Ankit Shah's repositories
agihouse-werewolf-template
Template repository for the Werewolf hackathon
AI-Crash-Course
AI Crash Course to help busy builders catch up to the public frontier of AI research in 2 weeks
agent-zero
Agent Zero AI framework
Awesome-Audio-LLM
Audio Large Language Models
Awesome-LLM-Long-Context-Modeling
📰 Must-read papers and blogs on LLM based Long Context Modeling 🔥
awesome-o1
A bibliography and survey of the papers surrounding o1
browser-use
Make websites accessible for AI agents
build-hours
Build hours code to share.
ChatDev
Create Customized Software using Natural Language Idea (through LLM-powered Multi-Agent Collaboration)
digital-human
NVIDIA AI Blueprint for digital human for customer service.
flash-attention
Fast and memory-efficient exact attention
IsaacLab
Unified framework for robot learning built on NVIDIA Isaac Sim
Janus
Janus-Series: Unified Multimodal Understanding and Generation Models
khoj
Your AI second brain. Self-hostable. Get answers from the web or your docs. Build custom agents, schedule automations, do deep research. Turn any online or local LLM into your personal, autonomous AI (gpt, claude, gemini, llama, qwen, mistral). Get started - free.
litellm
Python SDK, Proxy Server (LLM Gateway) to call 100+ LLM APIs in OpenAI format - [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthropic, Sagemaker, HuggingFace, Replicate, Groq]
llama-stack
Composable building blocks to build Llama Apps
prime
prime is a framework for efficient, globally distributed training of AI models over the internet.
Search-o1
Search-o1: Agentic Search-Enhanced Large Reasoning Models
skypilot
SkyPilot: Run AI and batch jobs on any infra (Kubernetes or 12+ clouds). Get unified execution, cost savings, and high GPU availability via a simple interface.
transferlearning
Transfer learning / domain adaptation / domain generalization / multi-task learning etc. Papers, codes, datasets, applications, tutorials.-迁移学习
VILA
VILA is a family of state-of-the-art vision language models (VLMs) for diverse multimodal AI tasks across the edge, data center, and cloud.
VinePPO
Code for the paper "VinePPO: Unlocking RL Potential For LLM Reasoning Through Refined Credit Assignment"