Muriz S.

HRM-Text. HRM-Text is a 1B text generation model based on the HRM architecture, strengthened by task completion and latent space reasoning.

parcae. Stable Looped Models and their Scaling Laws

inspect_petri. An alignment auditing agent capable of quickly exploring alignment hypothesis

LiteRT-LM. LiteRT-LM is Google's production-ready, high-performance, open-source inference framework for deploying Large Language Models on edge devices.

heretic. Fully automatic censorship removal for language models

repoprover. Research code base for Automatic Textbook Formalization

slime. slime is an LLM post-training framework for RL Scaling.

OpenEnv. An interface library for RL post training with environments.

gemma_penzai. A JAX Research Toolkit for Visualizing, Manipulating, and Understanding Gemma Models with Multi-modal Support based on Penzai.

rlm-minimal. Super basic implementation (gist-like) of RLMs with REPL environments.

catnip. Like catnip, a highly addictive agentic coding tool

smart-tab-grouping. Code for tuning Smart Tab Grouping models for Firefox

paper-implementations. Clean, reusable paper implementations for trending papers on alphaXiv

scribe. Python

openinference. OpenTelemetry Instrumentation for AI Observability

lighteval. Lighteval is your all-in-one toolkit for evaluating LLMs across multiple backends

openai-guardrails-python. OpenAI Guardrails - Python

pretrain-data. Pretraining data reconstruction scripts for Apertus

apertus-tech-report. Tech Report of the Apertus LLM

apertus-format. Response format to be used with apertus

abogen. Generate audiobooks from EPUBs, PDFs and text with synchronized captions.

open-operator-evals. Opensource benchmark evaluating web operators/agents performance

gpt-oss. gpt-oss-120b and gpt-oss-20b are two open-weight language models by OpenAI

repeng. A library for making RepE control vectors

llm-compression-intelligence. Official github repo for the paper "Compression Represents Intelligence Linearly" [COLM 2024]

rllm. Democratizing Reinforcement Learning for LLMs

sdk-python. Temporal Python SDK

ART. Agent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-job training. Reinforcement learning for Qwen3.6, GPT-OSS, Llama, and more!

SkyRL. SkyRL: A Modular Full-stack RL Library for LLMs

Search-R1. Search-R1: An Efficient, Scalable RL Training Framework for Reasoning & Search Engine Calling interleaved LLM based on veRL

TinyZero. Minimal reproduction of DeepSeek R1-Zero

ToolRL. Python

PRIME. Scalable RL solution for advanced reasoning of language models

lmdeploy. LMDeploy is a toolkit for compressing, deploying, and serving LLMs.

MonkeyOCR. A lightweight LMM-based Document Parsing Model

tau-bench. Code and Data for Tau-Bench

LlamaFactory. Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

VLM-R1. Solve Visual Understanding with Reinforced VLMs

Qwen-Agent. Agent framework and applications built upon Qwen>=3.0, featuring Function Calling, MCP, Code Interpreter, RAG, Chrome extension, etc.

verifiers. Our library for RL environments + evals

nano-vllm. Nano vLLM

tuning_playbook. A playbook for systematically maximizing the performance of deep learning models.

smolagents. 🤗 smolagents: a barebones library for agents that think in code.

oat. 🌾 OAT: A research-friendly framework for LLM online alignment, including reinforcement learning, preference learning, etc.

parler-tts. Inference and training library for high-quality TTS models.

verl. verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework

hertz-dev. first base model for full-duplex conversational audio

moonshine. Very low latency speech to text, intent recognition, and text to speech, for building voice agents and interfaces

borg. Deduplicating archiver with compression and authenticated encryption.

plano. Plano is an AI-native proxy server and data plane for agentic apps. Smart LLM routing, observability, agent orchestration, and guardrails so you stay focused on your agents core logic.

axolotl. Go ahead and axolotl questions

evaluation-guidebook. Sharing both practical insights and theoretical knowledge about LLM evaluation that we gathered while managing the Open LLM Leaderboard and designing lighteval!

ml-depth-pro. Depth Pro: Sharp Monocular Metric Depth in Less Than a Second.

baml. The programming language for agents

NeMo-Aligner. Scalable toolkit for efficient model alignment

explorecareers. Explore careers based on your interests and skills with AI

The_Prompt_Report. HTML

unsloth. Unsloth is a local UI for training and running Kimi K3, Gemma 4, Qwen3.6, DeepSeek, GLM and other models.

pocketbase. Open Source realtime backend in 1 file

SUPIR. SUPIR aims at developing Practical Algorithms for Photo-Realistic Image Restoration In the Wild. Our new online demo is also released at suppixel.ai.

fsdp_qlora. Training LLMs with QLoRA + FSDP

llama-cookbook. Welcome to the Llama Cookbook! This is your go to guide for Building with Llama: Getting started with Inference, Fine-Tuning, RAG. We also show you how to solve end to end problems using Llama model family and using them on various provider services

Yi. A series of large language models trained from scratch by developers @01-ai

pandoc-latex-template. A pandoc LaTeX template to convert markdown files to PDF or LaTeX.

hamilton. Apache Hamilton helps data scientists and engineers define testable, modular, self-documenting dataflows, that encode lineage/tracing and metadata. Runs and scales everywhere python does.

BS-RoFormer. Implementation of Band Split Roformer, SOTA Attention network for music source separation out of ByteDance AI Labs

conditional-flow-matching. TorchCFM: a Conditional Flow Matching library

jepa. PyTorch code and models for V-JEPA self-supervised learning from video.

awesome-ml. Curated list of useful LLM / Analytics / Datascience resources

grobid. A machine learning software for extracting information from scholarly documents

paperetl. 📄 ⚙️ ETL processes for medical and scientific papers

llmsherpa. Developer APIs to Accelerate LLM Projects

milvus. Milvus is a high-performance, cloud-native vector database built for scalable vector ANN search

chroma. Search infrastructure for AI

unstructured. 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 to learn more about our enterprise grade Platform product for production grade workflows, partitioning, enrichments, chunking and embedding.

PhotoMaker. PhotoMaker [CVPR 2024]

DiskANN. A vector indexing library to bring fast, fresh and filtered search to your database

gpt-fast. Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.

bubblewrap. Low-level unprivileged sandboxing tool used by Flatpak and similar projects

CRATE. Code for CRATE (Coding RAte reduction TransformEr).

generative-models. Generative Models by Stability AI

brainmagick. Training and evaluation pipeline for MEG and EEG brain signal encoding and decoding using deep learning. Code for our paper "Decoding speech perception from non-invasive brain recordings" published in Nature Machine Intelligence, 2023.

adept-inference. Inference code for Persimmon-8B

codellama. Inference code for CodeLlama models

Awesome-LLMOps. An awesome & curated list of best LLMOps tools for developers

audiocraft. Audiocraft is a library for audio processing and generation with deep learning. It features the state-of-the-art EnCodec audio compressor / tokenizer, along with MusicGen, a simple and controllable music generation LM with textual and melodic conditioning.

Kalman-and-Bayesian-Filters-in-Python. Kalman Filter book using Jupyter Notebook. Focuses on building intuition and experience, not formal proofs. Includes Kalman filters,extended Kalman filters, unscented Kalman filters, particle filters, and more. All exercises include solutions.

TorchIntegral. Integral Neural Networks in PyTorch

llama. Inference code for Llama models

upscayl. 🆙 Upscayl - #1 Free and Open Source AI Image Upscaler for Linux, MacOS and Windows.

IF. Python

StableLM. StableLM: Stability AI Language Models

skypilot. The AI Compute Platform for frontier teams. SkyPilot turns fragmented AI compute into one AI supercomputer, so frontier AI teams build custom intelligence faster.

gpt4all. GPT4All: Run Local LLMs on Any Device. Open-source and available for commercial use.

Text2Video-Zero. [ICCV 2023 Oral] Text-to-Image Diffusion Models are Zero-Shot Video Generators

peft. 🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.

alpa. Training and serving large-scale neural networks with auto parallelization.

GPTQ-for-LLaMa. 4 bits quantization of LLaMA using GPTQ

gptq. Code for the ICLR 2023 paper "GPTQ: Accurate Post-training Quantization of Generative Pretrained Transformers".

gerev. 🧠 AI-powered enterprise search engine 🔎

audioFlux. A library for audio and music analysis, feature extraction.

chatgpt-retrieval-plugin. The ChatGPT Retrieval Plugin lets you easily find personal or work documents by asking questions in natural language.

alpaca-lora. Instruct-tune LLaMA on consumer hardware

stanford_alpaca. Code and documentation to train Stanford's Alpaca models, and generate the data.

alpaca.cpp. Locally run an Instruction-Tuned Chat-Style LLM

evals. Evals is a framework for evaluating LLMs and LLM systems, and an open-source registry of benchmarks.

sd-webui-controlnet. WebUI extension for ControlNet

ControlNet. Let us control diffusion models!

og-equity-compensation. Stock options, RSUs, taxes — read the latest edition: www.holloway.com/ec

AudioLDM. AudioLDM: Generate speech, sound effects, music and beyond, with text.

riffusion-app-hobby. Stable diffusion for real-time music generation (web app)

instruct-pix2pix. Python

LMOps. General technology for enabling AI capabilities w/ LLMs and MLLMs

lora. Using Low-rank adaptation to quickly fine-tune diffusion models.

rbo. Implementation of Rank-biased Overlap

coolicons. coolicons is a carefully designed collection of 440+ icons with a focus on simplicity and consistency. Perfectly suited for web, application and mobile design.

tailwind-react-native-classnames. simple, expressive API for tailwindcss + react-native

can-it-be-done-in-react-native. ⚛️ 📺 Projects from the “Can it be done in React Native?” YouTube series

react-native-photo-editor. React Native: Native Photo Editor

react-native-vector-icons. Customizable Icons for React Native with support for image source and full styling.

react-native-fonts. Fonts available out of the box in a React Native project

unilm. Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities

composer. Supercharge Your Model Training

trlx. A repo for distributed training of language models with Reinforcement Learning via Human Feedback (RLHF)

Open-Assistant. OpenAssistant is a chat-based assistant that understands tasks, can interact with third-party systems, and retrieve information dynamically to do so.

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

gpt-2-output-dataset. Dataset of GPT-2 outputs for research in detection, biases, and more

PaLM-rlhf-pytorch. Implementation of RLHF (Reinforcement Learning with Human Feedback) on top of the PaLM architecture. Basically ChatGPT but with PaLM

xformers. Hackable and optimized Transformers building blocks, supporting a composable construction.

riffusion-hobby. Stable diffusion for real-time music generation

cbp-translate. Python

modal-examples. Examples of programs built using Modal

custom-diffusion. Custom Diffusion: Multi-Concept Customization of Text-to-Image Diffusion (CVPR 2023)

SimSwap. An arbitrary face-swapping framework on images and videos with one single trained model!

textual_inversion. Jupyter Notebook

sygil-webui. Stable Diffusion web UI

imaginAIry. Pythonic AI generation of images and videos

stable-diffusion-webui. Stable Diffusion web UI

Dreambooth-Stable-Diffusion. Implementation of Dreambooth (https://arxiv.org/abs/2208.12242) with Stable Diffusion

Txt2Vectorgraphics. Custom Script for Automatics1111 StableDiffusion-WebUI.

RAVE. Official implementation of the RAVE model: a Realtime Audio Variational autoEncoder

mind-vis. Code base for MinD-Vis

sige. [NeurIPS 2022, T-PAMI 2023] Efficient Spatially Sparse Inference for Conditional GANs and Diffusion Models

SwinIR. SwinIR: Image Restoration Using Swin Transformer (official repository)

Qt-Advanced-Docking-System. Advanced Docking System for Qt

Awesome-Diffusion-Models. A collection of resources and papers on Diffusion Models

aqtinstall. aqt: Another (unofficial) Qt CLI Installer on multi-platforms

neurotic. Curate, visualize, annotate, and share your behavioral ephys data using Python

vector-quantize-pytorch. Vector (and Scalar) Quantization, in Pytorch

tortoise-tts. A multi-voice TTS system trained with an emphasis on quality

whisper. Robust Speech Recognition via Large-Scale Weak Supervision

Attention-based-spatio-temporal-spectral-feature-learning-for-subject-specific-EEG-classification. Official code for "Attention-Based Spatio-Temporal-Spectral Feature Learning for Subject-Specific EEG Classification" paper

pyqtgraph. Fast data visualization and GUI tools for scientific / engineering applications

diffusers. 🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.

nirstorm. Brainstorm plugin for fNIRS data analysis

TDDR. Temporal Derivative Distribution Repair: A motion correction method for fNIRS

preprocessingfNIRS. UCLA SCN lab preprocessing function for fNIRS data, collected with NIRx

stable-diffusion. A latent text-to-image diffusion model

fauxpilot. FauxPilot - an open-source alternative to GitHub Copilot server

Homer3. MATLAB application for fNIRS data processing and visualization

OmegaFold. OmegaFold Release Code

mne-python. MNE: Magnetoencephalography (MEG) and Electroencephalography (EEG) in Python

VQ-Diffusion. Official implementation of VQ-Diffusion

prettymaps. Draw pretty maps from OpenStreetMap data! Built with osmnx +matplotlib + shapely

calibre-web. :books: Web app for browsing, reading and downloading eBooks stored in a Calibre database

Tools-to-Design-or-Visualize-Architecture-of-Neural-Network. Tools to Design or Visualize Architecture of Neural Network

perceiver-ar. Python

TiddlyWiki5. A self-contained JavaScript wiki for the browser, Node.js, AWS Lambda etc.

latent-diffusion. High-Resolution Image Synthesis with Latent Diffusion Models

scikit-tda. Topological Data Analysis for Python🐍

TTS. 🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production

flax. Flax is a neural network library for JAX that is designed for flexibility.

dm-haiku. JAX-based neural network library

activitywatch. The best free and open-source automated time tracker. Cross-platform, extensible, privacy-focused.

user.js. Firefox privacy, security and anti-tracking: a comprehensive user.js template for configuration and hardening

How-To-Secure-A-Linux-Server. An evolving how-to guide for securing a Linux server.

unbound. Unbound is a validating, recursive, and caching DNS resolver.

dnsperftest. DNS Performance test

raspberrypiwireguard. Install and configure WireGuard on Raspberry Pi (and others)

awesome-tunneling. List of ngrok, Cloudflare Tunnel, Tailscale, and ZeroTier alternatives and other tunneling software and services. Focus on self-hosting.

age. A simple, modern and secure encryption tool (and Go library) with small explicit keys, no config options, and UNIX-style composability.

alphafold. Open source code for AlphaFold 2.

stylegan3. Official PyTorch implementation of StyleGAN3

macOS-Security-and-Privacy-Guide. Community guide to securing and improving privacy on macOS.

cmix. cmix is a lossless data compression program aimed at optimizing compression ratio at the cost of high CPU/memory usage.

tapiriik. tapiriik keeps your fitness in sync

garmin-connect-seed. Monkey C

connectiq-apps. A collection of Connect IQ apps.

pisearch. Go language pi search code

choochoo. Training Diary

BeautifulAlgorithms.jl. Concise and beautiful algorithms written in Julia

project-bodypix. BodyPix model demo application for Google Coral

Coq-HoTT. A Coq library for Homotopy Type Theory

DaemonMode.jl. Client-Daemon workflow to run faster scripts in Julia

AMDGPU.jl. AMD GPU (ROCm) programming in Julia

mathlib3. Lean 3's obsolete mathematical components library: please use mathlib4

mesh-transformer-jax. Model parallel transformers in JAX and Haiku

M2. The primary source code repository for Macaulay2, a system for computing in commutative algebra, algebraic geometry and related fields.

pyimagej. Use ImageJ from Python

skimage-tutorials. skimage-tutorials: a collection of tutorials for the scikit-image package.