A specialized Claude Code workspace for creating long-form
Agent harness to make your slop code well-engineered and beautiful
AI Agent Source Code Deep Research Report
ClawTeam: Agent Swarm Intelligence (One Command → Full Automation)
Fast State-of-the-Art Static Embeddings
Build reliable Gen AI solutions without overhead
Terminal-based LLM chat tool with multi-model and local support
Self-evolving AI agent framework for automated workflows
Workplace AI platform for enterprise search and workflow automation
Easily compute clip embeddings and build a clip retrieval system
Reflexion: Language Agents with Verbal Reinforcement Learning
Cosmos-RL is a flexible and scalable Reinforcement Learning framework
High-performance inference server for text embeddings models API layer
Multilingual Document Layout Parsing in a Single Vision-Language Model
Enterprise multi-agent orchestration framework for scalable AI apps
Open Source Speech Language Model
Shared repository for open-sourced projects from the Google AI Lang
An on-premises, OCR-free unstructured data extraction
Reinforcement Learning for Humanoid Robot with Zero-Shot Sim2Real
Master the fundamentals of machine learning, deep learning
Numerical differential equation solvers in JAX
A comprehensive quantitative trading system with AI-powered analysis
Codes/Notebooks for AI Projects
Handwritten Text Recognition (HTR) system implemented with TensorFlow
Repository containing notebooks of my posts on Medium