[EMNLP2025] "LightRAG: Simple and Fast Retrieval-Augmented Generation"

MoBA: Mixture of Block Attention for Long-Context LLMs

Source code for the Microsoft Comic Chat IRC client

V Rising Dedicated Server Instructions

OpenWiki is a CLI that writes and maintains agent documentation for your codebase.

A feed-forward 3D foundation model for reconstructing scenes from streaming data

Scale computer-use 2.0 with open-source drivers, cross-OS fleets, and benchmarks for training, evaluation, and data generation.

Codex-assisted local 2D animation spritesheet generator and scene compositing workspace.

Machine Learning From Scratch. Bare bones NumPy implementations of machine learning models and algorithms with a focus on accessibility. Aims to cover everything from linear regression to deep lear…

A unified library of SOTA model optimization techniques like quantization, distillation, pruning, neural architecture search, speculative decoding, etc. It compresses deep learning models for downs…

A Flexible Framework for Experiencing Heterogeneous LLM Inference/Fine-tune Optimizations

Become a cracked AI/ML Research Engineer

ResearchStudio: Our AI co-author, from research problem to final publication.

Run GLM-5.2 (744B MoE) on a 25GB-RAM consumer machine — pure C, zero deps, experts streamed from disk. Tiny engine, immense model. 🐦

Connect your devices into a secure WireGuard®-based overlay network with SSO, MFA and granular access controls.

Red Team AI Benchmark: Evaluating LLMs for authorized offensive-security tasks

Local AI app and inference engine for agents. Run open-weight LLMs locally — private, 100% offline on your computer.

H2O LLM Studio - a framework and no-code GUI for fine-tuning LLMs. Documentation: https://docs.h2o.ai/h2o-llmstudio/

DevilDev aims to be spec driven lovable which is better and open src

A runtime substrate that turns an agent's execution into a reversible, Git-like trace, so meta-agents can observe, fork, replay, and revert any run. Couples agent and environments in a copy-on-writ…

Official Kaggle CLI

A lightweight, lightning-fast, in-process vector database

autonomous red teaming platform; multi-agent offensive-security meta-harness

20+ high-performance LLMs with recipes to pretrain, finetune and deploy at scale.

A minimal GPU design in Verilog to learn how GPUs work from the ground up

LLM training in simple, raw C/CUDA

The best ChatGPT that $100 can buy.

The simplest, fastest repository for training/finetuning medium-sized GPTs.