Brian Fitzgerald

program-probes. Measures whether a language model's internal state predict properties of its own output

marin. Open-source framework for the research and development of foundation models.

vllm-lens. Extract residual-stream activations and apply steering vectors (including activation oracles) to any vLLM model during inference.

hunk. Review-first terminal diff viewer for agentic coders

pool. pool is Poolside’s coding agent that runs in your terminal or integrates with any ACP-compatible editor

SNKRX. A replayable arcade shooter where you control a snake of heroes.

nano-vllm. Nano vLLM

viztracer. A debugging and profiling tool that can trace and visualize python code execution

claude-context. Code search MCP for Claude Code. Make entire codebase the context for any coding agent.

context7. Context7 Platform -- Up-to-date code documentation for LLMs and AI code editors

opencode. The open source coding agent.

RL2. Python

verifiers. Our library for RL environments + evals

llm-debugger-vscode-extension. VSCode extension that demonstrates the use of large language models (LLMs) for active debugging of programs

picotron. Minimalistic 4D-parallelism distributed training framework for education purpose

open-r1. Fully open reproduction of DeepSeek-R1

papers. speedrun implementation of dl papers throughout history

llm.c. LLM training in simple, raw C/CUDA

axolotl. Go ahead and axolotl questions

latent-scope. A scientific instrument for investigating latent spaces

DataDreamer. DataDreamer: Prompt. Generate Synthetic Data. Train & Align Models.   🤖💤

NeuralFlow. Visualize the intermediate output of Mistral 7B

scedit-pytorch. Implementation of "SCEdit: Efficient and Controllable Image Diffusion Generation via Skip Connection Editing"

textbook. distill chatGPT coding ability into small model (1b)

llm-reasoners. A library for advanced large language model reasoning

five-dollar-model. Python

gpt-json. Structured and typehinted GPT responses in Python

ImageReward. [NeurIPS 2023] ImageReward: Learning and Evaluating Human Preferences for Text-to-image Generation

StableStudio. Community interface for generative AI

TemporalKit. An all in one solution for adding Temporal Stability to a Stable Diffusion Render via an automatic1111 extension

StableLM. StableLM: Stability AI Language Models

babyagi. Python

BlenderGPT. Use commands in English to control Blender with OpenAI's GPT-4

ai-notes. notes for software engineers getting up to speed on new AI developments. Serves as datastore for https://latent.space writing, and product brainstorming, but has cleaned up canonical references under the /Resources folder.

nxml. LLaMA from First Principles

alpaca-roleplay-discordbot. A discord bot that roleplays!

NormalMap-Online. NormalMap Generator Online

simple-llm-finetuner. Simple UI for LLM Model Finetuning

toolformer-pytorch. Implementation of Toolformer, Language Models That Can Use Tools, by MetaAI

e4t-diffusion. Implementation of Encoder-based Domain Tuning for Fast Personalization of Text-to-Image Models

ai-forge. C#

OpenChatKit. Python

minLoRA. minLoRA: a minimal PyTorch library that allows you to apply LoRA to any PyTorch model.

Prompt-Engineering-Guide. 🐙 Guides, papers, lessons, notebooks and resources for prompt engineering, context engineering, RAG, and AI Agents.

FlexLLMGen. Running large language models on a single GPU for throughput-oriented scenarios.

plug-and-play. Official Pytorch Implementation for “Plug-and-Play Diffusion Features for Text-Driven Image-to-Image Translation” (CVPR 2023)

ChatRWKV. ChatRWKV is like ChatGPT but powered by RWKV (100% RNN) language model, and open source.

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

ControlNet. Let us control diffusion models!

Photoshop-Export-Layers-to-Files-Fast. This script allows you to export your layers as individual files at a speed much faster than the built-in script from Adobe.

Dreambooth. Fine-tuning of diffusion models

TEXTurePaper. Official Implementation for "TEXTure: Text-Guided Texturing of 3D Shapes"

agentic. Your API ⇒ Paid MCP. Instantly.

ManimML. ManimML is a project focused on providing animations and visualizations of common machine learning concepts with the Manim Community Library.

EveryDream. Advanced fine tuning tools for vision models

Auto-Photoshop-StableDiffusion-Plugin. A user-friendly plug-in that makes it easy to generate stable diffusion images inside Photoshop using either Automatic or ComfyUI as a backend.

car-data. Scraping and predicting car info

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

hh-rlhf. Human preference data for "Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback"

summarize-from-feedback. Code for "Learning to summarize from human feedback"

trl. Train transformer language models with reinforcement learning.

awesome-node-based-uis. A curated list with resources about node-based UIs

latent-nerf. Official Implementation for "Latent-NeRF for Shape-Guided Generation of 3D Shapes and Textures"

stability-sdk. SDK for interacting with stability.ai APIs (e.g. stable diffusion inference)

awesome-blender. 🪐 A curated list of awesome Blender addons, tools, tutorials; and 3D resources for everyone.

goa. Design-first Go framework that generates API code, documentation, and clients. Define once in an elegant DSL, deploy as HTTP and gRPC services with zero drift between code and docs.

open_spiel. OpenSpiel is a collection of environments and algorithms for research in general reinforcement learning and search/planning in games.

muzero-general. MuZero

stable-diffusion-video-maker. Video generation tool for Stable Diffusion.

system-design. Learn how to design systems at scale and prepare for system design interviews

dance-diffusion. Tools to train a generative model on arbitrary audio samples

services-engineering. A reading list for services engineering, with a focus on cloud infrastructure services

motion-diffusion-model. The official PyTorch implementation of the paper "Human Motion Diffusion Model"

sample-factory. High throughput synchronous and asynchronous reinforcement learning

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

cleanrl. High-quality single file implementation of Deep Reinforcement Learning algorithms with research-friendly features (PPO, DQN, C51, DDPG, TD3, SAC, PPG)

stable-dreamfusion. Text-to-3D & Image-to-3D & Mesh Exportation with NeRF + Diffusion.

pytorch-fm. Factorization Machine models in PyTorch

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

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

alpha-zero-general. A clean implementation based on AlphaZero for any game in any framework + tutorial + Othello/Gobang/TicTacToe/Connect4 and more

chess-alpha-zero. Chess reinforcement learning by AlphaGo Zero methods.

maua. Deep learning toolkit for image, video, and audio synthesis

dream-textures. Stable Diffusion built-in to Blender

pytorch3d. PyTorch3D is FAIR's library of reusable components for deep learning with 3D data

DiscoDiffusion-Warp. DiscoDiffusion Warp

stable-diffusion. Jupyter Notebook

CodeBERT. CodeBERT

kaolin-wisp. NVIDIA Kaolin Wisp is a PyTorch library powered by NVIDIA Kaolin Core to work with neural fields (including NeRFs, NGLOD, instant-ngp and VQAD).

CogVideo. text and image to video generation: CogVideoX (2024) and CogVideo (ICLR 2023)

ldm-finetune. Home of `erlich` and `ongo`. Finetune latent-diffusion/glid-3-xl text2image on your own data.

majesty-diffusion. Majesty Diffusion by @Dango233(@Dango233max) and @apolinario (@multimodalart)

gpt-code-clippy. Full description can be found here: https://discuss.huggingface.co/t/pretrain-gpt-neo-for-open-source-github-copilot-model/7678?u=ncoop57

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

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

deep_learning_curriculum. Language model alignment-focused deep learning curriculum

particles_detection_fsr. Code associated with 'Airborne Particle Classification in LiDAR Point Clouds Using Deep Learning'

musicinformationretrieval.com. Instructional notebooks on music information retrieval.

RETRO-pytorch. Implementation of RETRO, Deepmind's Retrieval based Attention net, in Pytorch

min-dalle. min(DALL·E) is a fast, minimal port of DALL·E Mini to PyTorch

RealtimeConeDetection. 1. Labelled a traffic cones dataset of 260 images. 2. Scripts to create your own dataset. & 3. Adapted YOLOv3 for SJTU racing team.

MarkovJunior. Probabilistic language based on pattern matching and constraint propagation, 153 examples

functional-transformer. A pure-functional implementation of a machine learning transformer model in Python/JAX

EPIJudge. EPI Judge - Preview Release

univnet. Unofficial PyTorch Implementation of UnivNet Vocoder (https://arxiv.org/abs/2106.07889)

AIDungeon. Infinite adventures await!

great_expectations. Always know what to expect from your data.

dalle-mini. DALL·E Mini - Generate images from a text prompt

transformers. 🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

pytorch-image-models. The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (ViT), MobileNetV4, MobileNet-V3 & V2, RegNet, DPN, CSPNet, Swin Transformer, MaxViT, CoAtNet, ConvNeXt, and more

PyTorch-VAE. A Collection of Variational Autoencoders (VAE) in PyTorch.

angle-grinder. Slice and dice logs on the command line

discreteVAE. Python

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

taming-transformers. Taming Transformers for High-Resolution Image Synthesis

DALLE-pytorch. Implementation / replication of DALL-E, OpenAI's Text to Image Transformer, in Pytorch

metrics. 📊 An infographics generator with 30+ plugins and 300+ options to display stats about your GitHub account and render them as SVG, Markdown, PDF or JSON!

slim. Slim(toolkit): Don't change anything in your container image and minify it by up to 30x (and for compiled languages even more) making it secure too! (free and open source)

ploomber. The fastest ⚡️ way to build data pipelines. Develop iteratively, deploy anywhere. ☁️

MiDaS. Code for robust monocular depth estimation described in "Ranftl et. al., Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer, TPAMI 2022"

altair. Declarative visualization library for Python

serve. ☁️ Build multimodal AI applications with cloud-native stack

cornell-mcray. 🕹 A quick'n'dirty game sample using kajiya, physx-rs, and dolly

kajiya. 💡 Experimental real-time global illumination renderer 🦀

display-switch. Turn a $30 USB switch into a full-featured multi-monitor KVM switch

faiss. A library for efficient similarity search and clustering of dense vectors.

viewer. ML models and internal tensors 3D visualizer

3D-printed-mirror-array. 3D-printable hexagonal mirror array capable of reflecting sunlight into arbitrary patterns

SwfitH264Demo. swift decode h264 file with videotoolbox

stylegan3. Official PyTorch implementation of StyleGAN3

geoblender. Tutorials for making 3D-looking maps with Blender and QGIS

projectm. projectM - Cross-platform Music Visualization Library. Open-source and Milkdrop-compatible.

shader-school. :mortar_board: A workshopper for GLSL shaders and graphics programming

python-pcl. Python bindings to the pointcloud library (pcl)

PointCloudSegmentation. The research project based on Semantic KITTTI dataset, 3d Point Cloud Segmentation , Obstacle Detection

nlp-labelling. Labelling platform for text using weak supervision.

awesome-machine-learning. A curated list of awesome Machine Learning frameworks, libraries and software.

leetcode-cli. A cli tool to enjoy leetcode!

zero-shot-object-tracking. Object tracking implemented with the Roboflow Inference API, DeepSort, and OpenAI CLIP.

ML-For-Beginners. 12 weeks, 26 lessons, 52 quizzes, classic Machine Learning for all

genanki. A Python 3 library for generating Anki decks

machine-learning-interview. Machine Learning Interviews from FAANG, Snapchat, LinkedIn. I have offers from Snapchat, Coupang, Stitchfix etc. Blog: mlengineer.io.

pointnet. PyTorch implementation of "PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation" https://arxiv.org/abs/1612.00593

votenet. Deep Hough Voting for 3D Object Detection in Point Clouds

IA_LIO_SAM. IA-LIO-SAM is enhanced LIO-SAM using Intensity and Ambient channel from OUSTER LiDAR.

rust-server. Provides a dedicated linux server for Rust (the game) running inside a Docker container.

is-thirteen. Check if a number is equal to 13.

pycrunch-trace. Time Travel Debugging for Python

PUN2VoiceWebGLUnity. This is a Github page of WebGL implementation of voice chat by using PUN 2 server solution.

NuGetForUnity. A NuGet Package Manager for Unity

palanteer. Visual Python and C++ nanosecond profiler, logger, tests enabler

eon-neos. Operating System for your comma two and EON

feather. A Minecraft server implementation in Rust

learning3d. This is a complete package of recent deep learning methods for 3D point clouds in pytorch (with pretrained models).

GANTheftAuto. Python

rayon. Rayon: A data parallelism library for Rust

TD-Examples. TouchDesigner Examples

unity-quickhull. An implementation in Unity of the Quickhull algorithm for generating 3D convex hulls

configuration. Like some files bro

module-linking. Proposal for allowing modules to define, import and export modules and instances

GameNetworkingSockets. Reliable & unreliable messages over UDP. Robust message fragmentation & reassembly. P2P networking / NAT traversal. Encryption.

CenterTrack. Simultaneous object detection and tracking using center points.

notarize-app. Make and notarise a .app or .dmg outside of Xcode

mmdetection3d. OpenMMLab's next-generation platform for general 3D object detection.

plane_fitter. C++

Unity-LerpShowcase. A project to compare different ways of doing networked Linear interpolation.

You-Dont-Need-GUI. Stop relying on GUI; CLI **ROCKS**

Ultra-Fast-Lane-Detection. Ultra Fast Structure-aware Deep Lane Detection (ECCV 2020)

paint. Fluid Paint - http://david.li/paint

docker-unity3d. Unity3d in docker for targeting Windows and Linux

Marching-Cubes-Terrain. Marching Cubes terrain implementation in Unity using the Job System and the Burst compiler

sense. Enhance your application with the ability to see and interact with humans using any RGB camera.

tilt-brush. C#

Cylinder3D. Rank 1st in the leaderboard of SemanticKITTI semantic segmentation (both single-scan and multi-scan) (Nov. 2020) (CVPR2021 Oral)

Pugrad. Perceptually uniform colormap generator for Unity

raytracing.github.io. Main Web Site (Online Books)

Mirror. #1 Open Source Unity Networking Library

bakery-hdrp-shaders. HDRP-compatible shaders for Bakery

abrash-black-book. Markdown source for Michael Abrash's Graphics Programming Black Book

MultiplayerFPS-Tutorial. C#

FirstPersonController. a tutorial for first person controller on unity

Coin-Allocator. Bitcoin/Altcoin/USD trading bot. Was moderately profitable, until the exchange got hacked. No longer under active development.

openpilot. openpilot is an operating system for robotics. Currently, it upgrades the driver assistance system on 300+ supported cars.

lidar_perception. A lidar perception system, including ground-filter, cluster, minbox, tracking and state estimation.

ddsp. DDSP: Differentiable Digital Signal Processing

the_silver_searcher. A code-searching tool similar to ack, but faster.

rs_pbrt. Rust crate to implement a counterpart to the PBRT book's (3rd edition) C++ code. See also https://www.rs-pbrt.org/about ...

react-pwa-reference. A project boilerplate and reference example of a universal, reactiflux, progressive web application

esbuild. An extremely fast bundler for the web

nannou. A Creative Coding Framework for Rust.

pb_CSG. A C# port of CSG.js by Evan W (http://evanw.github.io/csg.js/).

stdx. The missing batteries of Rust

rex-gym. OpenAI Gym environments for an open-source quadruped robot (SpotMicro)

connectr. A super lightweight Spotify controller

PcxEffects3. Unity VFX with point cloud

building_tools. Building generation addon for blender

kinect-openni-bvh-saver. This project is based on OpenNI2, NITE2, and OpenCV2, it will automatically save many skeleton animation clips to bvh files.

HoudiniEngineForBlender. Branch of Blender featuring a Houdini Engine based modifier

deno. A modern runtime for JavaScript and TypeScript.

UGATIT. Official Tensorflow implementation of U-GAT-IT: Unsupervised Generative Attentional Networks with Adaptive Layer-Instance Normalization for Image-to-Image Translation (ICLR 2020)