Memory infrastructure for LLMs and AI agents

Python SQL Parser and Transpiler

Tora: Torchtune-LoRA for RL

Open source AI analyst powered by E2B. Analyze your CSV files with Llama 3.1 and create interactive charts.

Examples of my Claude Code infrastructure with skill auto-activation, hooks, and agents

🐍 Community-driven Python implementation of TOON

🎒 Token-Oriented Object Notation (TOON) – Compact, human-readable, schema-aware JSON for LLM prompts. Spec, benchmarks, TypeScript SDK.

Deepagents is an agent harness built on langchain and langgraph. Deep agents are equipped with a planning tool, a filesystem backend, and the ability to spawn subagents - making them well-equipped …

A series of Jupyter notebooks that walk you through the fundamentals of Machine Learning and Deep Learning in Python using Scikit-Learn, PyTorch, and Hugging Face libraries.

Learn how to design large-scale systems. Prep for the system design interview. Includes Anki flashcards.

🤗 LeRobot: Making AI for Robotics more accessible with end-to-end learning

Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3, Qwen3-MoE, DeepSeek-R1, GLM4.5, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, GLM4.5v, Llava, …

Model interpretability and understanding for PyTorch

Professional-grade background patterns and gradients for your websites and apps. Easily copy and paste into your next project. Crafted with modern CSS and Tailwind for seamless integration.

[EMNLP 2025 Demo] Extracting internal representations from vision-language models. Beta version.

Contexts Optical Compression

Skyfall-GS: Synthesizing Immersive 3D Urban Scenes from Satellite Imagery

Thesis template in Typst for University of Minho

A Python library for extracting structured information from unstructured text using LLMs with precise source grounding and interactive visualization.

Simplifying reinforcement learning for complex game environments

This is the first paper to explore how to effectively use R1-like RL for MLLMs and introduce Vision-R1, a reasoning MLLM that leverages cold-start initialization and RL training to incentivize reas…

Easily fine-tune, evaluate and deploy gpt-oss, Qwen3, DeepSeek-R1, or any open source LLM / VLM!

[COLM’25] DeepRetrieval — 🔥 Training Search Agent by RLVR with Retrieval Outcome

RL gym for vision language models written in JAX

React components for visualizing traces from AI agents

Official repo for "More Thought, Less Accuracy? On the Dual Nature of Reasoning in Vision-Language Models"

The best ChatGPT that $100 can buy.