Python

• theroyallab/tabbyAPI - The official API server for Exllama. OAI compatible, lightweight, and fast.
• unslothai/unsloth - Web UI for training and running open models like Gemma 4, Qwen3.6, DeepSeek, gpt-oss locally.
• simonw/files-to-prompt - Concatenate a directory full of files into a single prompt for use with LLMs
• nrl-ai/llama-assistant - AI-powered assistant to help you with your daily tasks, powered by Llama 3, DeepSeek R1, and many more models on HuggingFace.
• bartolli/mcp-llm-bridge - MCP implementation that enables communication between MCP servers and OpenAI-compatible LLMs
• Haervwe/open-webui-tools - Open‑WebUI Tools is a modular toolkit designed to extend and enrich your Open WebUI instance, turning it into a powerful AI workstation. With a suite of over 15 specialized tools, function pipelines, and filters, this project supports academic research, agentic autonomy, multimodal creativity, workflows, and more
• AutoGPTQ/AutoGPTQ - An easy-to-use LLMs quantization package with user-friendly apis, based on GPTQ algorithm.
• qwopqwop200/GPTQ-for-LLaMa - 4 bits quantization of LLaMA using GPTQ
• turboderp/exllama - A more memory-efficient rewrite of the HF transformers implementation of Llama for use with quantized weights.
• the-crypt-keeper/can-ai-code - Self-evaluating interview for AI coders
• evilsocket/opensnitch - OpenSnitch is a GNU/Linux interactive application firewall inspired by Little Snitch.
• FOLLGAD/godmode - Godmode.space. Reached one million users in 3 months
• open-webui/open-webui - User-friendly AI Interface (Supports Ollama, OpenAI API, ...)
• onyx-dot-app/onyx - Open Source AI Platform - AI Chat with advanced features that works with every LLM
• bentoml/OpenLLM - Run any open-source LLMs, such as DeepSeek and Llama, as OpenAI compatible API endpoint in the cloud.
• mrhan1993/Fooocus-API - FastAPI powered API for Fooocus
• pytorch/torchtune - PyTorch native post-training library
• pytorch/torchchat - Run PyTorch LLMs locally on servers, desktop and mobile
• Lightning-AI/pytorch-lightning - Pretrain, finetune ANY AI model of ANY size on 1 or 10,000+ GPUs with zero code changes.
• sayakpaul/diffusers-torchao - End-to-end recipes for optimizing diffusion models with torchao and diffusers (inference and FP8 training).
• pytorch/ao - PyTorch native quantization and sparsity for training and inference
• ParisNeo/lollms-webui - Lord of Large Language and Multi modal Systems Web User Interface
• jahwag/ClaudeSync - ClaudeSync is a Python tool that automates the synchronization of local files with Claude.ai Projects
• SigmaNight/basiliskLLM - 🐍 Where LLMs Unite
• swingmx/swingmusic - Swing Music is a beautiful, self-hosted music player for your local audio files. Like a cooler Spotify ... but bring your own music.
• microsoft/markitdown - Python tool for converting files and office documents to Markdown.
• microsoft/AIOpsLab - A holistic framework to enable the design, development, and evaluation of autonomous AIOps agents.
• exo-explore/gym - EXO Gym is an open-source Python toolkit that facilitates distributed AI research.
• Thytu/Agentarium - open-source framework for creating and managing simulations populated with AI-powered agents. It provides an intuitive platform for designing complex, interactive environments where agents can act, learn, and evolve.
• bgorlick/getai - GetAI - The Easiest to Use AI Model Search & Download API and Interactive Console Tool
• huggingface/smolagents - 🤗 smolagents: a barebones library for agents that think in code.
• ai-robots-txt/ai.robots.txt - A list of AI agents and robots to block.
• turboderp-org/exllamav2 - A fast inference library for running LLMs locally on modern consumer-class GPUs
• AntonOsika/gpt-engineer - CLI platform to experiment with codegen. Precursor to: https://lovable.dev
• AK391/ai-gradio - A Python package that makes it easy for developers to create AI apps powered by various AI providers.
• goruck/home-generative-agent - A home assistant generative agent integration based on langchain and langgraph.
• jimmc414/onefilellm - Specify a github or local repo, github pull request, arXiv or Sci-Hub paper, Youtube transcript or documentation URL on the web and scrape into a text file and clipboard for easier LLM ingestion
• SamuelSchmidgall/AgentLaboratory - Agent Laboratory is an end-to-end autonomous research workflow meant to assist you as the human researcher toward implementing your research ideas
• lllyasviel/Fooocus - Focus on prompting and generating
• MervinPraison/PraisonAI - PraisonAI 🦞 — Hire a 24/7 AI Workforce. Stop writing boilerplate and start shipping autonomous self-improving agents that research, plan, code, and execute tasks. Deployed in 5 lines of code with built-in memory, RAG, and support for 100+ LLMs.
• tensorgi/T6 - The official implementation of Tensor ProducT ATTenTion Transformer (T6) (https://arxiv.org/abs/2501.06425)
• BrainBlend-AI/atomic-agents - Building AI agents, atomically
• SWE-agent/SWE-agent - SWE-agent takes a GitHub issue and tries to automatically fix it, using your LM of choice. It can also be employed for offensive cybersecurity or competitive coding challenges. \[NeurIPS 2024]
• All-Hands-AI/OpenHands - 🙌 OpenHands: Code Less, Make More
• OpenAutoCoder/Agentless - Agentless🐱: an agentless approach to automatically solve software development problems
• bespokelabsai/curator - Synthetic data curation for post-training and structured data extraction
• ModelCloud/GPTQModel - LLM model quantization (compression) toolkit with HW acceleration support for Nvidia, AMD, Intel GPU and Intel/AMD/Apple CPU via HF, vLLM, and SGLang.
• enoch3712/ExtractThinker - ExtractThinker is a Document Intelligence library for LLMs, offering ORM-style interaction for flexible and powerful document workflows.
• plurai-ai/intellagent - A framework for comprehensive diagnosis and optimization of agents using simulated, realistic synthetic interactions
• sgl-project/sglang - SGLang is a high-performance serving framework for large language models and multimodal models.
• karpathy/nanoGPT - The simplest, fastest repository for training/finetuning medium-sized GPTs.
• microsoft/unilm - Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities
• stas00/ml-engineering - Machine Learning Engineering Open Book
• mosaicml/llm-foundry - LLM training code for Databricks foundation models
• linkedin/Liger-Kernel - Efficient Triton Kernels for LLM Training
• ShishirPatil/gorilla - Gorilla: Training and Evaluating LLMs for Function Calls (Tool Calls)
• oumi-ai/oumi - Easily fine-tune, evaluate and deploy gpt-oss, Qwen3, DeepSeek-R1, or any open source LLM / VLM!
• spcl/QuaRot - Code for Neurips24 paper: QuaRot, an end-to-end 4-bit inference of large language models.
• mozilla-ai/lumigator - Source code for Mozilla.ai's Lumigator platform
• deepseek-ai/Janus - Janus-Series: Unified Multimodal Understanding and Generation Models
• lotus-data/lotus - AI-Powered Data Processing: Use LOTUS to process all of your datasets with LLMs and embeddings. Enjoy up to 1000x speedups with fast, accurate query processing, that's as simple as writing Pandas code
• agno-agi/agno - Run agents as production software.
• deepspeedai/DeepSpeed - DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
• handrew/browserpilot - Natural language browser automation
• Skyvern-AI/skyvern - Automate browser based workflows with AI
• browser-use/browser-use - 🌐 Make websites accessible for AI agents. Automate tasks online with ease.
• maximilianh/pubMunch - various tools to download, convert and process the full text of scientific articles
• kleer001/Text\_Loom - Network for procedural editing of text with LLMs
• ZacharyHampton/HomeHarvest - Python package for scraping real estate property data
• huggingface/open-r1 - Fully open reproduction of DeepSeek-R1
• brainrotjs/brainrot.js - Text to video generator in the brainrot form. Learn about any topic from your favorite personalities 😼.
• simonw/llm-anthropic - LLM access to models by Anthropic, including the Claude series
• commixproject/commix - Automated All-in-One OS Command Injection Exploitation Tool
• SomeOddCodeGuy/WilmerAI - WilmerAI is one of the oldest LLM semantic routers. It uses multi-layer prompt routing and complex workflows to allow you to not only create practical chatbots, but to extend any kind of application that connects to an LLM via REST API. Wilmer sits between your app and your many LLM APIs, so that you can manipulate prompts as needed.
• SomeOddCodeGuy/OfflineWikipediaTextApi - This small API downloads and exposes access to NeuML's txtai-wikipedia and full wikipedia datasets, taking in a query and returning full article text
• NotJoeMartinez/yt-fts - YouTube Full Text Search - Search all of YouTube from the command line
• GitToby/howto-ai - Dont know the right command? Just ask howto!
• playtron-os/rpm-specs-gaming - Various RPM specs for packages optimized for gaming.
• docling-project/docling - Get your documents ready for gen AI
• lss233/kirara-ai - 🤖 可 DIY 的 多模态 AI 聊天机器人 | 🚀 快速接入 微信、 QQ、Telegram、等聊天平台 | 🦈支持DeepSeek、Grok、Claude、Ollama、Gemini、OpenAI | 工作流系统、网页搜索、AI画图、人设调教、虚拟女仆、语音对话 |
• open-compass/VLMEvalKit - Open-source evaluation toolkit of large multi-modality models (LMMs), support 220+ LMMs, 80+ benchmarks
• showlab/Impossible-Videos - ICML 2025 - Impossible Videos
• mgagvani/minecraft\_texture\_upscaler - Minecraft Texture Upscaler automatically processes low-resolution Minecraft texture packs and increases their resolution. It is almost as good as native, (paid), high-resolution texture packs.
• philz1337x/ComfyUI-ClarityAI - ComfyUI Node of Clarity AI creative image upscaler and enhancer. ComfyUI alternative of Magnific AI
• RetiredWizard/PyDOS - DOS-like OS for microcontroller boards running Micropython or Circuitpython
• khoj-ai/khoj - Your AI second brain. Self-hostable. Get answers from the web or your docs. Build custom agents, schedule automations, do deep research. Turn any online or local LLM into your personal, autonomous AI (gpt, claude, gemini, llama, qwen, mistral). Get started - free.
• zju3dv/Vox-Fusion - Code for "Dense Tracking and Mapping with Voxel-based Neural Implicit Representation", ISMAR 2022
• LibrePhotos/librephotos - A self-hosted open source photo management service.
• mannaandpoem/OpenManus - No fortress, purely open ground. OpenManus is Coming.
• adafruit/cookiecutter-adafruit-circuitpython - Cookiecutter template for Adafruit's CircuitPython libraries.
• todbot/circuitpython-tricks - Some CircuitPython tricks, mostly reminders to myself
• BrianPugh/belay - Belay is a python library that enables the rapid development of projects that interact with hardware via a micropython-compatible board.
• Jack-Bagel/Minecraft-Lora-Training - Folder used to train a LoRa model using the Kohya trainer.
• sentient-agi/OpenDeepSearch - SOTA search powered LLM
• EleutherAI/lm-evaluation-harness - A framework for few-shot evaluation of language models.
• darsagent/DARS-Agent
• BigComputer-Project/SWE-Arena - SWE Arena
• containers/ramalama - RamaLama is an open-source developer tool that simplifies the local serving of AI models from any source and facilitates their use for inference in production, all through the familiar language of containers.
• ai-christianson/RA.Aid - Develop software autonomously.
• TransformerOptimus/SuperAGI - <⚡️> SuperAGI - A dev-first open source autonomous AI agent framework. Enabling developers to build, manage & run useful autonomous agents quickly and reliably.
• asweigart/pyautogui - A cross-platform GUI automation Python module for human beings. Used to programmatically control the mouse & keyboard.
• augmentcode/augment-swebench-agent - The #1 open-source SWE-bench Verified implementation
• CanvizAI/DARS-Agent
• stanfordnlp/dspy - DSPy: The framework for programming—not prompting—language models
• unclecode/crawl4ai - 🚀🤖 Crawl4AI: Open-source LLM Friendly Web Crawler & Scraper. Don't be shy, join here: https://discord.gg/jP8KfhDhyN
• eqimp/hogwild\_llm - Official PyTorch implementation for Hogwild! Inference: Parallel LLM Generation with a Concurrent Attention Cache
• onnx/onnx - Open standard for machine learning interoperability
• vaibhavagg303/DARS-Agent
• open-webui/mcpo - A simple, secure MCP-to-OpenAPI proxy server
• QwenLM/Qwen-Agent - Agent framework and applications built upon Qwen>=3.0, featuring Function Calling, MCP, Code Interpreter, RAG, Chrome extension, etc.
• FoundationAgents/OpenManus - No fortress, purely open ground. OpenManus is Coming.
• noahgsolomon/brainrot.js - Text to video generator in the brainrot form. Learn about any topic from your favorite personalities 😼.
• MODSetter/SurfSense - An open source, privacy focused alternative to NotebookLM for teams with no data limits. Join our Discord: https://discord.gg/ejRNvftDp9
• QwenLM/Qwen3 - Qwen3 is the large language model series developed by Qwen team, Alibaba Cloud.
• infiniflow/ragflow - RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs
• apify/actor-llmstxt-generator - The /llms.txt Generator Actor 🕸️📄 extracts website content to create an llms.txt file for AI apps 🤖✨ like LLM fine-tuning and indexing. Output is available 📥 in the Key-Value Store for easy download and integration into workflows. 🚀
• Abiorh001/mcp\_omni\_connect - MCPOmni Connect is a complete AI agent platform featuring OmniAgent - a revolutionary agent builder with local tools system, self-flying background agents, and multi-tier memory with semantic search. Connects to MCP servers via stdio/SSE/HTTP, supports autonomous modes, real-time events, XML reasoning, and production databases. Embeddable or CLI.
• langchain-ai/mcpdoc - Expose llms-txt to IDEs for development
• cased/kit - The toolkit for AI devtools context engineering. Build with codebase mapping, symbol extraction, and many kinds of code search.
• run-llama/llama-lab
• paulpierre/markdown-crawler - A multithreaded 🕸️ web crawler that recursively crawls a website and creates a 🔽 markdown file for each page, designed for LLM RAG
• dmayboroda/minima - On-premises conversational RAG with configurable containers
• mage-ai/mage-ai - 🧙 Build, run, and manage data pipelines for integrating and transforming data.
• ostris/ai-toolkit - The ultimate training toolkit for finetuning diffusion models
• astral-sh/ty - An extremely fast Python type checker and language server, written in Rust.
• stitionai/devika - Devika is the first open-source implementation of an Agentic Software Engineer. Initially started as an open-source alternative to Devin.
• rescuezilla/rescuezilla - The Swiss Army Knife of System Recovery
• borgbackup/borg - Deduplicating archiver with compression and authenticated encryption.
• bjodah/llm-multi-backend-container - Docker/podman container for llama.cpp/vllm/exllamav{2,3} orchestrated using llama-swap
• multi-swe-bench/MopenHands
• ChocoMeow/Vocard - Vocard is a simple music bot. It leads to a comfortable experience which is user-friendly, It supports Youtube, Soundcloud, Spotify, Twitch and more!
• Olow304/memvid - Video-based AI memory library. Store millions of text chunks in MP4 files with lightning-fast semantic search. No database needed.
• wey-gu/py-pglite - PGlite wrapper in Python for testing. Test your app with Postgres just as lite as SQLite.
• ezyang/codemcp - Coding assistant MCP for Claude Desktop
• oraios/serena - A powerful MCP toolkit for coding, providing semantic retrieval and editing capabilities - the IDE for your agent
• SWE-agent/SWE-ReX - Sandboxed code execution for AI agents, locally or on the cloud. Massively parallel, easy to extend. Powering SWE-agent and more.
• morphik-org/morphik-core - The most accurate document search and store for building AI apps
• microsoft/renderformer - Official Code Release for \[SIGGRAPH 2025] RenderFormer: Transformer-based Neural Rendering of Triangle Meshes with Global Illumination
• bunkerity/bunkerweb - 🛡️ Open-source and cloud-native Web Application Firewall (WAF)
• byt3bl33d3r/CrackMapExec - A swiss army knife for pentesting networks
• pat-jj/s3 - \[EMNLP'25] s3 - ⚡ Efficient & Effective Search Agent Training via RL for RAG (RLVR for Search with Minimal Data)
• QwenLM/ParScale - Parallel Scaling Law for Language Model — Beyond Parameter and Inference Time Scaling
• pixeltable/pixelagent - Pixelagent — Multimodal stateful agents
• apify/crawlee-python - Crawlee—A web scraping and browser automation library for Python to build reliable crawlers. Extract data for AI, LLMs, RAG, or GPTs. Download HTML, PDF, JPG, PNG, and other files from websites. Works with Parsel, BeautifulSoup, Playwright, and raw HTTP. Both headful and headless mode. With proxy rotation.
• MinishLab/model2vec - Fast State-of-the-Art Static Embeddings
• Operative-Sh/web-eval-agent - An MCP server that autonomously evaluates web applications.
• agno-agi/agent-api - A minimal, open-source setup for serving Agents using FastAPI and Postgres. Built for speed, clarity, and dev happiness.
• i-am-bee/acp - Open protocol for communication between AI agents, applications, and humans.
• cocoindex-io/cocoindex - Incremental engine for long horizon agents 🌟 Star if you like it!
• browser-use/workflow-use - ⚙️ Create and run workflows (RPA 2.0)
• ag-ui-protocol/ag-ui - AG-UI: the Agent-User Interaction Protocol. Bring Agents into Frontend Applications.
• bytedance/deer-flow - An open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message gateway, it handles different levels of tasks that could take minutes to hours.
• i-am-bee/beeai-framework - Build production-ready AI agents in both Python and Typescript.
• camel-ai/owl - 🦉 OWL: Optimized Workforce Learning for General Multi-Agent Assistance in Real-World Task Automation
• tensorgi/TPA - \[NeurIPS 2025 Spotlight] TPA: Tensor ProducT ATTenTion Transformer (T6) (https://arxiv.org/abs/2501.06425)
• OWASP/www-project-ai-testing-guide - OWASP Foundation web repository
• EvalsOne/MCP-connect - Enables cloud-based AI services to access local Stdio based MCP servers via HTTP requests
• letta-ai/letta - Letta is the platform for building stateful agents: AI with advanced memory that can learn and self-improve over time.
• searxng/searxng - SearXNG is a free internet metasearch engine which aggregates results from various search services and databases. Users are neither tracked nor profiled.
• searxng/searx-space - Statistics of the public SearXNG instances
• mit-han-lab/nunchaku - \[ICLR2025 Spotlight] SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models
• coleam00/ottomator-agents - All the open source AI Agents hosted on the oTTomator Live Agent Studio platform!
• goauthentik/authentik - The authentication glue you need.
• kfirtoledo/multi-mcp
• hyperb1iss/droidmind - Control your Android devices with AI using Model Context Protocol
• SDGLBL/mcp-claude-code - MCP implementation of Claude Code capabilities and more
• vladkens/twscrape - 2025! X / Twitter API scrapper with authorization support. Allows you to scrape search results, User's profiles (followers/following), Tweets (favoriters/retweeters) and more.
• alirezamika/autoscraper - A Smart, Automatic, Fast and Lightweight Web Scraper for Python
• GeeeekExplorer/nano-vllm - Nano vLLM
• BeehiveInnovations/zen-mcp-server - The power of Claude Code / GeminiCLI / CodexCLI + \[Gemini / OpenAI / OpenRouter / Azure / Grok / Ollama / Custom Model / All Of The Above] working as one.
• coderamp-labs/gitingest - Replace 'hub' with 'ingest' in any GitHub URL to get a prompt-friendly extract of a codebase
• langbot-app/LangBot - Production-grade platform for building agentic IM bots - 生产级多平台智能机器人开发平台. 提供 Agent、知识库编排、插件系统 / Bots for Discord / Slack / LINE / Telegram / WeChat(企业微信, 企微智能机器人, 公众号) / 飞书 / 钉钉 / QQ / Satori e.g. Integrated with ChatGPT(GPT), DeepSeek, Dify, n8n, Langflow, Coze, Claude, Gemini, MiniMax, Ollama, SiliconFlow, Moonshot, GLM, clawdbot / openclaw
• deforum/sd-webui-deforum - Deforum extension for AUTOMATIC1111's Stable Diffusion webui
• divar-ir/ai-doc-gen - AI-powered multi-agent system that automatically analyzes codebases and generates comprehensive documentation. Features GitLab integration, concurrent processing, and multiple LLM support for better code understanding and developer onboarding.
• 9001/copyparty - Portable file server with accelerated resumable uploads, dedup, WebDAV, SFTP, FTP, TFTP, zeroconf, media indexer, thumbnails++ all in one file
• intruder-io/autoswagger - Autoswagger by Intruder - detect API auth weaknesses
• brennercruvinel/CCPlugins - Best Claude Code framework that actually save time. Built by a dev tired of typing "please act like a senior engineer" in every conversation.
• GAIR-NLP/ASI-Arch - AlphaGo Moment for Model Architecture Discovery.
• arjunguha/BigCodeBench-X - A benchmark of programming tasks for LLMs that supports almost any programming language.
• sapientinc/HRM - Hierarchical Reasoning Model Official Release
• Alpha-Innovator/InternAgent - When Agent Becomes the Scientist – Building Closed-Loop System from Hypothesis to Verification
• SalesforceAIResearch/MCPEval - MCP-based Agent Deep Evaluation System
• SAAgent/MCPWorld
• chroma-core/chroma-mcp - A Model Context Protocol (MCP) server implementation that provides database capabilities for Chroma
• needle-ai/needle-mcp - Needle MCP Server for easy RAG.Long-term memory for LLMs.
• alizdavoodi/MCPDocSearch - This project provides a toolset to crawl websites wikis, tool/library documentions and generate Markdown documentation, and make that documentation searchable via a Model Context Protocol (MCP) server, designed for integration with tools like Cursor.
• existence-master/Sentient - A personal AI assistant for everyone
• assafelovic/gpt-researcher - An autonomous agent that conducts deep research on any data using any LLM providers
• NPC-Worldwide/npcpy - The python library for research and development in NLP, multimodal LLMs, Agents, ML, Knowledge Graphs, and more.
• blazickjp/arxiv-mcp-server - A Model Context Protocol server for searching and analyzing arXiv papers
• mrexodia/ida-pro-mcp - AI-powered reverse engineering assistant that bridges IDA Pro with language models through MCP.
• Klavis-AI/klavis - Klavis AI: MCP integration platforms that let AI agents use tools reliably at any scale
• tadata-org/fastapi\_mcp - Expose your FastAPI endpoints as Model Context Protocol (MCP) tools, with Auth!
• The-Pocket/PocketFlow-Template-Python - Pocket Flow Project Template: Agentic Coding for Python
• The-Pocket/PocketFlow-Tutorial-Codebase-Knowledge - Pocket Flow: Codebase to Tutorial
• langroid/langroid - Harness LLMs with Multi-Agent Programming
• anmolksachan/TheTimeMachine - Weaponizing WaybackUrls for Recon, BugBounties , OSINT, Sensitive Endpoints and what not
• sparfenyuk/mcp-proxy - A bridge between Streamable HTTP and stdio MCP transports
• CursorTouch/Windows-MCP - MCP Server for Computer Use in Windows
• nunchaku-tech/nunchaku - \[ICLR2025 Spotlight] SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models