This is your work, valued
is-my-problem-new. Semantic search for competitive programming problems
★ 338CFBooster. Python
★ 60fjzzq2002.github.io. JavaScript
★ 52winter_mutual_training_contest_2018. 2018年集训队冬令营前胡策个人吐槽仓库
★ 35pizza. Code repository for "The Clock and the Pizza: Two Stories in Mechanistic Explanation of Neural Networks"
★ 20random_transformers. Official code for "Algorithmic Capabilities of Random Transformers" (NeurIPS 2024)
★ 15WeightWatch. Official Repository of Paper "Watch the Weights: Unsupervised monitoring and control of fine-tuned LLMs"
★ 14cpideas. Use GPT-3 to generate competitive programming ideas.
★ 12livepaper. JavaScript
★ 5QQDuelBot. A bot to make codeforces duels in QQ groups
★ 4atcoder_code_grabber. A tool to grab atcoder codes
★ 3learn-language-by-pe. Haskell
★ 2MiniShader. A Simple Renderer
★ 2DOVICTheGame. The game named DOVIC.
★ 1HackMIT2022Demo. A social / blog platform where you can't read too much. In Beaver Dam, meet something new every day.
★ 14chess. C++
★ 1april_fools_group_delivery. HTML
★ 1bzoj-mover. port to uoj
★ 1conversation-tampering. Do LLMs notice when their conversation history has been silently tampered with?
★ 1nanoNLA. minimal implementation of Natural Language Autoencoders (Anthropic, 2026)
★ 11ODCV-Bench. A Benchmark for Evaluating Outcome-Driven Constraint Violations in Autonomous AI Agents
★ 13flash-linear-attention. 🚀 Efficient implementations for emerging model architectures
★ 5.3khumanization-by-iterative-paraphrasing. Python
★ 5Countdown-Code. A testbed for studying the emergence and generalization of reward hacking
★ 9CanonicalLean. A Lean tactic for Canonical, a search procedure for terms in dependent type theory.
★ 129Pando. Pando: Do Interpretability Methods Work When Models Won't Explain Themselves?
★ 5djinn. Generating, validating and running exploitable verifiable coding problems
★ 10terminal-wrench. Dataset of hackable TerminalBench-style tasks and exploit trajectories
★ 30utterances. :crystal_ball: A lightweight comments widget built on GitHub issues
★ 9.7klatex-document-skill. Universal LaTeX document skill for Claude Code: 27 templates, 27 scripts, 26 reference guides. Made with Claude Code on ✦ HappyCapy AI ✦ platform
★ 600pv-tool. Automaticly generate kinetic typography
★ 386hodoscope. Analyze AI agent trajectories: extract actions, summarize, embed, and visualize.
★ 116obfuscation-atlas. The Obfuscation Atlas: Mapping Where Honesty Emerges in RLVR with Deception Probes
★ 13ms-swift. Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.6, DeepSeek-V4, GLM-5.1, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, GLM4.5v, Gemma4, Llava, Phi4, ...) (AAAI 2025).
★ 15kopenTSNE. Extensible, parallel implementations of t-SNE
★ 1.6kpi. AI agent toolkit: unified LLM API, agent loop, TUI, coding agent CLI
★ 69kseer. This was designed for interp researchers who want to do research on or with interp agents to give quality of life improvements and fix some of the annoying things you get from only using Claude code out of the box
★ 146rl-rewardhacking. Python
★ 44togasat. A Header-Only CDCL SAT Solver for Programming Contest
★ 74rendercv. Resume builder for academics and engineers
★ 17kpopsicle. Popsicle aims to bridge the JUCE c++ framework to python.
★ 203typer. Typer, build great CLIs. Easy to code. Based on Python type hints.
★ 20kweight-steering. Python
★ 10eliciting-secret-knowledge. Code repository for "Eliciting Secret Knowledge from Language Models"
★ 23scribe-task-suite. A suite of interpretability tasks to evaluate agents using Scribe for notebook access
★ 18scribe. Python
★ 85diffing-toolkit. A toolkit that provides a range of model diffing techniques including a UI to visualize them interactively.
★ 76nnterp. Unified access to Large Language Model modules using NNsight
★ 115MiMo-Audio. MiMo-Audio: Audio Language Models are Few-Shot Learners
★ 1.1khexo-theme-one-paper. 专注于写作,模拟纸张阅读感受的轻量 Hexo 主题。
★ 157hexo-theme-minimalism. hexo 极简主题
★ 328kitten-tts-web-demo. Kitten TTS web demo using tansformers.js
★ 100Awesome-Marp. 🤙 Easy replacement for LaTeX Beamer! 🥂 custom Marp templates with a selection of over a dozen themes
★ 1kdata_laundering. Data Laundering: Artificially Boosting Benchmark Results through Knowledge Distillation
★ 11slime. slime is an LLM post-training framework for RL Scaling.
★ 7.4kBlackFriday-GPTs-Prompts. List of free GPTs that doesn't require plus subscription
★ 9.6knlparam. Augmenting Statistical Models with Natural Language Parameters
★ 28circuit-tracer. Python
★ 2.9kscripts. Python
★ 5BackdoorLLM. [NeurIPS 2025] BackdoorLLM: A Comprehensive Benchmark for Backdoor Attacks and Defenses on Large Language Models
★ 315safety-tooling. Inference API for many LLMs and other useful tools for empirical research
★ 132circuit-breakers-eval. Independent robustness evaluation of Improving Alignment and Robustness with Short Circuiting
★ 18AIME-Preview. Python
★ 84strongreject. Repository for "StrongREJECT for Empty Jailbreaks" paper
★ 157SafeUnlearning. Safe Unlearning: A Surprisingly Effective and Generalizable Solution to Defend Against Jailbreak Attacks
★ 32OLMo. Modeling, training, eval, and inference code for OLMo
★ 6.6kstrong_reject. Python
★ 144polarity-music-tools. 🔥 Bitwig presets by polarity for you to use. Every week new stuff for bitwig & popular vsts.
★ 493CP-Templates. Competitive Programming Templates
★ 166library. Algorithms in C++17
★ 15llm_rules. RuLES: a benchmark for evaluating rule-following in language models
★ 255awesome_LLM-harmful-fine-tuning-papers. A survey on harmful fine-tuning attack for large language model (ACM CSUR)
★ 247360-LLaMA-Factory. adds Sequence Parallelism into LLaMA-Factory
★ 607LlamaFactory. Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
★ 73kpromptfoo. Test your prompts, agents, and RAGs. Red teaming/pentesting/vulnerability scanning for AI. Compare performance of GPT, Claude, Gemini, DeepSeek, and more. Simple declarative configs with command line and CI/CD integration. Used by OpenAI and Anthropic.
★ 23kAutomated-Multi-Turn-Jailbreaks. Python
★ 139nanoGCG. A fast + lightweight implementation of the GCG algorithm in PyTorch
★ 343repomix. 📦 Repomix is a powerful tool that packs your entire repository into a single, AI-friendly file. Perfect for when you need to feed your codebase to Large Language Models (LLMs) or other AI tools like Claude, ChatGPT, DeepSeek, Perplexity, Gemini, Gemma, Llama, Grok, and more.
★ 27krefusal_direction. Code and results accompanying the paper "Refusal in Language Models Is Mediated by a Single Direction".
★ 417persona-hub. Official repo for the paper "Scaling Synthetic Data Creation with 1,000,000,000 Personas"
★ 1.6kDeepSeek-R1.
★ 92knnsight. The nnsight package enables interpreting and manipulating the internals of deep learned models.
★ 981PyMuPDF-Utilities. Demos, examples and utilities using PyMuPDF
★ 721REPA. [ICLR'25 Oral] Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think
★ 1.7knih-plug. Rust VST3 and CLAP plugin framework and plugins - because everything is better when you do it yourself
★ 2.9kds_store_exp. A .DS_Store file disclosure exploit. It parses .DS_Store file and downloads files recursively.
★ 1.7karc-agi-benchmarking. Testing baseline LLMs performance across various models
★ 351surya. OCR, layout analysis, reading order, table recognition in 90+ languages
★ 21kpianoteq-pi. A quick way to install Pianoteq and tweak your system on Raspberry Pi ⚡️
★ 151vocos. Vocos: Closing the gap between time-domain and Fourier-based neural vocoders for high-quality audio synthesis
★ 1.1kRerender_A_Video. [SIGGRAPH Asia 2023] Rerender A Video: Zero-Shot Text-Guided Video-to-Video Translation
★ 3klaunchpad.py. Novation Launchpad (and Midi Fighter) control suite for Python
★ 382rpi-rgb-led-matrix. Controlling up to three chains of 64x64, 32x32, 16x32 or similar RGB LED displays using Raspberry Pi GPIO
★ 4.3ktransformer-debugger. Python
★ 4.1kLLM4Decompile. Reverse Engineering: Decompiling Binary Code with Large Language Models
★ 6.7kInternVL. [CVPR 2024 Oral] InternVL Family: A Pioneering Open-Source Alternative to GPT-4o. 接近GPT-4o表现的开源多模态对话模型
★ 10kARC-AGI. The Abstraction and Reasoning Corpus
★ 4.8kseq_icl. Jupyter Notebook
★ 54dspy. DSPy: The framework for programming—not prompting—language models
★ 36kFooocus. Focus on prompting and generating
★ 51kbitsandbytes. Accessible large language models via k-bit quantization for PyTorch.
★ 8.3klm-evaluation-harness. A framework for few-shot evaluation of language models.
★ 13krerope. Rectified Rotary Position Embeddings
★ 393TinyLlama. The TinyLlama project is an open endeavor to pretrain a 1.1B Llama model on 3 trillion tokens.
★ 9kMathPile. [NeurlPS D&B 2024] Generative AI for Math: MathPile
★ 418magic-cpp. A C++20 header-only library that supports powerful reflection for C++
★ 325tokencost. Easy token price estimates for 400+ LLMs. TokenOps.
★ 2ktensor-trust-data. Dataset for the Tensor Trust project
★ 49kge. LibKGE - A knowledge graph embedding library for reproducible research
★ 835BIG-bench. Beyond the Imitation Game collaborative benchmark for measuring and extrapolating the capabilities of language models
★ 3.2kawesome-RLHF. A curated list of reinforcement learning with human feedback resources (continually updated)
★ 4.4kevalplus. Rigourous evaluation of LLM-synthesized code - NeurIPS 2023 & COLM 2024
★ 1.8knotero. A Zotero plugin for syncing items and notes into Notion
★ 3.2kReinMax. Beyond Straight-Through
★ 110pythia. The hub for EleutherAI's work on interpretability and learning dynamics
★ 2.8kBIMT. Brain-Inspired Modular Training (BIMT), a method for making neural networks more modular and interpretable.
★ 177character-tokenizer. A character tokenizer for Hugging Face Transformers
★ 32true. Code and data accompanying the paper "TRUE: Re-evaluating Factual Consistency Evaluation".
★ 92chatgpt_system_prompt. A collection of GPT system prompts and various prompt injection/leaking knowledge.
★ 11kfunction_vectors. Function Vectors in Large Language Models (ICLR 2024)
★ 199make-real. Draw a ui and make it real
★ 5.4kbaukit. Python
★ 253zero123plus. Code repository for Zero123++: a Single Image to Consistent Multi-view Diffusion Base Model.
★ 2kMathGLM. Official Pytorch Implementation for MathGLM
★ 329tinygrad. You like pytorch? You like micrograd? You love tinygrad! ❤️
★ 33kAutomatic-Circuit-Discovery. Jupyter Notebook
★ 293litgpt. 20+ high-performance LLMs with recipes to pretrain, finetune and deploy at scale.
★ 13kTurboBench. Compression Benchmark
★ 368MiraiMidiProduce. :musical_score:在线作曲插件 | online music composing mirai plugin
★ 39SciencePlots. Matplotlib styles for scientific plotting
★ 9kmusic-generation-toolbox. Toolbox for generating music
★ 28wiliwili. 第三方B站客户端,目前可以运行在PC全平台、PSVita、PS4 、Xbox 和 Nintendo Switch上
★ 5.3kTree-Generator. Help competitive programming problem setters to generate different kinds of trees :evergreen_tree:
★ 131TransformerLens. A library for mechanistic interpretability of GPT-style language models
★ 3.7knanoGPT. The simplest, fastest repository for training/finetuning medium-sized GPTs.
★ 61kCefDetectorX. 【升级版-Electron】Check how many CEFs are on your computer. 检测你电脑上有几个CEF.
★ 2.5kvirtual_piano. 钢琴瀑布流+五线谱+和弦识别
★ 85point-e. Point cloud diffusion for 3D model synthesis
★ 6.9ktiktoken. tiktoken is a fast BPE tokeniser for use with OpenAI's models.
★ 19kni. 💡 Use the right package manager
★ 8.3kriffusion-hobby. Stable diffusion for real-time music generation
★ 3.9ksacrebleu. Reference BLEU implementation that auto-downloads test sets and reports a version string to facilitate cross-lab comparisons
★ 1.3knni. An open source AutoML toolkit for automate machine learning lifecycle, including feature engineering, neural architecture search, model compression and hyper-parameter tuning.
★ 14kysfx. Hosting library for JSFX
★ 247TextGAN-PyTorch. TextGAN is a PyTorch framework for Generative Adversarial Networks (GANs) based text generation models.
★ 906PainterEngine. PainterEngine is a application/game engine with software renderer,PainterEngine can be transplanted to any platform that supports C
★ 3.3kvision-transformers-cifar10. Let's train vision transformers (ViT) for cifar 10 / cifar 100!
★ 719Poetry. 非常全的古诗词数据,收录了从先秦到现代的共计85万余首古诗词。
★ 1.8ksynth. An attempt at making a synth using Python
★ 184ChineseBQB. 🇨🇳 Chinese sticker pack,More joy / 表情包的博物馆, Github最有毒的仓库, 中国表情包大集合, 聚欢乐~
★ 16kstable-diffusion-webui. Stable Diffusion web UI
★ 164kEasyVtuber. Based on Talking-head-anime 3, works like Vtube Studio.
★ 3kpedalboard. 🎛 🔊 A Python library for audio.
★ 6.2kDeepSpeed-MII. MII makes low-latency and high-throughput inference possible, powered by DeepSpeed.
★ 2.1kutaformatix3. An application for converting projects among singing voice synthesizer softwares.
★ 347word2word. Easy-to-use word-to-word translations for 3,564 language pairs.
★ 367composer. Supercharge Your Model Training
★ 5.5kMUSE. A library for Multilingual Unsupervised or Supervised word Embeddings
★ 3.2ktorchdynamo. A Python-level JIT compiler designed to make unmodified PyTorch programs faster.
★ 1.1kwhisper. Robust Speech Recognition via Large-Scale Weak Supervision
★ 105kAITemplate. 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.
★ 4.7ksentence-transformers. State-of-the-Art Embeddings, Retrieval, and Reranking
★ 19kgpt-paper-title-generator. Generating paper titles (and more!) with GPT trained on data scraped from arXiv.
★ 148k-diffusion. Karras et al. (2022) diffusion models for PyTorch
★ 2.6kmimikatz. A little tool to play with Windows security
★ 22kml4a. A python library and collection of notebooks for making art with machine learning.
★ 1.6kRWKV-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.
★ 15kminGPT-tuned. A *tuned* minimal PyTorch re-implementation of the OpenAI GPT (Generative Pretrained Transformer) training
★ 118minGPT. A minimal PyTorch re-implementation of the OpenAI GPT (Generative Pretrained Transformer) training
★ 25kDiffusion-LM. Diffusion-LM
★ 1.2kECDICT. Free English to Chinese Dictionary Database
★ 7.9kChinese-Word-Vectors. 100+ Chinese Word Vectors 上百种预训练中文词向量
★ 12kTokyuSurvival. A Visual Novel Game
★ 118symbolic-music-diffusion. Symbolic Music Generation with Diffusion Models
★ 280probot. 🤖 A framework for building GitHub Apps to automate and improve your workflow
★ 9.6kiris. Transformers are Sample-Efficient World Models. ICLR 2023, notable top 5%.
★ 895tauri. Build smaller, faster, and more secure desktop and mobile applications with a web frontend.
★ 109kCSGO-Toolbox. CSGO工具箱:一个为CSGO游戏的各个方面带来便利的工具集合
★ 175ultimatevocalremovergui. GUI for a Vocal Remover that uses Deep Neural Networks.
★ 25kSummer2026-Internships. Summer 2026 software engineering, data science, AI, quant, product management, and hardware internship postings. Updated daily by Simplify and Pitt CSC.
★ 45kColossalAI. Making large AI models cheaper, faster and more accessible
★ 41kAutoEq. Automatic headphone equalization from frequency responses
★ 16kDeepFaceLive. Real-time face swap for PC streaming or video calls
★ 31kcode-golf. A game designed to let you show off your code-fu by solving problems in the least number of characters.
★ 1.3ksvg-spinners. A collection of 24 x 24 dp SVG spinners! (CSS & SMIL)
★ 7ktuc. When cut doesn't cut it
★ 820htmacros. Hypertext macros for managing websites using LaTeX-like syntax
★ 3metaseq. Repo for external large-scale work
★ 6.5krun. 润学全球官方指定GITHUB,整理润学宗旨、纲领、理论和各类润之实例;解决为什么润,润去哪里,怎么润三大问题; 并成为新中国人的核心宗教,核心信念。
★ 32kcli. 🥧 HTTPie CLI — modern, user-friendly command-line HTTP client for the API era. JSON support, colors, sessions, downloads, plugins & more.
★ 38kSmartGuitarAmp. Guitar plugin made with JUCE that uses neural networks to emulate a tube amplifier.
★ 1.3kSmartAmpPro. Guitar plugin using neural networks to capture real amps and pedals
★ 208Chameleon. Vintage guitar amp using neural networks.
★ 90TS-M1N3. TS-9 guitar pedal clone using neural networks.
★ 62synthv-suzu-scripts. A collection of Synthesizer V Scripts by Suzumof.
★ 17rocq-tricks. Tricks you wish the Coq manual told you [maintainer=@tchajed]
★ 552CodeRetriever. Source code downloader for competitive programming platforms
★ 17HowToCook. Programmer's guide about how to cook at home.
★ 101ksensible-side-buttons. A macOS menu bar app that enables system-wide navigation functionality for the side buttons on third-party mice.
★ 2.1kspring22. Problem Sets for MIT 6.822 Formal Reasoning About Programs, Spring 2022
★ 20frap. Formal Reasoning About Programs
★ 730pure. A set of small, responsive CSS modules that you can use in every web project.
★ 24kpyo. Python DSP module
★ 1.4kdicebear. DiceBear is an avatar library for designers and developers. 🌍
★ 9kLxgwWenKai. An unprofessional open-source Chinese font derived from Fontworks' Klee One. 一款非专业的开源中文字体,基于 FONTWORKS 出品字体 Klee One 衍生。
★ 25kminifaker. A lightweight alternative to faker.js
★ 75formalising-mathematics-2022. Lean 3 material for Kevin Buzzard's Jan-Mar 2022 course on formalising mathematics. Lean 4 version available here: https://github.com/ImperialCollegeLondon/formalising-mathematics-2024
★ 121Tone.js. A Web Audio framework for making interactive music in the browser.
★ 15kavataaars-generator. Simple generator React app for avataaars
★ 3kdoodle2search. Doodle to Search: Practical Zero Shot Sketch Based Image Retrieval
★ 81MockingBird. 🚀Clone a voice in 5 seconds to generate arbitrary speech in real-time
★ 37kPaddlePaddle-DeepSpeech. 基于PaddlePaddle实现的语音识别,中文语音识别。项目完善,识别效果好。支持Windows,Linux下训练和预测,支持Nvidia Jetson开发板预测。
★ 761ASRT_SpeechRecognition. A Deep-Learning-Based Chinese Speech Recognition System 基于深度学习的中文语音识别系统
★ 8.4kKanaQuiz. Hiragana/Katakana Speed Reading Quiz in Command Line !! :sunglasses:
★ 175TeXnique. A LaTeX Typesetting Game
★ 338ArchiSteamFarm. C# application with primary purpose of farming Steam cards from multiple accounts simultaneously.
★ 14kfree-midi-chords. A collection of free MIDI chords and progressions ready to be used in your DAW, Akai MPC, or Roland MC-707/101
★ 2.3kyyjson. The fastest JSON library in C
★ 3.8kcode-library. Templates, algorithms and data structures implemented and collected for programming contests.
★ 3.6k