Explore code projects and try interactive demos from GitHub, Hugging Face and GitLab. Find a project by what it does and where it lives.
Explore interactive AI demos. Ordered by Hugging Face likes within this selection.
Upload a person image and a garment image to generate a virtual clothing try-on preview.
Public demo; sign-in, queues or GPU usage limits may apply. Model and output terms may differ from the code license.
Source and counts checked 17 Sept 2026Generate images from text prompts with FLUX.1 dev, with controls for image dimensions, seed and inference steps.
Public demo; sign-in, queues or GPU usage limits may apply. Model and output terms may differ from the code license.
Source and counts checked 17 Sept 2026Generate optical-illusion images from an input pattern and a text prompt, with controls for illusion strength.
Public demo; sign-in, queues or GPU usage limits may apply. Model and output terms may differ from the code license.
Source and counts checked 17 Sept 2026Try text-to-image generation with FLUX.1 schnell and adjust image dimensions, seed and inference steps.
Public demo; sign-in, queues or GPU usage limits may apply. Model and output terms may differ from the code license.
Source and counts checked 17 Sept 2026Generate short music clips from a text description, optionally using an audio melody to guide the result.
Public demo; sign-in, queues or GPU usage limits may apply. Model and output terms may differ from the code license.
Source and counts checked 17 Sept 2026Generate images from text with Z-Image-Turbo, using controls for output dimensions, steps and seed.
Public demo; sign-in, queues or GPU usage limits may apply. Model and output terms may differ from the code license.
Source and counts checked 17 Sept 2026Generate a video from an image and text prompt using a Wan2.2 demo, with duration and generation controls.
Public demo; sign-in, queues or GPU usage limits may apply. Model and output terms may differ from the code license.
Source and counts checked 17 Sept 2026Turn text into speech with selectable voices and speaking speed, and preview the generated audio.
Public demo; sign-in, queues or GPU usage limits may apply. Model and output terms may differ from the code license.
Source and counts checked 17 Sept 2026Explore 3D generation from images or text with controls for generation settings and downloadable asset files.
Public demo; sign-in, queues or GPU usage limits may apply. Model and output terms may differ from the code license.
Source and counts checked 17 Sept 2026Analyse an image with CLIP and generate descriptive text that can help inform image-generation prompts.
Public demo; sign-in, queues or GPU usage limits may apply. Model and output terms may differ from the code license.
Source and counts checked 17 Sept 2026Remove backgrounds from uploaded images or image URLs, with a PNG download and before-and-after preview.
Public demo; sign-in, queues or GPU usage limits may apply. Model and output terms may differ from the code license.
Source and counts checked 17 Sept 2026Transcribe audio or translate speech into English using a browser demo of Whisper Large V3.
Public demo; sign-in, queues or GPU usage limits may apply. Model and output terms may differ from the code license.
Source and counts checked 17 Sept 2026Extend an image beyond its original borders, with controls for aspect ratio, alignment and optional text guidance.
Public demo; sign-in, queues or GPU usage limits may apply. Model and output terms may differ from the code license.
Source and counts checked 17 Sept 2026Restore faces in an image, with controls for fidelity, face upsampling and background enhancement.
Public demo; sign-in, queues or GPU usage limits may apply. Model and output terms may differ from the code license.
Source and counts checked 17 Sept 2026Generate audio from text with Bark and select an acoustic prompt to influence the output.
Public demo; sign-in, queues or GPU usage limits may apply. Model and output terms may differ from the code license.
Source and counts checked 17 Sept 2026Edit images with an interactive interface that combines brush strokes, colour guidance and text prompts.
Public demo; sign-in, queues or GPU usage limits may apply. Model and output terms may differ from the code license.
Source and counts checked 17 Sept 2026Generate speech from text and explore voice design or reference-audio voice cloning in the Qwen3-TTS demo.
Public demo; sign-in, queues or GPU usage limits may apply. Model and output terms may differ from the code license.
Source and counts checked 17 Sept 2026Upscale and enhance an image with prompt guidance and a before-and-after comparison.
Public demo; sign-in, queues or GPU usage limits may apply. Model and output terms may differ from the code license.
Source and counts checked 17 Sept 2026Generate a 3D asset from an input image and adjust the output resolution and texture settings.
Public demo; sign-in, queues or GPU usage limits may apply. Model and output terms may differ from the code license.
Source and counts checked 17 Sept 2026Generate images from text prompts with Stable Diffusion 3.5 Large, with optional negative prompts and generation controls.
Public demo; sign-in, queues or GPU usage limits may apply. Model and output terms may differ from the code license.
Source and counts checked 17 Sept 2026Explore original code projects. Ordered by GitLab stars within this selection.
Run OpenCode tasks in GitLab CI using a Docker image and a configurable CI component.
Requires GitLab CI setup and credentials for the model provider you choose.
Source and counts checked 17 Sept 2026A Python library for evaluating machine-learning security and explaining model decisions, with attack methods and visualisation tools.
Requires a local Python environment and the project dependencies.
Source and counts checked 17 Sept 2026Build high-dimensional neural network potentials with the Ruhr University Neural Network Energy Representation framework.
Install locally using the project documentation; this is research software, not a browser demo.
Source and counts checked 17 Sept 2026A Python backend for research-document search and retrieval-augmented generation, supporting embeddings, vector search and multiple LLM backends.
Requires backend services and configuration; hosted model providers may need API keys.
Source and counts checked 17 Sept 2026A worked project demonstrating LLM development and testing with GitLab CI services, Docker and a local Ollama server.
Requires uv, Docker and an Ollama model for the worked example.
Source and counts checked 17 Sept 2026Top 10 by stars among 60 repositories matching your filters.
Loading chart… Exact counts are available under “View numbers & links”.
Stars and forks are community signals, not quality ratings or unique user counts. This chart compares GitHub repositories only. GitHub cards retain their combined popularity, momentum and activity ranking. About GitHub stars
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
The agent that grows with you
DeepSeek Harness: Everything is a Plugin.
Reverse engineer anything with agents, from app behavior down to native binaries.
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
Supercharge your AI agents with data from the web and beyond. Building the library for superintelligence. 🔥
An Open Source Machine Learning Framework for Everyone
🤗 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.
Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and Gemini CLI: local deterministic AST parsing, every edge explained, no vector store.
The agent engineering platform.
21 Lessons, Get Started Building with Generative AI
Orca is the ADE for working with a fleet of parallel agents. Run any coding agent with your own subscription. Available on desktop, mobile and remote runtime.
Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More
Learn AI Engineering! Learn it. Build it. Ship it for others.
Composable, accessible components with thoughtful defaults. Build your own component library with code you can customize, extend, and make your own.
Langflow is a powerful tool for building and deploying AI-powered agents and workflows.
Never stop coding. Free MIT AI gateway: one endpoint, 359 providers (150+ free), 1200+ models Kimi, Claude, GPT, Gemini, GLM, DeepSeek, MiniMax. Works with Claude Code, Codex, Cursor, OpenCode, Cline & Copilot. Quota-aware auto-fallback, RTK+Caveman compression saves 15-95% tokens, MCP/A2A, Desktop/PWA. Built by hundreds of contributors
Agents that use the browser.
Turn any idea, plan, or codebase into a beautiful interactive diagram. An agent skill for Claude Code, Codex, and more.
🙌 OpenHands: AI-Driven Development
18 Lessons to Get Started Building AI Agents
Open-source web crawler and scraper for LLMs and AI agents: any website into clean, LLM-ready Markdown. Run it yourself, or use Crawl4AI Cloud with one key.
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
Open-source AI penetration testing tool to find and fix your app’s vulnerabilities.
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.
Open Source Computer Vision Library
🌊 The original agent harness. Deploy intelligent multi-player swarms, coordinate autonomous workflows, and build conversational AI systems. Features adaptive memory, self-learning intelligence, federation, vector RAG integration, and native Claude Code / Codex / Hermes and many more Integrated
An open-source AI agent that brings the power of Gemini directly into your terminal.
Marketing skills for Claude Code and AI agents. CRO, copywriting, SEO, analytics, and growth engineering.
AirLLM 2.8T LLM inference with single 4GB GPU
real time face swap and one-click video deepfake with only a single image
Tesseract Open Source OCR Engine (main repository)
The Memory Layer for AI Agents - Drop-in memory infrastructure for AI agents and apps. Context that persists. Built for production.
《深入理解 AI Agent：设计原理与工程实践》（李博杰 著）开源主仓库：全书正文、编译版 PDF 与按章配套代码
scikit-learn: machine learning in Python
from vibe coding to agentic engineering - practice makes claude perfect
Ultralytics YOLO27, YOLO26, YOLO11, YOLOv8 — object detection, instance segmentation, semantic segmentation, image classification, pose estimation, object tracking
Stop renting your intelligence. Own it with AnythingLLM. Everything you need for a powerful local-first agent experience
12 weeks, 26 lessons, 52 quizzes, classic Machine Learning for all
Framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks.
an open source, extensible AI agent that goes beyond code suggestions - install, execute, edit, and test with any LLM
Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
The fastest path to AI-powered full stack observability, even for lean teams.
Build resilient agents.
🧠 Train a 64M-parameter LLM from scratch in just 2h!
12 Weeks, 24 Lessons, AI for All!
Ultra-lightweight, open-source, self-hosted personal AI agent framework in Python with WebUI, tools, memory, MCP, multi-agent workflows, automation, and chat apps
Deep Learning for humans
Qlib is an AI-oriented Quant investment platform that aims to use AI tech to empower Quant Research, from exploring ideas to implementing productions. Qlib supports diverse ML modeling paradigms, including supervised learning, market dynamics modeling, and RL, and is now equipped with https://github.com/microsoft/RD-Agent to automate R&D process.
A community-supported supercharged document management system: scan, index and archive all your documents
The open-source app everyone uses to manage agents at work
Ultralytics YOLOv5 in PyTorch for object detection, instance segmentation, classification, training, and export.
DeepTutor: Lifelong Personalized Tutoring. https://deeptutor.info/.
🗂 The essential checklist for modern web development, for humans and AI agents
Unrestricted Open-source alternative to AI video platforms — Free AI image & video generation studio with 600+ models (Flux, Midjourney, Kling, Sora, Veo). No content filters. Self-hosted, MIT licensed.
Streamlit — A faster way to build and share data apps.
Apache Airflow - A platform to programmatically author, schedule, and monitor workflows
[EMNLP2025] LightRAG: Simple and Fast Retrieval-Augmented Generation
Community plugin to control Blender 3D with any LLM of your choice
Build and run agents you can see, understand and trust.
