Nat Friedman

RedPajama-Data. The RedPajama-Data repository contains code for preparing large datasets for training large language models.

Vesuvius-First-Letters. Python

Crackle-Viewer. Vesuvius Challenge Ink Crackle Labeling Tool for Scroll Segmentations

aider. aider is AI pair programming in your terminal

khartes. Python

llama.cpp. LLM inference in C/C++

vesuvius-blender. Explore the X-ray scans from the Vesuvius Challenge in Blender.

samsung-frame-art. A small script that makes it easy to fling a folder of images onto the Samsung Frame TV

WebGPT. Run GPT model on the browser with WebGPU. An implementation of GPT inference in less than ~1500 lines of vanilla Javascript.

VolumeAnnotate. Virtual Unwrapping Tool for the Vesuvius Challenge

langflow. Langflow is a powerful tool for building and deploying AI-powered agents and workflows.

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

embedland. A collection of text embedding experiments

elk. Keeping language models honest by directly eliciting knowledge encoded in their activations.

mctx. Monte Carlo tree search in JAX

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

AITemplate. AITemplate is a Python framework which renders neural network into high performance CUDA/HIP C++ code. Specialized for FP16 TensorCore (NVIDIA GPU) and MatrixCore (AMD GPU) inference.

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

RWKV-LM. RWKV (pronounced RwaKuv) is an RNN with great LLM performance, which can also be directly trained like a GPT transformer (parallelizable). We are at RWKV-7 "Goose". So it's combining the best of RNN and transformer - great performance, linear time, constant space (no kv-cache), fast training, infinite ctx_len, and free sentence embedding.

LaTeX-OCR. pix2tex: Using a ViT to convert images of equations into LaTeX code.

FasterTransformer. Transformer related optimization, including BERT, GPT

cbp-translate. Python

tiktoken. tiktoken is a fast BPE tokeniser for use with OpenAI's models.

gpt-commit-summarizer. JavaScript

tier. The easiest way to add pricing to your SaaS. Get billing over with.

thingies. Various little scripts I use.

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

yfs. Synchronize text files between browser and disk using Yjs and the File System Access API

CodeGen. CodeGen is a family of open-source model for program synthesis. Trained on TPU-v4. Competitive with OpenAI Codex.

litestream. Streaming replication for SQLite.

instapaper-to-omnivore-import. 📖 Import Instapaper content to Omnivore

omnivore. Omnivore is a complete, open source read-it-later solution for people who like reading.

promnesia. Another piece of your extended mind

laundry-symbols. Every laundry symbol as a 24x24 SVG

AltStore. AltStore is an alternative app store for non-jailbroken iOS devices.

XUAN.

modern-unix. A collection of modern/faster/saner alternatives to common unix commands.

serenity. The Serenity Operating System 🐞

umami. Umami is a modern, privacy-focused analytics platform. An open-source alternative to Google Analytics, Mixpanel and Amplitude.

LegoMicroscope. To learn about optics and microscopy, we generated a simple to build lego microscope that does not need precision optics and 3D printed parts.

opal. Policy and data administration, distribution, and real-time updates on top of Policy Agents (OPA, Cedar, ...)

intellij-codespaces. Dockerfile

superfolder-covid-mrna-vaccines. SuperFolder COVID mRNA vaccines, stabilized for in vitro storage and shipping

ohm. A library and language for building parsers, interpreters, compilers, etc.

CHIRP. A DFIR tool written in Python.

data-transfer-project. The Data Transfer Project makes it easy for platforms to build interoperable user data portability features. We are establishing a common framework, including data models and protocols, to enable direct transfer of data both into and out of participating online service providers.

virtual-unfolding. "virtual unfolding" computational pipeline

ghostwriter. Text editor for Markdown

mold. mold: A Modern Linker 🦠

VICAR.

fprime. F´ - A flight software and embedded systems framework

httpstat. It's like curl -v, with colours.

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

smile. When ASCII art is the executable

github-script. Write workflows scripting the GitHub API in JavaScript

openwifipass. An open source implementation of Apple's Wi-Fi Password Sharing protocol in Python.

Charts. Beautiful charts for iOS/tvOS/OSX! The Apple side of the crossplatform MPAndroidChart.

Rectangle. Move and resize windows on macOS with keyboard shortcuts and snap areas

resources. Tools, data, and contact lists relevant to The disclose.io Project.

horrifying-pdf-experiments. :syringe: Stuff which works in Chrome and maybe Acrobat and Foxit.

SaveAmphetamine. Apple has threatened to remove Amphetamine from the App Store.

artichoke. 💎 Artichoke is a Ruby made with Rust

DnaChisel. :pencil2: A versatile DNA sequence optimizer

TabFS. 🗄 Mount your browser tabs as a filesystem.

jest-image-snapshot. ✨ Jest matcher for image comparisons. Most commonly used for visual regression testing.

macadmin-scripts. Scripts of possible interest to macOS admins

CovidExtractor. My Covid Extractor

automerge-classic. A JSON-like data structure (a CRDT) that can be modified concurrently by different users, and merged again automatically.

SwiftBar. Powerful macOS menu bar customization tool

youtube-dl. Command-line program to download videos from YouTube.com and other video sites

runner. The Runner for GitHub Actions :rocket:

toolkit. The GitHub ToolKit for developing GitHub Actions.

covid-19-data. A repository of data on coronavirus cases and deaths in the U.S.

xbar. Put the output from any script or program into your macOS Menu Bar (the BitBar reboot)

go-bitbar. Go library for building BitBar plugins

dn. 💾 dn - offline full-text search and archiving for your Chromium-based browser.

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

minGPT. A minimal PyTorch re-implementation of the OpenAI GPT (Generative Pretrained Transformer) training

act. Run your GitHub Actions locally 🚀

covid-tracker-app. COVID Tracker App Repository

axi. Library for working with the AxiDraw v3 pen plotter.

scipython-maths. A repository of small maths projects explored with Python

a-shell. A terminal for iOS, with multiple windows

covid-sanity. Aspires to help the influx of bioRxiv / medRxiv papers on COVID-19

covid19_scenarios. Models of COVID-19 outbreak trajectories and hospital demand

COVID-19. Novel Coronavirus (COVID-19) Cases, provided by JHU CSSE

big-mac-data. Data and methodology for the Big Mac index

around_the_world. Find the shortest path between the continents

cli. GitHub’s official command line tool

simple-twitter. A bare-bones Twitter clone implemented in a single file

action-tmate. Debug your GitHub Actions via SSH by using tmate to get access to the runner system itself.

vscode. Visual Studio Code

gMusic. This is a multi platform music player.

WhisperJar. WhisperJar

django-facebook. Integrate Facebook into your Django application.

maccore. MacCore contains the shared code between MonoTouch and MonoMac

bottlenose. A Python wrapper for the Amazon Product Advertising API.

trackmac. A simple time tracker for Mac OS X

playnice. A tool to autmatically update Google Latitude with your iPhone location. Put it in Cron.

playnice. A tool to autmatically update Google Latitude with your iPhone location. Put it in Cron.