision code. Built with OpenAI, Claude and Gemini
Meeting Assistant built to enhance virtual meetings by providing real-time insights, summaries, and intelligent assistance.
Real-time visual assistance for blind and visually impaired users, powered by Vision Agents
An interactive language learning app like Duolingo, powered by React Native and featuring a real-time AI voice tutor. Built securely with Expo, Stream, Clerk, and NativeWind.
React Native Duolingo clone with a real-time AI voice teacher. Built with Expo, Stream Voice Agents, Clerk auth, and NativeWind for a complete, interactive mobile learning experience.
Photo-Agents (2026) is the premier AI utility for advanced image processing and automated editing. Experience high-speed neural enhancements and fully optimized tools for elite visual content creation.
Next.js + Python demo of a smart video meeting assistant using Stream Video/Chat and realtime LLMs.
FiftyOne Gemma 4 model zoo integration
Add a description, image, and links to the vision-agents topic page so that developers can more easily learn about it.
To associate your repository with the vision-agents topic, visit your repo's landing page and select "manage topics."