Popular repositories Loading

1. Drafting-AI-Agent Drafting-AI-Agent Public

   An autonomous drafting agent built with LangGraph and Groq LLM that plans, reasons, and iteratively refines written content. The agent can update drafts, improve quality through multi-turn interact…

   Jupyter Notebook 1

2. Audiovisual-Speech-Recognition-Lip-Audio-Fusion-with-CTC- Audiovisual-Speech-Recognition-Lip-Audio-Fusion-with-CTC- Public

   Prototype implementation: Audio Spectrogram CNN + Lip 3D CNN + Transformer Fusion + CTC loss

   Python

3. Multimodal-Robot-Navigation-with-PPO Multimodal-Robot-Navigation-with-PPO Public

   A multimodal robot navigation agent that fuses RGB camera, LiDAR, and language commands via CNN + MLP + embedding encoders into a shared Actor-Critic policy trained with PPO to navigate a grid worl…

   Python

4. smartbook-ai smartbook-ai Public

   Intelligent RAG-based textbook assistant with GPU acceleration, semantic search, and LLM integration. Processes PDFs in 30 seconds, delivers answers in <3s with citations - 2x faster than enterpris…

   Python

5. visual-question-answering-chat-blip2 visual-question-answering-chat-blip2 Public

   Built a zero-shot Visual Question Answering system using pretrained BLIP-2 (OPT-2.7B), enabling natural language querying of any image without model training. Deployed as an interactive chat interf…

   Python

6. lpi-developer-kit lpi-developer-kit Public

   Forked from Life-Atlas/lpi-developer-kit

   LPI Developer Kit — Build AI agents on the Life Programmable Interface. Open MCP sandbox with SMILE methodology, 63 knowledge entries, 10 case studies. MIT licensed.

   JavaScript