CollabAI is an open-source & self-hosted AI operation platform for small and medium-sized businesses. It’s a customizable & team-centric platform where you can have access to custom AI agents tailored to your business needs.

(EMNLP 2025) Weaver: A modular agentic pipeline that dynamically combines SQL and LLMs for advanced table-based question answering

RAPTOR (Rapid AI-Powered Text and Object Recognition) is an AI-native Content Insight Engine that transforms passive media storage into an intelligent knowledge platform through automated analysis, semantic search, and actionable insights. RAPTOR reducing manual tagging by 85% and making content discovery 10x faster.

Pipecat(Daily.co) x Gemini hackathon project. Talk to your agent and make your daily life memorable!

Sheldon AI Assistant is a powerful and versatile Discord bot and web application that enhances user interaction and automates tasks within your Discord server and beyond. With advanced AI models, seamless integrations, a intuitive web interface, and a wide range of features, Sheldon is your go-to assistant for an engaging and productive experience.

Advanced AI architecture integrating multi-modal reasoning, dynamic token optimization, and self-reflective learning loops. Designed for high efficiency, deep contextual understanding, and adaptive general intelligence across vision, language, and logic tasks—pushing beyond conventional transformer limits.

Cast different EHR (electronic health record) layers to a shared latent space to identify patient subtypes

Enterprise-grade RAG system featuring dual online/offline operation, multi-modal document processing, and advanced AI capabilities including knowledge graph construction and hybrid search for intelligent document analysis.

Powerful framework for building applications with Large Language Models (LLMs), enabling seamless integration with memory, agents, and external data sources.

A curated list of AI agents (open-source & proprietary) that solve real-world problems. Updated regularly!

AI video analysis + web research in one tool. Upload videos, ask questions, get comprehensive insights with current web data.

Text-Vision-Agent is an AI-powered assistant that generates images from text descriptions and provides detailed image descriptions. It combines image generation using FluxPipeline with vision-based language models like ChatOllama, enabling seamless text-to-image and image interpretation interactions.

A multi-modal recommender system that suggests books or music based on: Voice input, Audio song recognition, Typed queries, Real-time weather in your city

Multi-Modal MCP Server/Client with SSE Transport Layer

Hygieia (Desktop Doctor): Local, private medical diagnosis and instruction AI. Secure, offline guidance. Runs with Ollama & supports images/docs.

🌟 Showcase innovative AI interactions with Sheldon, a spatial AI interface for enriched canvas conversations and multi-model intelligence.