Trending AI projects

A standardized communication protocol that enables multiple client applications to connect to and synchronize state with AI agent sessions.

An open-source, Python-based educational book that teaches causal inference and impact estimation through a rigorous yet light-hearted and accessible approach.

decider is an open-source collection of language models that, instead of generating text, read a state and typed questions (choice, score, or yes/no) and output calibrated probability distributions for each question in a single forward pass. It includes models from 0.8B to 35B parameters, with weights on Hugging Face, and ranks well on third-party decision benchmarks.

An enterprise-grade open-source RPA desktop application that enables low-code automation of Windows desktop software and web pages with native AI agent integration.

roboflow/notebooks is a GitHub repository containing 61 Jupyter notebook tutorials for computer vision, covering models like YOLO, SAM, Gemini, and Qwen2.5-VL. Each notebook can be opened in Colab, Kaggle, or SageMaker Studio Lab, and includes links to related blog posts, videos, and papers. It's designed for hands-on learning of tasks like object detection, segmentation, OCR, and data extraction.

A production-grade Sanskrit chant text-to-speech system that generates traditional melodic recitation instead of flat read-aloud speech.

A full-stack AI learning platform that combines a learning roadmap, popular AI interview questions, AI-graded practice with follow-up discussion, a gamified growth system, and a suggestion community — built with Vue 3, Spring Boot, FastAPI, and MySQL.

AI Hero is an open-source educational project that provides developers with the code, exercises, and tools needed to transition into AI engineering.

A browser automation skill for Codex that offloads repetitive navigation and clicking to the Jev model to increase speed and reduce token costs.

A unified evaluation toolkit for Large Multimodal Models that provides reproducible and efficient benchmarking across image, video, and audio tasks.

A context gateway for AI systems that optimizes token usage and costs by selecting, compressing, and filtering task-relevant information before it reaches the LLM.

A comprehensive, 14-week open-source curriculum covering the entire spectrum of Natural Language Processing, from foundational word embeddings to modern LLM systems and AI agents.

An open-source, self-hosted platform for tracking and optimizing brand visibility and citations across AI answer engines like ChatGPT, Perplexity, and Gemini.

A high-performance Rust-based tokenizer for language modeling that provides up to 1000x speedup over HuggingFace tokenizers by using SIMD-optimized pretokenization.

A lightweight, cross-platform library for building AI-integrated XR experiences that works across both specialized headsets and desktop browsers.

A structured, all-in-one repository of learning roadmaps, books, courses, papers, tools, and communities for mastering AI/ML/DL — with separate paths for different career goals and skill levels.

SREGym is an AI-native benchmarking platform that provides live Kubernetes environments to evaluate and train AI agents in diagnosing and mitigating real-world Site Reliability Engineering (SRE) failures.

CrispASR is a C++‑only speech engine that runs 119 open‑weight ASR and TTS models from a single binary. It offers zero‑Python dependencies, cross‑platform builds (including WebAssembly), GPU‑accelerated CUDA/Vulkan/HIP options, an HTTP server API, streaming, and language bindings. The project includes a rich ecosystem (Flutter app, embedding library, Python GUI) and extensive documentation for quick start, model management, and compliance.

A bilingual Python-based desktop voice assistant that automates daily computer tasks, system controls, and web searches through voice commands.

A local rendering tool that converts Mermaid diagram source into SVG, PNG, and ASCII formats, specifically designed for integration with AI agents and terminal-based workflows.

A tool and set of guidelines that prevents AI agents from including rejected ideas or conversational residue in final deliverables like commit messages and PR titles.

An open‑source SvelteKit web UI for chatting with any OpenAI‑compatible LLM endpoint. Handles history (MongoDB), theming, optional smart routing (Omni), MCP tool calling, and provides a Docker image for easy deployment. Powers HuggingChat and can be used with local servers (llama.cpp, Ollama) or cloud providers.

A Claude Code skill that generates professional presentation decks and responsive websites by combining extracted brand DNA with codified, research-backed design principles.

PenEcho is an interactive, AI-powered canvas that allows users to turn sketches and notes into diagrams and working widgets, integrating with AI agents via the Model Context Protocol.

A multi-model orchestration framework for Codex that allows a lead model to plan, delegate, and review work performed by various worker models and tools.

humanize is an MIT‑licensed repo that ships two static, rule‑based skills—`humanize` (rewrites AI text to sound human) and `ai-check` (produces a forensic AI‑detection report). The skills work with any LLM agent (Claude Code, Codex CLI, ChatGPT desktop, Gemini, etc.) via a simple install script or marketplace command. Benchmarked on 25 diverse inputs, both internal and external perplexity‑based detectors rate the rewritten output as human‑like. The approach is offline, zero‑dependency, but cannot evade learned classifiers like GPTZero.

An agentic security automation platform that enables security teams to build AI agents and durable workflows for automated cyber defense and incident response.

Bug Hunter is an adversarial AI code-audit tool that uses a multi-agent system of hunters, skeptics, and referees to filter out false positives and provide evidence-backed security and behavioral bug reports.

FlyEnv is a cross‑platform desktop app that natively installs, versions, and orchestrates runtimes (PHP, Node, Python, Java, Go, etc.) and services (databases, caches, search, web servers). It offers per‑project workflow definitions, local HTTPS domains, and an MCP server that lets AI coding assistants query the local stack. Available via installers for Windows, macOS, and Linux, it’s open‑source (BSD‑3‑Clause) and targets developers who want a native alternative to XAMPP/Laragon/Docker for full‑stack local development.

Agent of Empires (AoE) is an open‑source session manager for AI coding agents on Linux/macOS. It runs each agent in a persistent tmux session, adds git worktree and container sandboxing, and provides TUI, web, CLI, and HTTP API interfaces for monitoring and control.

A real‑time noise‑suppression audio plugin (VST, LV2, LADSPA, AU) that uses the RNNoise neural‑network model to mute background sounds from a microphone. Works at 48 kHz, offers VAD‑based controls, and can be built for Windows, Linux and macOS.

PACE is an Apache‑2.0 Python framework that identifies actuator and joint dynamics for legged robots, optimises them with CMA‑ES, and plugs the results into NVIDIA Isaac Lab to improve sim‑to‑real locomotion performance.

DeepChat is an open-source, local-first desktop client that unifies AI models, agent protocols like MCP and ACP, and reusable skills into a single, traceable workspace.

A comprehensive evaluation platform for large language and vision-language models that integrates over 100 datasets and multiple inference backends for standardized benchmarking.

A distributed GPU-accelerated framework compatible with PyTorch for scalable evolutionary computation, offering a vast library of algorithms and benchmark problems.

gcx is a CLI for Grafana that lets you query metrics, manage alerts and dashboards, and work with Grafana Cloud products from the terminal or AI coding agents. It supports Grafana Cloud, Enterprise, and OSS, with full support for Grafana 13+ and limited support for 12. Installation is via script or Homebrew. It integrates with AI agents via bundled skills. Some Cloud features incur usage costs.

iCTRL is an AI-friendly automation service for iOS that exposes a JSON-RPC API, allowing AI agents to control an iPhone by reading the screen, tapping, typing, and navigating apps.

A Rust-based command-line tool to query and export local encrypted WeChat data, featuring AI-friendly outputs for integration with LLM agents.

An open-source AI poster design tool and online image editor featuring a DOM canvas, AI background removal, and a full management backend.

Jac is a unified programming language and toolchain that allows developers and AI agents to build full-stack applications in a single, compiler-checked codebase, eliminating the need for glue code and external database management.

A cloud-native AI agent framework that decomposes monolithic agents into serverless components for better scalability, security, and cost-efficiency on AWS.

A collection of extensions and libraries for the Pi Coding Agent that adds advanced coding tools, workflow automation, and observability features.

A collection of 50 specialized Claude Code sub-agents that turn Claude into an offensive security research assistant for penetration testing and red teaming.

Ratel is a Rust‑backed retrieval engine with TypeScript and Python SDKs that lets LLM agents load only the tools and skill playbooks they actually need for each turn, cutting token cost and improving accuracy. It works with any model, requires no vector DB, and provides adapters for popular agent frameworks.

A local-first control plane and MCP server that allows any LLM to author, edit, and execute ComfyUI workflows using natural language.

A Node.js CLI tool that synchronizes AI development tool configurations by generating tool-specific files from a single, unified source of truth.

A terminal-native AI coding assistant that uses persistent memory and multi-agent orchestration to handle long-horizon software development tasks.

LLM Wiki Agent is a local, agent‑driven system that ingests PDFs, DOCX, markdown, etc., extracts entities and concepts, builds an ever‑growing inter‑linked markdown wiki, flags contradictions, and generates a visual knowledge graph—all without a server or database.