Stars
🎒 Token-Oriented Object Notation (TOON) – Compact, human-readable, schema-aware JSON for LLM prompts. Spec, benchmarks, TypeScript SDK.
Multi-agent framework, runtime and control plane. Built for speed, privacy, and scale.
Run Windows apps such as Microsoft Office/Adobe in Linux (Ubuntu/Fedora) and GNOME/KDE as if they were a part of the native OS, including Nautilus integration. Hard fork of https://github.com/Fmst…
Efficient Triton Kernels for LLM Training
A course in reinforcement learning in the wild
Video-based AI memory library. Store millions of text chunks in MP4 files with lightning-fast semantic search. No database needed.
TensorZero is an open-source stack for industrial-grade LLM applications. It unifies an LLM gateway, observability, optimization, evaluation, and experimentation.
Pytorch Implementation of DQN / DDQN / Prioritized replay/ noisy networks/ distributional values/ Rainbow/ hierarchical RL
Development repository for the Triton language and compiler
FULL Augment Code, Claude Code, Cluely, CodeBuddy, Comet, Cursor, Devin AI, Junie, Kiro, Leap.new, Lovable, Manus Agent Tools, NotionAI, Orchids.app, Perplexity, Poke, Qoder, Replit, Same.dev, Trae…
Implementing the 4 agentic patterns from scratch
12 Lessons to Get Started Building AI Agents
Agent framework and applications built upon Qwen>=3.0, featuring Function Calling, MCP, Code Interpreter, RAG, Chrome extension, etc.
Code repository for the paper - "Matryoshka Representation Learning"
SGLang is a fast serving framework for large language models and vision language models.
Fine-tuning & Reinforcement Learning for LLMs. 🦥 Train OpenAI gpt-oss, DeepSeek-R1, Qwen3, Gemma 3, TTS 2x faster with 70% less VRAM.
The official repo of Qwen (通义千问) chat & pretrained large language model proposed by Alibaba Cloud.
Real-ESRGAN aims at developing Practical Algorithms for General Image/Video Restoration.
Semantic segmentation models with 500+ pretrained convolutional and transformer-based backbones.
Hackable and optimized Transformers building blocks, supporting a composable construction.
🪢 Open source LLM engineering platform: LLM Observability, metrics, evals, prompt management, playground, datasets. Integrates with OpenTelemetry, Langchain, OpenAI SDK, LiteLLM, and more. 🍊YC W23
Convert documents to structured data effortlessly. Unstructured is open-source ETL solution for transforming complex documents into clean, structured formats for language models. Visit our website …
An extension to read Medium posts for free
LongEmbed: Extending Embedding Models for Long Context Retrieval (EMNLP 2024)
GISTEmbed: Guided In-sample Selection of Training Negatives for Text Embeddings
A Python framework for sequence labeling evaluation(named-entity recognition, pos tagging, etc...)