Trending AI projects

Roboflow Inference is a self‑hosted server that turns any machine into a computer‑vision hub. It serves your own or public models, lets you build composable “Workflows” that combine detection, segmentation, OCR, tracking, and custom Python code, and provides a REST API plus Python SDK for real‑time video stream processing. Runs via Docker on CPU or GPU, supports edge devices, and offers optional cloud/enterprise extensions.

An open-source cloud architecture diagram generator that creates professional AWS, Azure, and GCP diagrams from either plain-English AI prompts or Terraform code.

mcp‑handler is a TypeScript library that converts a Model Context Protocol (MCP) server into a standard Fetch `(Request) => Promise<Response>` handler. It works with Next.js, Nuxt, SvelteKit, Hono, etc., and supports both the latest 2026‑07‑28 MCP spec and the older 2025 Streamable‑HTTP fallback, plus built‑in OAuth‑CIMD authorization helpers.

Scarf is a native Swift‑UI GUI for the Hermes AI‑agent, offering dashboards, chat (text & voice), project management, and full configuration over SSH on macOS and iOS.

SAGA is a framework for segmenting 3D Gaussian Splatting scenes, allowing users to isolate 3D objects using interactive point prompts or open-vocabulary text queries.

VSLAM‑LAB is a command‑line framework that unifies dataset handling, baseline installation, experiment execution, and evaluation for visual SLAM research. It supports dozens of SLAM algorithms and datasets, uses the pixi package manager for reproducible environments, and offers YAML‑based experiment definitions, headless operation, and live iPhone streaming. The project is GPL‑v3 and includes citation info for academic use.

A tool that detects hallucinated citations in academic papers by extracting references from PDFs and validating them against multiple academic databases.

Olive is an AI model optimization toolkit that automatically transforms models into efficient ONNX formats tailored for specific hardware, ensuring high performance for cloud and edge deployment.

A set of AI-enabled effects and generators for Audacity that run 100% locally using OpenVINO to provide music separation, noise suppression, and transcription.

A curated collection of pre-compiled Python wheels for AI/ML libraries that are difficult to install on Windows, eliminating the need to build from source.

A self-hosted AI app builder: one HTTP request spawns an isolated container, runs a coding agent against your prompt, and returns a live preview URL — with your own models, data, and infrastructure. The idea: instead of sending your code to a hosted builder like Bolt or v0, you own the whole stack. sandboxd is intentionally small — Go + Docker + Traefik + SQLite, no Kubernetes — and favors operational simplicity: idle containers sleep and wake automatically, so many apps fit on one machine. Two ways to use it: a REST API for embedding into products, or a no-code web console (a pure API client) for interactive building. Beyond AI generation, it can launch 80+ curated open-source apps as one-click containers. Not for everyone: the README says skip it if you just need a couple of containers (a Docker script suffices). It's aimed at scenarios like AI app-builder products, agent platforms, per-user preview environments, or team multi-app hosting. Monetization: MIT-licensed core, optional managed cloud and BYOC services.

A set of ComfyUI nodes that provides a guided, error-checked interface for creating the complex, structured prompts required by the MiniMax H3 video model.

This project is a ComfyUI extension that allows users to integrate the MiniMax H3-LongMedia model into their local node-based generation workflows.

An AI-powered internationalization solution for web and mobile apps that provides per-component content management, a visual editor, and a CMS.

AIUsage is a macOS dashboard that centralizes the management, configuration, and usage tracking of multiple AI coding tools and API providers, allowing developers to switch between models and accounts seamlessly.

A locally-hosted AI agent that integrates personal files and applications through an extensible package system and a unified web interface.

The repository provides open‑source hardware designs and assembly instructions for building high‑performance, locally‑run AI workstations (from a 2‑GPU desktop to an 8‑GPU rack). It pairs the hardware with open‑source inference software (Grid, vLLM, Ollama, llama.cpp) so users can run large language models on‑prem, avoiding cloud costs and preserving data privacy.

A suite of Python packages for Neuro AI, providing tools for curated dataset fetching, high-performance data loading, and scalable model training and benchmarking.

A lightweight, YAML-driven Python robot simulator for rapid prototyping of navigation, control, and learning algorithms in 2D environments.

projectmem adds a local, file‑based memory layer for AI coding assistants. It records typed events (issues, attempts, fixes, decisions) in a hidden `.projectmem/` folder, serves them via a single MCP server, and provides git‑hook pre‑commit warnings and visual dashboards so agents can reuse past experience and avoid repeating failures.

BuildingAI is an enterprise-grade, no-code platform for creating intelligent AI agents and applications, featuring built-in RAG pipelines, model aggregation, and business billing systems.

A Blender addon that uses AI agents to enable natural language control of 3D modeling, supporting both local and remote LLM backends.

A lightweight, automated runner for RWKV models that provides an OpenAI-compatible API and a user-friendly interface for chat, completion, and music composition.

A modular, lightweight Python framework for building secure, multi-agent AI applications with support for complex workflows, persistent memory, and human-in-the-loop approvals.

OpenCursor is an open-source AI coding agent for VS Code that allows developers to integrate various cloud or local models to automate coding tasks, file edits, and terminal operations with full review control.

Pipali is a desktop AI co‑worker that can read your files, browse the web, generate documents, automate routine tasks, and integrate with tools like Jira and Slack—all running in a local sandbox for safety.

A software framework for real-time predictive control using MuJoCo, enabling the authoring and solving of complex robotics tasks through various planning methods.

A library for flexible and powerful tensor operations using Einstein-inspired notation to make deep learning code more readable and framework-independent.

Watcher is an AI-powered cybersecurity platform that automates threat intelligence gathering, data leak detection, and domain monitoring to help security teams identify and respond to emerging threats.

LocAgent is a graph-guided LLM agent framework that identifies the precise location of bugs or required changes in a codebase by representing code as a directed heterogeneous graph.

PySyft enables privacy‑preserving data science by letting data owners keep raw data locally while data scientists submit sandboxed Python jobs that run on that data. It syncs over cloud‑file services (e.g., Google Drive), uses explicit peer approval, and returns only approved results.

ChatMock is a local server that exposes your ChatGPT Codex models through OpenAI- and Ollama-compatible APIs, letting you use them in any chat app or coding tool. It solves the lock-in of the official interface.

A VS Code extension that integrates DeepSeek V4 models into the GitHub Copilot Chat model picker, allowing users to keep Copilot's agent mode and tool calling while using DeepSeek's API.

IDM-VTON is a research codebase for AI-powered virtual try-on. It uses diffusion models plus body-mapping and garment-understanding tools to realistically place clothing on a person in a photo. The repo provides training, inference, and a local web demo, requires the VITON-HD or DressCode datasets, and is licensed for non-commercial use only.

A centralized management platform that provides a unified API and dashboard to create, schedule, and run AI agents across multiple disparate agent runtimes.

A ComfyUI custom node that integrates FlashVSR and FlashVSR+ for efficient, high-quality diffusion-based video super-resolution.

A tool that converts text corpora into interactive knowledge graphs of concepts using local LLMs, enabling advanced text analysis and Graph RAG.

A multi-account manager and proxy for the official OpenAI Codex CLI that enables request rotation, rate-limit management, and workspace switching across multiple ChatGPT accounts.

MLX Swift provides Swift bindings for the MLX tensor library, enabling high‑performance machine‑learning (including LLMs, vision‑language models and diffusion) on Apple‑silicon GPUs (Metal) and Linux (CPU/CUDA). It offers core tensor ops, neural‑network layers, optimizers and example apps, and can be added to Xcode or SwiftPM projects.

An open-source academic paper management tool that simplifies metadata scraping and organization, featuring LLM-powered summarization and semantic search.

A self-hosted server software for Anki Vector robots that enables free voice command functionality for Vector 1.0 and 2.0 models.

A comprehensive ANSI C image processing and analysis library used by projects like Tesseract and OpenCV to handle document and natural image manipulation.

An automated AI news aggregation and analysis platform that uses Cloudflare Workers and Google Gemini to generate and publish daily AI reports to GitHub Pages.

A 3D visualization tool that replays coding-agent sessions on a map of a codebase to reveal how agents explore and modify files.

An AI-powered Docker security scanner that prioritizes vulnerabilities using EPSS and provides plain-English explanations and concrete fixes for Dockerfiles and Compose files.

A Python SDK for the Langfuse platform that provides observability, tracing, prompt management, and evaluation tools for LLM applications.

EdgeBench is a benchmark and evaluation harness (SForge) designed to measure how autonomous AI agents learn and improve through iterative interaction with real-world environments over long time horizons.

A collection of software builds and container images that enable modern machine learning frameworks and ROCm tools to run on deprecated AMD GFX906 architecture GPUs.