This is your work, valued
"Hell is other peoples code" - Jean Paul Sartre, if he were a software engineer
CX_DB8. a contextual, biasable, word-or-sentence-or-paragraph extractive summarizer powered by the latest in text embeddings (Bert, Universal Sentence Encoder, Flair)
★ 230Constrained-Text-Generation-Studio. Code repo for "Most Language Models can be Poets too: An AI Writing Assistant and Constrained Text Generation Studio" at the (CAI2) workshop, jointly held at (COLING 2022)
★ 217Language-games. Dead simple games made with word vectors.
★ 97DebateSum. Corresponding code repo for the paper at COLING 2020 - ARGMIN 2020: "DebateSum: A large-scale argument mining and summarization dataset"
★ 55llm_steer-oobabooga. Steer LLM outputs towards a certain topic/subject and enhance response capabilities using activation engineering by adding steering vectors, now in oobabooga text generation webui!
★ 46Active-Explainable-Classification. A set of tools for leveraging pre-trained embeddings, active learning and model explainability for effecient document classification
★ 29Python-Cooperative-Synapse-NeuroEvolution. A Python implementation of the "CoSyne" algorithim, as described in this paper: https://pdfs.semanticscholar.org/966e/41903b4aff42601a188bd7b26d71ef120d11.pdf
★ 25python-neuroevolution. An implementation of "Conventional Neuroevolution" - evolving ANNs without backpropegation
★ 9DebateKG. Code Repo for the DebateGraph paper
★ 8Genetic-Algorithims-Python. Some fun code I wrote. One file does string matching and another one solves the Knapsack problem.
★ 7Bright. Measure how bright your github repo shines, and learn about interesting work that the people who were (or could have been) inspired by your repo have done
★ 5ECLAT-Association-Rule-Mining. An implementation of the Equivalence Class Transformation Association Rule Mining algorithim in Python
★ 4debate2vec. Word-vectors created from a large corpus of competative debate evidence
★ 4Hellisotherpeople.
★ 2DeepDebater. A Fully Automated and Choreographed Competitive Policy Debate System
★ 2Geist. A philosophy-inspired roguelike with Dijkstra-Maps and Unique Mechanics!
★ 2Simulated-Annealing-TSP-Numba. Using a metaheaurisitic technique called Simulated Annealing to solve the Traveling Salesman Problem.
★ 2llm_steer. Steer LLM outputs towards a certain topic/subject and enhance response capabilities using activation engineering by adding steering vectors
★ 1openchamber. Desktop and web interface for OpenCode AI agent
★ 7koh-my-pi. ⌥ AI Coding agent for the terminal — hash-anchored edits, optimized tool harness, LSP, Python, browser, subagents, and more
★ 21kpi. AI agent toolkit: unified LLM API, agent loop, TUI, coding agent CLI
★ 81ktokscale. 🛰️ Track token usage across AI coding agents from your terminal. 🏅 Global leaderboard with quadrillions of tokens tracked.
★ 4.7klol-map-champion-tracker. Python
★ 3PaperBanana. PaperBanana: Automating Academic Illustration For AI Scientists
★ 6.9ksd-webui-forge-classic. The good ol' Forge WebUI, now updated with new features~
★ 1.6kopencode. The open source coding agent.
★ 191kStalker_GAMMA. S.T.A.L.K.E.R. G.A.M.M.A. modpack for Anomaly
★ 1.2khermes-agent. The agent that grows with you
★ 223kVEXTREME. VEXTREME - Vectrex Multicart
★ 75whisper-key-local. Global hotkeys to record speech and transcribe directly to your cursor
★ 180VibeVoice. Open-Source Frontier Voice AI
★ 52kModel-Optimizer. A unified library of SOTA model optimization techniques like quantization, distillation, pruning, neural architecture search, speculative decoding, etc. It compresses deep learning models for downstream deployment frameworks like TensorRT-LLM, TensorRT, vLLM, etc. to optimize inference speed.
★ 3.3kslop-forensics. Jupyter Notebook
★ 363Gmail-MCP-Server. A Model Context Protocol (MCP) server for Gmail integration in Claude Desktop with auto authentication support. This server enables AI assistants to manage Gmail through natural language interactions.
★ 1.2kheretic. Fully automatic censorship removal for language models
★ 27kEpsteOut. See which of your LinkedIn connections appear in the Epstein files.
★ 641excalidraw-mcp. Fast and streamable Excalidraw MCP App
★ 5kskyvern. Automate browser based workflows with AI
★ 23kSaveOurShip2. C#
★ 48pytorch. Tensors and Dynamic neural networks in Python with strong GPU acceleration
★ 102kopenclaw. Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞
★ 385kEngram. Conditional Memory via Scalable Lookup: A New Axis of Sparsity for Large Language Models
★ 4.6knnsight. The nnsight package enables interpreting and manipulating the internals of deep learned models.
★ 1kIMTalker. ACM MM | IMTalker: Efficient Audio-driven Talking Face Generation with Implicit Motion Transfer
★ 186awesome-talking-head-generation.
★ 1.9kAutonomous-Agents. Autonomous Agents (LLMs) research papers. Updated Daily.
★ 1.4kdolt. Dolt – Git for Data
★ 24kAssetOpsBench. AssetOpsBench - Industry 4.0: A unified benchmark and framework for building, orchestrating, and evaluating domain-specific AI agents for Industry 4.0 asset operations and maintenance, with 460+ scenarios, 5 specialist agents (IoT, FMSR, TSFM, Work Order,...), and multi-agent orchestration blueprints (MetaAgent, AgentHive) over MCP.
★ 2.1kComputational-Argumentation.
★ 12nerfies.github.io. JavaScript
★ 4.3kcalm. Official implementation of "Continuous Autoregressive Language Models"
★ 812mobile-use. AI agents can now use real Android and iOS apps, just like a human.
★ 2.7kreasoning-with-sampling. Python
★ 442Vectorblade. Vectorblade, a vectrex game and port of Warblade
★ 22pitrex-baremetal. C
★ 24Vide. Vectrex Integrated Development Environment
★ 62pyversity. Fast Diversification for Search & Retrieval
★ 493ai_papers_scrapper. Download papers pdfs and other info from main AI conferences
★ 53playball. Watch MLB games from the comfort of your own terminal
★ 1.2kTek405xEmulator. Tektronix 405x Emulator
★ 29coqui-ai-TTS. 🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production
★ 2.3kTop-H-Decoding. Official PyTorch implementation of Top-H decoding—an entropy-aware, training-free sampler that adapts creativity and coherence in LLM text generation. Paper: arXiv:2509.02510
★ 11NeuroPriest. Rogue-lite as a Notepad++ Plugin
★ 90gnulag.net. gnulag's homepage on the interwebz
★ 7osci-render. 〰📺🔊 Synthesiser audio plugin for making music by drawing objects on an oscilloscope using audio.
★ 714Large-Scale-Selection-for-LLMs. AISTATS 2025: Efficient and Asymptotically Unbiased Constrained Decoding for Large Language Models
★ 4Microsoft-Activation-Scripts. Open-source Windows and Office activator featuring HWID, Ohook, TSforge, and Online KMS activation methods, along with advanced troubleshooting.
★ 185kwinutil. Chris Titus Tech's Windows Utility - Install Programs, Tweaks, Fixes, and Updates
★ 59kag2. AG2 (formerly AutoGen): The Open-Source AgentOS.Join us at: https://discord.gg/sNGSwQME3x
★ 4.8kbuying-domains. useful data and advice for buying domains.
★ 117text-to-lora. Hypernetworks that adapt LLMs for specific benchmark tasks using only textual task description as the input
★ 1.3kmermaid. Generation of diagrams like flowcharts or sequence diagrams from text in a similar manner as markdown
★ 89kschemic. Actually Working OpenAI Structured Output
★ 19Performance-Fish. Performance Mod for RimWorld
★ 679Prepatcher. Structured assembly rewriting library/mod for RW
★ 119syncode. Efficient and general syntactical decoding for Large Language Models
★ 338itergen. Iterate on LLM-based structured generation forward and backward
★ 23multilspy. multilspy is a lsp client library in Python intended to be used to build applications around language servers.
★ 598ComfyUI-Hunyuan3DWrapper. Python
★ 1kComfyUI-3D-Pack. An extensive node suite that enables ComfyUI to process 3D inputs (Mesh & UV Texture, etc) using cutting edge algorithms (3DGS, NeRF, etc.)
★ 3.8kHunyuan3D-2. High-Resolution 3D Assets Generation with Large Scale Hunyuan3D Diffusion Models.
★ 14kTRELLIS. Official repo for paper "Structured 3D Latents for Scalable and Versatile 3D Generation" (CVPR'25 Spotlight).
★ 13kComfyUI-Upscaler-Tensorrt. 2-4x faster ComfyUI Image Upscaling using Tensorrt ⚡
★ 247ComfyUI-RealESRGAN_Upscaler. ComfyUI-RealESRGAN_Upscaler
★ 27ComfyUI_TensorRT. Python
★ 705pydantic-ai. AI Agent Framework, the Pydantic way
★ 19kNdLinear. NdLinear by Ensemble is a drop-in PyTorch module that shrinks your models with no accuracy loss. It powers the Ensemble Platform—upload any model and get back a smaller, faster version, ready to deploy. Export to all frameworks (ONNX, TensorRT, SNPE, and more). Try it now → https://app.ensemblecore.ai/signup
★ 297nnd. A debugger for Linux
★ 1.7kbeyond-nanogpt. Minimal and annotated implementations of key ideas from modern deep learning research.
★ 1.3kllm-sampling. A very simple interactive demo to understand the common LLM samplers.
★ 40xan. The CSV magician
★ 4.4ktop_nsigma. The official code repo and data hub of top_nsigma sampling strategy for LLMs.
★ 26annotateai. 📝 Automatically annotate papers using LLMs
★ 422token-explorer. A simple tool that let's you explore different possible paths that an LLM might sample.
★ 213manifold. Manifold is an experimental platform for enabling long horizon workflow automation using teams of AI assistants.
★ 497quest. Quantitative evalUation of modErn LLM Sampling Techniques
★ 2AidanBench. Aidan Bench attempts to measure <big_model_smell> in LLMs.
★ 321minp_paper. Code Implementation, Evaluations, Documentation, Links and Resources for Min P paper
★ 51crawl4ai. 🚀🤖 Crawl4AI: Open-source LLM Friendly Web Crawler & Scraper. Don't be shy, join here: https://discord.gg/jP8KfhDhyN
★ 76kag2studio. AG2 Studio
★ 52agentok. AG2 Visualized - Build Multi-Agentic Apps with Drag-and-Drop.
★ 418sparsify. Sparsify transformers with SAEs and transcoders
★ 735helium. Lighter web automation with Python
★ 8.3ksmolagents. 🤗 smolagents: a barebones library for agents that think in code.
★ 29kalpaca-trade-api-python. Python client for Alpaca's trade API
★ 1.9kllm-reasoners. A library for advanced large language model reasoning
★ 2.3koutlines. Structured Outputs
★ 15kxgrammar. Fast, Flexible and Portable Structured Generation
★ 1.8knotion-sdk-py. Notion API client SDK, rewritten in Python! (sync + async)
★ 2.2kcosmos. NVIDIA Cosmos is an open platform of world models, datasets, and tools that enables developers to build Physical AI for robots, autonomous vehicles, smart infrastructure, and more.
★ 11kAgentLaboratory. Agent Laboratory is an end-to-end autonomous research workflow meant to assist you as the human researcher toward implementing your research ideas
★ 5.8koptillm. Optimizing inference proxy for LLMs
★ 4.2ksearch-and-learn. Recipes to scale inference-time compute of open models
★ 1.1kcut-it. Over 400 cross-platform downloads 🥳🎈 Cut-It, the next generation card cutter
★ 10paperlists. Processed / Cleaned Data for Paper Copilot
★ 953llama3_interpretability_sae. A complete end-to-end pipeline for LLM interpretability with sparse autoencoders (SAEs) using Llama 3.2, written in pure PyTorch and fully reproducible.
★ 641sonar. Large-scale LLM inference engine
★ 1.8kQuest-Best-Tokens. An introduction to LLM Sampling
★ 80lm-polygraph. Python
★ 498sd-webui-live-portrait. LivePortrait for AUTOMATIC1111 Stable Diffusion WebUI
★ 78sd-webui-cn-sam-preprocessor. Segment Anything preprocessor for ControlNet inside Stable Diffusion WebUI
★ 16entropix. Entropy Based Sampling and Parallel CoT Decoding
★ 3.4kbacktrack_sampler. An easy-to-understand framework for LLM samplers that rewind and revise generated tokens
★ 151sd-forge-couple. An Extension for Forge Webui that implements Attention Couple
★ 459chatbot_clinic. Science-driven chatbot development
★ 66mirostat. Code for the paper-"Mirostat: A Perplexity-Controlled Neural Text Decoding Algorithm" (https://arxiv.org/abs/2007.14966).
★ 61jit-implementation. 🚀 JIT Implementation: Code That Writes Itself
★ 119strategic-debate-tot. A DSPy-based implementation of the tree of thoughts method (Yao et al., 2023) for generating persuasive arguments
★ 103EQ-Bench. A benchmark for emotional intelligence in large language models
★ 444antislop-sampler. Python
★ 351intel-extension-for-transformers. ⚡ Build your chatbot within minutes on your favorite device; offer SOTA compression techniques for LLMs; run LLMs efficiently on Intel Platforms⚡
★ 2.2kintel-extension-for-pytorch. A Python package for extending the official PyTorch that can easily obtain performance on Intel platform
★ 2kComfyUI. The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.
★ 123kCAA. Steering Llama 2 with Contrastive Activation Addition
★ 244activation-steering. [ICLR 2025] General-purpose activation steering library
★ 181sglang. SGLang is a high-performance serving framework for large language models and multimodal models.
★ 31kLlamaFactory. Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
★ 74kctypes.sh. A foreign function interface for bash.
★ 2.2khuggingface-llama-recipes. Jupyter Notebook
★ 711fundus. A very simple news crawler with a funny name
★ 471evolutionaryLanguageGames. A repo for a paper writing on evolutionary language games as a mechanism for refining AI Pluralism
★ 3cloud-gpus.github.io. A comparison site for cloud GPU instances.
★ 53flash-attention. Fast and memory-efficient exact attention
★ 25kllm-compressor. Transformers-compatible library for applying various compression algorithms to LLMs for optimized deployment with vLLM
★ 3.6kvllm. A high-throughput and memory-efficient inference and serving engine for LLMs
★ 88kdspy. DSPy: The framework for programming—not prompting—language models
★ 36kLLM101n. LLM101n: Let's build a Storyteller
★ 38klm-format-enforcer. Enforce the output format (JSON Schema, Regex etc) of a language model
★ 2kPaCMAP. PaCMAP: Large-scale Dimension Reduction Technique Preserving Both Global and Local Structure
★ 1ksd-webui-untitledmerger. Python
★ 22sd-webui-old-sd-firstpasser. Firstpass generation with old SD model, Loras, embedding, etc
★ 32spectrum. Python
★ 145agno. Build, run, and manage agent platforms.
★ 42kCataclysm-EOD. Cataclysm - Era Of Decay. A turn-based survival game set in a post-apocalyptic world.
★ 64abliterator. Simple Python library/structure to ablate features in LLMs which are supported by TransformerLens
★ 685pyreft. Stanford NLP Python library for Representation Finetuning (ReFT)
★ 1.6kmommy. mommy's here to support you, in any shell, on any system~ ❤️
★ 461grammar_sys_msg_ctx. Python
★ 1TwoAI. A simple experiment on letting two local LLM have a conversation about anything!
★ 112sd-webui-state-manager. A state manager to quickly save and return to previous configs in A1111
★ 67OpenHands. 🙌 OpenHands: AI-Driven Development
★ 83ktransformer-heads. Toolkit for attaching, training, saving and loading of new heads for transformer models
★ 299LongLoRA. Code and documents of LongLoRA and LongAlpaca (ICLR 2024 Oral)
★ 2.7kinstructor. structured outputs for llms
★ 14ksd-webui-inpaint-difference. A1111 extension to find the inpaint mask to use based on the difference between two images.
★ 5601. The #1 open-source voice interface for desktop, mobile, and ESP32 chips.
★ 5.1kdevika. Devika is the first open-source implementation of an Agentic Software Engineer. Initially started as an open-source alternative to Devin.
★ 20kOpenMoE. A family of open-sourced Mixture-of-Experts (MoE) Large Language Models
★ 1.7kfairseq. Facebook AI Research Sequence-to-Sequence Toolkit written in Python.
★ 32kmegablocks. Python
★ 1.6kSpeakLocal. A TTS extension for oobabooga text WebUI
★ 31sd-mecha. Executable State Dict Recipes
★ 81sd-webui-untitledmerger. Python
★ 15fast-llm-security-guardrails. The fastest Trust Layer for AI Agents
★ 154representation-engineering. Representation Engineering: A Top-Down Approach to AI Transparency
★ 1kArxivPapers. Code behind Arxiv Papers
★ 543Aimmy. Universal Second Eye for Gamers with Impairments (Universal AI Aim Aligner (AI Aimbot) - ONNX/YOLOv8 - C#)
★ 1.5kaici. AICI: Prompts as (Wasm) Programs
★ 2.1kFERemastered. Lua
★ 11lorax. Multi-LoRA inference server that scales to 1000s of fine-tuned LLMs
★ 3.8kClipboardConqueror. Clipboard Conqueror is a novel copy and paste copilot alternative designed to bring your very own LLM AI assistant to any text field.
★ 445SillyTavern. LLM Frontend for Power Users.
★ 31kDEBATunE. [ACL'24] Can LLMs Speak For Diverse People? Tuning LLMs via Debate to Generate Controllable Controversial Statements
★ 25axolotl. Go ahead and axolotl questions
★ 12kprompt-lookup-decoding. Simple speculative decoding technique, integrated in vLLM and transformers
★ 611repeng. A library for making RepE control vectors
★ 747bagel. A bagel, with everything.
★ 326stable-diffusion-webui-forge. Python
★ 13kllm_debate. Code release for "Debating with More Persuasive LLMs Leads to More Truthful Answers"
★ 131llm_steer. Steer LLM outputs towards a certain topic/subject and enhance response capabilities using activation engineering by adding steering vectors
★ 280unsloth. Unsloth is a local UI for training and running Kimi K3, Gemma 4, Qwen3.6, DeepSeek, GLM and other models.
★ 69ksd-webui-fabric. Python
★ 408sd-webui-agentattention. Speed up image generation and improve image quality using Agent Attention.
★ 44sd-webui-cads. Greatly increase the diversity of your generated images in Automatic1111 WebUI through Condition-Annealed Sampling.
★ 108stable-diffusion-webui-extension-templates. a template of stable-diffusion-webui extension
★ 75WhisperSpeech. An Open Source text-to-speech system built by inverting Whisper.
★ 4.6kDRUGS. Stop messing around with finicky sampling parameters and just use DRµGS!
★ 364loom. Multiversal tree writing interface for human-AI collaboration
★ 1.4kseq2seq_constrained_decoding. Constrained decoding utilities for text generation using Huggingface seq2seq models
★ 25sd-webui-cd-tuner. Color/Detail control for Stable Diffusion web-ui
★ 226sd_civitai_extension. All of the Civitai models inside Automatic 1111 Stable Diffusion Web UI
★ 2.4kcivitai. A repository of models, textual inversions, and more
★ 7.2ktrieve. All-in-one platform for search, recommendations, RAG, and analytics offered via API
★ 2.7kDocsGPT. Private AI platform for agents, assistants and enterprise search. Built-in Agent Builder, Deep research, Document analysis, Multi-model support, and API connectivity for agents.
★ 18kllamppl. Probabilistic programming with large language models
★ 176emnlp-2023. Repository containing the website for the EMNLP 2023 conference
★ 17debate-auto-highlight. An automatic highlighter tool for debate
★ 4evidencer. Debate card cutting chrome extension
★ 6CoDeF. [CVPR'24 Highlight] Official PyTorch implementation of CoDeF: Content Deformation Fields for Temporally Consistent Video Processing
★ 4.8kstable-diffusion-webui-tensorrt. Python
★ 317Fooocus. Focus on prompting and generating
★ 52kprompttools. Open-source tools for prompt testing and experimentation, with support for both LLMs (e.g. OpenAI, LLaMA) and vector databases (e.g. Chroma, Weaviate, LanceDB).
★ 3kseamless-tile-inpainting. An automatic1111 extension for making seamless tiles using Stable Diffusion inpainting
★ 40sd-webui-refiner. Webui Extension for integration refiner in generation process
★ 157MLAlgorithms. Minimal and clean examples of machine learning algorithms implementations
★ 11kFew-Shot-Patch-Based-Training. The official implementation of our SIGGRAPH 2020 paper Interactive Video Stylization Using Few-Shot Patch-Based Training
★ 625magenta. Magenta: Music and Art Generation with Machine Intelligence
★ 20kkohya_ss. Python
★ 13k