Masafumi Oyamada

leaf. Terminal Markdown previewer — GUI-like experience.

CursorBounds. A Swift package to retrieve the position and bounds of the text cursor (caret) in macOS applications using the Accessibility API.

OpenSuperWhisper. macOS dictation app

lexical. Lexical is an extensible text editor framework that provides excellent reliability, accessibility and performance.

ftr-site-config. Site-specific article extraction rules to aid content extractors, feed readers, and 'read later' applications.

iclr2026-affiliations. PDF-derived institutional affiliations for 5,356 ICLR 2026 accepted papers — full pipeline (scrape → parse → render), clean dataset (CSV + XLSX), and treemap charts.

ds4. DeepSeek 4 Flash and PRO local inference engine for Metal, CUDA and ROCm

stanford-cme-296-diffusion-large-vision-models. VIP cheatsheet for Stanford's CME 296 Diffusion and Large Vision Models

reasoning-memory. Procedural Knowledge at Scale Improves ReasoningThis repository contains the minimal, end-to-end pipeline for reproducing the paper results generate a procedural knowledge datastore, build retrieval indices, run retrieval, perform model rollouts with retrieved subroutines, and filter the samples to output the final metrics.

typia. Super-fast/easy runtime validators and serializers via transformation

ai-deadlines. ⏰ AI conference deadline countdowns

parameter-golf. Train the smallest LM you can that fits in 16MB. Best model wins!

DeepResearch. Tongyi Deep Research, the Leading Open-source Deep Research Agent

rllm. Democratizing Reinforcement Learning for LLMs

azooKey-Desktop. azooKey-Desktop is an open-source Japanese input method for macOS, written in Swift and powered by the Zenzai neural kana-kanji converter. It provides live conversion, optional LLM-based “Magic Conversions”, and Tuner-backed personalization for a smooth, desktop typing experience.

optillm. Optimizing inference proxy for LLMs

eza. A modern alternative to ls

vibe-kanban. Get 10X more out of Claude Code, Codex or any coding agent

Bridge-LLM-reasoning. Behavior Injection: Preparing Language Models for Reinforcement Learning (NeurIPS 2025)

mcp-chrome. Chrome MCP Server is a Chrome extension-based Model Context Protocol (MCP) server that exposes your Chrome browser functionality to AI assistants like Claude, enabling complex browser automation, content analysis, and semantic search.

ccresume. A CUI tool for browsing and resuming Claude Code conversations

twscrape. Python library and CLI for X/Twitter scraping with multi-account rotation and built-in rate-limit handling.

deep-research. An AI-powered research assistant that performs iterative, deep research on any topic by combining search engines, web scraping, and large language models. The goal of this repo is to provide the simplest implementation of a deep research agent - e.g. an agent that can refine its research direction overtime and deep dive into a topic.

suna. The Company AI Command Center

owl. 🦉 OWL: Optimized Workforce Learning for General Multi-Agent Assistance in Real-World Task Automation

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

docs. Documentation for the Model Context Protocol (MCP)

nova-act. Amazon Nova Act is an AWS service for building and deploying highly reliable AI agents that automate UI-based workflows at scale.

OpenManus. No fortress, purely open ground. OpenManus is Coming.

stagehand. The SDK For Browser Agents

wxt. ⚡ Next-gen Web Extension Framework

browser-use. 🌐 Make websites accessible for AI agents. Automate tasks online with ease.

edamagit. Magit for VSCode

docling-parse. Simple package to extract text with coordinates from programmatic PDFs

cline. Autonomous coding agent as an SDK, IDE extension, or CLI assistant.

Awesome-LLM-Strawberry. A collection of LLM papers, blogs, and projects, with a focus on OpenAI o1 🍓 and reasoning techniques.

zellij. A terminal workspace with batteries included

VILA. VILA is a family of state-of-the-art vision language models (VLMs) for diverse multimodal AI tasks across the edge, data center, and cloud.

dspy. DSPy: The framework for programming—not prompting—language models

AppAgent. AppAgent: Multimodal Agents as Smartphone Users, an LLM-based multimodal agent framework designed to operate smartphone apps.

albumentations. Fast and flexible image augmentation library. Paper about the library: https://www.mdpi.com/2078-2489/11/2/125

PowerInfer. High-speed Large Language Model Serving for Local Deployment

NeuroSurgeon. NeuroSurgeon is a package that enables researchers to uncover and manipulate subnetworks within models in Huggingface Transformers

chatgpt_system_prompt. A collection of GPT system prompts and various prompt injection/leaking knowledge.

argilla. Argilla is a collaboration tool for AI engineers and domain experts to build high-quality datasets

prompt-lookup-decoding. Simple speculative decoding technique, integrated in vLLM and transformers

InsTag. InsTag: A Tool for Data Analysis in LLM Supervised Fine-tuning

JapaneseEmbeddingEval. Jupyter Notebook

yarn. YaRN: Efficient Context Window Extension of Large Language Models

llama. Inference code for Llama models

ripgrep. ripgrep recursively searches directories for a regex pattern while respecting your gitignore

kanagawa.nvim. NeoVim dark colorscheme inspired by the colors of the famous painting by Katsushika Hokusai.

CTranslate2. Fast inference engine for Transformer models

obsidian-kindle-plugin. Sync your Kindle notes and highlights directly into your Obsidian vault

LongForm. Reverse Instructions to generate instruction tuning data with corpus examples

awesome-instruction-dataset. A collection of open-source dataset to train instruction-following LLMs (ChatGPT,LLaMA,Alpaca)

WhisperAPI-Youtube-Transcription. Using Whisper API to transcribe Youtube videos.

bloomz.cpp. C++ implementation for BLOOM

AutoGPT. AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.

Japanese-Alpaca-LoRA. Jupyter Notebook

LLM-As-Chatbot. LLM as a Chatbot Service

basaran. Basaran is an open-source alternative to the OpenAI text completion API. It provides a compatible streaming API for your Hugging Face Transformers-based text generation models.

voicevox_core. 無料で使える中品質なテキスト読み上げソフトウェア、VOICEVOXのコア

dolly. Databricks’ Dolly, a large language model trained on the Databricks Machine Learning Platform

mojxml2geojson. 法務省登記所備付地図データ（地図XML）をGeoJSONに変換するコンバータ

sb2md. sb2md converts Scrapbox notation to Markdown

userscripts. An open-source userscript manager for Safari

langchain. The agent engineering platform.

useDApp. Framework for rapid Dapp development. Simple. Robust. Extendable. Testable

arrow. 🏹 Better dates & times for Python

RSSHub. 🧡 Everything is RSSible

ethers.js. Complete Ethereum library and wallet implementation in JavaScript.

react-box. Truffle, Webpack and React boilerplate.

cloudflare-scraper. A package to bypass Cloudflare's protection

vfat-tools. JavaScript

awesome-taxonomy. A curated resource for taxonomy research

awesome-crawler. A collection of awesome web crawler,spider in different languages

react-chartjs-2. React components for Chart.js, the most popular charting library

nheqminer. Equihash miner for NiceHash

bert-japanese. BERT models for Japanese text.

scma. JavaScript

vscode-emacs-mcx. Awesome Emacs Keymap - VSCode emacs keybinding with multi cursor support

vscode-emacs. TypeScript

onnxmltools. ONNXMLTools enables conversion of models to ONNX

aws-toolkit-jetbrains. AWS Toolkit for JetBrains - a plugin for interacting with AWS from JetBrains IDEs

autohotkey_emacs_keymap. AutoHotkey script to simulate Emacs keybindings on Windows

pytorch-lightning. Pretrain, finetune ANY AI model of ANY size on 1 or 10,000+ GPUs with zero code changes.

mysql2sqlite. Converts MySQL dump to SQLite3 compatible dump

elasticsearch-analysis-kuromoji-ipadic-neologd. Elasticsearch's Analyzer for Kuromoji with Neologd

gensim. Topic Modelling for Humans

papermill. 📚 Parameterize, execute, and analyze notebooks

fastText. Library for fast text representation and classification.

jupyterlab-lsp. Coding assistance for JupyterLab (code navigation + hover suggestions + linters + autocompletion + rename) using Language Server Protocol

fastapi. FastAPI framework, high performance, easy to learn, fast to code, ready for production

javascript-typescript-langserver. JavaScript and TypeScript code intelligence through the Language Server Protocol

TinySegmenterMaker. Python

rakutenma. Rakuten MA - morphological analyzer (word segmentor + PoS Tagger) for Chinese and Japanese written purely in JavaScript.

Cica. プログラミング用日本語等幅フォント Cica(シカ)

aozorabunko. HTML

tqdm. :zap: A Fast, Extensible Progress Bar for Python and CLI

zprint. Executables, uberjar, and library to beautifully format Clojure and Clojurescript source code and s-expressions.

zsh-autosuggestions. Fish-like autosuggestions for zsh

jsedn. javascript implementation of edn

k-goku. A configuration using GokuRakuJoudo to generate Karabiner profile.

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

GokuRakuJoudo. config karabiner with ease

subword-nmt. Unsupervised Word Segmentation for Neural Machine Translation and Text Generation

clip-as-service. 🏄 Scalable embedding, reasoning, ranking for images and sentences with CLIP

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.

rdflib. RDFLib is a Python library for working with RDF, a simple yet powerful language for representing information.

doccano. Open source annotation tool for machine learning practitioners.

Sourcetrail. Sourcetrail - free and open-source interactive source explorer

kit. 🧱 Describe your site, AI builds it, you own it as Markdown. Snap together Tailwind blocks like Lego — landing pages, blogs, portfolios, docs & more. No AI slop. Free to deploy anywhere 👇

node-fx-sync. Node.js client for Firefox Sync

mark.js. JavaScript keyword highlighting. Mark text with options that fit every application. Also available as jQuery plugin.

node-fx-sync. Node.js client for Firefox Sync

vue-virtual-scroller. ⚡️ Blazing fast scrolling for any amount of data

lsp-mode. Emacs client/library for the Language Server Protocol

google-drive-ocamlfuse. FUSE filesystem over Google Drive

gluonts. Probabilistic time series modeling in Python

LM-LSTM-CRF. Empower Sequence Labeling with Task-Aware Language Model

slack-export-viewer. A Slack Export archive viewer that allows you to easily view and share your Slack team's export

ace. Ace (Ajax.org Cloud9 Editor)

tf-recsys. tf-recsys contains collaborative filtering (CF) model based on famous SVD and SVD++ algorithm. Both of them are implemented by tensorflow in order to utilize GPU acceleration.

md2sb-online. Online Cosense Converter

sb2md. Scrapbox contents -> Markdown

react-ga. React Google Analytics Module

astor. Python AST read/write

brat. brat rapid annotation tool (brat) - for all your textual annotation needs

HRL-RE. Joint Relation Extraction with Hierarchical Reinforcement Learning

ikeysnail. iKeySnail provides fully-configurable hardware keyboard functionalities for web browsing on iOS (iPadOS)

react-dropzone. Simple HTML5 drag-drop zone with React.js.

React-Redux-Flask. Boilerplate application for a Python/Flask JWT Backend and a Javascript/React/Redux Front-End with Material UI.

material-ui. Material UI: Comprehensive React component library that implements Google's Material Design. Free forever.

featuretools. An open source python library for automated feature engineering

pixiedust. Python Helper library for Jupyter Notebooks

nmslib. Non-Metric Space Library (NMSLIB): An efficient similarity search library and a toolkit for evaluation of k-NN methods for generic non-metric spaces.

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

frovedis. Framework of vectorized and distributed data analytics

anago. Bidirectional LSTM-CRF and ELMo for Named-Entity Recognition, Part-of-Speech Tagging and so on.

blink. Blink Mobile Shell for iOS (Mosh based)

org-mode. An Atom package for org-mode syntax highlighting

apt-cyg. Apt-cyg, an apt-get like tool for Cygwin

Probabilistic-matrix-factorization-in-Python. Probabilistic matrix factorization (PMF) in Python

recommend. recommendation system with python

polylearn. A library for factorization machines and polynomial networks for classification and regression in Python.

Open-XML-SDK. Open XML SDK by Microsoft

emacs-grammarly. an Emacs extension to send a text to/from Grammarly

bebop. Groovy WebExtension that offers command line interface like emacs helm for browsing.

webextensions-examples. Example Firefox add-ons created using the WebExtensions API

extension-boilerplate. ⚡️ A template for building cross browser extensions for Chrome, Opera & Firefox.

xkeysnail. Yet another keyboard remapping tool for X environment

python-xlib. XLib in pure Python (Py2/Py3 compatible)

pykeymacs. Emacs style keyboard macros implemented in Python

mendeley-python-sdk. Python SDK for the Mendeley API.

pnotify. Beautiful JavaScript notifications with Web Notifications support.

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

scholar.py. A parser for Google Scholar, written in Python

Surfingkeys. Map your keys for web surfing, expand your browser with javascript and keyboard.

pyro. Deep universal probabilistic programming with Python and PyTorch

lightning. Large-scale linear classification, regression and ranking in Python

CARSKit. Java-Based Context-aware Recommendation Library

MLC_toolbox. A MATLAB/OCTAVE library for Multi-Label Classification

dblp-python. A simple Python wrapper around the DBLP API, currently supporting author search and author and publication lookup.

org-pomodoro. pomodoro technique for org-mode

phillip. Abductive reasoner for NLP in C++

spacemacs. A community-driven Emacs distribution - The best editor is neither Emacs nor Vim, it's Emacs *and* Vim!

numbskull. Numba-based version of DimmWitted Gibbs sampler

company-mode. Modular in-buffer completion framework for Emacs

pix2pix. Image-to-image translation with conditional adversarial nets

gitbase. SQL interface to git repositories, written in Go. https://docs.sourced.tech/gitbase

ksuperkey. Linux utility that allows you to use the Super key both to open the start menu and as a modifier key in keyboard shortcuts

KaTeX. Fast math typesetting for the web.

timeago.js. :clock8: :hourglass: timeago.js is a tiny(2.0 kb) library used to format date with `*** time ago` statement.

fastFM. fastFM: A Library for Factorization Machines

superset. Apache Superset is a Data Visualization and Data Exploration Platform

react-bootstrap. Bootstrap components built with React

yarn. The 1.x line is frozen - features and bugfixes now happen on https://github.com/yarnpkg/berry

react-router. Declarative routing for React

fbone. Fbone (Flask bone) is a Flask (Python microframework) starter/template/bootstrap/boilerplate application.

flask-react-boilerplate. JavaScript

dropzone. Dropzone is an easy to use drag'n'drop library. It supports image previews and shows nice progress bars.

codemirror5. In-browser code editor (version 5, legacy)

jupyter-themes. Custom Jupyter Notebook Themes

jupyterlab. JupyterLab computational environment.

jupyter_contrib_nbextensions. A collection of various notebook extensions for Jupyter

mecab-ipadic-neologd. Neologism dictionary based on the language resources on the Web for mecab-ipadic

edward. A probabilistic programming language in TensorFlow. Deep generative models, variational inference.

hyperopt. Distributed Asynchronous Hyperparameter Optimization in Python

live-plugin. IntelliJ plugin for writing IntelliJ plugins at runtime ⚡️

mintty-color-schemes. Some color schemes for MinTTY

tkool-sandbox. JavaScript

dissolve-struct. Distributed solver library for large-scale structured output prediction, based on Spark. Project website:

prml-python. PythonでPRMLの題材ｺﾞﾆｮｺﾞﾆｮしてﾆﾖﾆﾖする場

PulseSensor_Amped_Arduino. PulseSensor Arduino code for BPM and Processing-Visualizer

cvxpy. A Python-embedded modeling language for convex optimization problems.

pystruct. Simple structured learning framework for python

foedus_code. FOEDUS main source code repository

DPMM. Dirichlet process mixture model code in Matlab. Sampling and variational.

dirichlet-process. Introduction to Nonparametric Bayes, Infinite Mixture Models, and the Dirichlet Process (+ McDonald's)