Starred repositories
Official code base for LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixels
Self-referential self-improving agents that can optimize for any computable task
🔥 LeetCode for PyTorch — practice implementing softmax, attention, GPT-2 and more from scratch with instant auto-grading. Jupyter-based, self-hosted or try online.
Codebase for EnterpriseOps-Gym from ServiceNow
Fast and Accurate ML in 3 Lines of Code
Hundreds of models & providers. One command to find what runs on your hardware.
250+ Fine-tuning & RL Notebooks for text, vision, audio, embedding, TTS models.
The largest open-source medical AI skills library for OpenClaw🦞.
An open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message gateway, it handles different levels of…
Open-source orchestration for zero-human companies
AI agents running research on single-GPU nanochat training automatically
The platform for LLM evaluations and AI agent testing
PyTorch implementation of Google Titans: Learning to Memorize at Test Time (arXiv:2501.00663)
An autonomous agent for deep financial research
Secure, Fast, and Extensible Sandbox runtime for AI agents.
Official code for paper "GUI-Libra: Training Native GUI Agents to Reason and Act with Action-aware Supervision and Partially Verifiable RL"
Hypernetworks that update LLMs to remember factual information
Analyze AI agent trajectories: extract actions, summarize, embed, and visualize.
Facilitates simple large scale processing of HLS Medical images, documents, zip files. OHIF Viewer, 2 segmentation models and interactive learning.
Trackers gives you clean, modular re-implementations of leading multi-object tracking algorithms released under the permissive Apache 2.0 license. You combine them with any detection model you alre…
Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.5, DeepSeek-R1, GLM-5, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, GLM4.5v, Llava, Phi4, ...)…
CVPR 2025 Highlight: Progressive Masked Auto-regressor for High-Resolution 3D Generation