Trending AI projects

nvitop is a Python‑based, cross‑platform interactive viewer for NVIDIA GPUs. It shows detailed, colour‑rich device and process information, can run in a live monitor mode with keyboard/mouse controls, lets you send signals to processes, includes a CUDA‑visible‑devices selector (`nvisel`), and provides Python APIs and an exporter for Prometheus/Grafana. Install via pip/conda or run with `uvx`/`pipx`.

An open-source tool that simplifies local AI model inference by packaging models and their dependencies into OCI containers, eliminating host system configuration complexity.

An AI-powered tool that automatically collects, recognizes, and organizes electronic invoices from emails into categorized folders and Excel reports for reimbursement.

A RAG-based system that converts Bilibili video collections into a searchable personal knowledge base by transcribing audio to text and indexing it for AI-driven Q&A.

An Android application that translates manga by detecting text bubbles and using local or AI-powered OCR and translation to overlay translated text directly onto images.

A semantic version control tool built on Git that diffs code at the entity level (functions, classes, methods) rather than by lines, designed for both humans and AI agents.

AIMM is a Python tool that logs into Facebook Marketplace, searches for user‑defined items, uses an LLM to rate each listing, and sends instant notifications via many channels. It offers a CLI, an AI‑guided configuration wizard, a local web UI, and Docker/NAS deployment options.

A collection of agent skills that teach AI coding assistants how to integrate, manage, and migrate to the Langfuse LLM engineering platform.

Pre-built Python bindings for OpenCV that allow users to install the computer vision library via pip without needing to manual compilation.

Code-as-World is a framework that represents the physical world as executable code to enable AI models to perform quantitative physical reasoning by discovering world representations through iterative simulation.

WindsurfAPI is a self-hosted Node.js gateway that translates Windsurf/Devin cloud AI models (100+) into standard OpenAI, Anthropic, and Gemini APIs, letting you use any existing SDK or agent with your own accounts.

A lightweight 8.3B parameter video generation model that enables high-quality text-to-video and image-to-video synthesis on consumer-grade GPUs.

ida-mcp-rs is a headless IDA Pro MCP server that lets AI coding agents directly load, analyze, and edit binary databases using IDA's engine. It provides a fast, lean, and crash-safe toolset for reverse engineering, with special support for Apple binaries and dyld shared caches.

Markra is an open‑source, local‑first Markdown editor that combines true WYSIWYG editing with built‑in AI assistance. Users can invoke LLMs (any OpenAI‑compatible or local model) to polish, rewrite, summarize, translate, or otherwise edit selected text or whole documents, with a preview step before changes are applied. The desktop app (Tauri) runs on macOS, Windows, and Linux; a web version mirrors the same features. Files stay as plain `.md` on disk, with optional WebDAV sync, image storage options, spellcheck, custom CSS themes, and export to HTML/PDF. Licensed under AGPL‑3.0 and community‑driven.

An MCP server that enables AI models to interact with Slack workspaces, allowing them to read, search, and manage messages, users, and channels.

A local, swarm-intelligence global forecasting system that fuses over 40 real-time data feeds into a 3D intelligence globe to predict world events.

A framework for improving AI agent output by shaping the environment, context, and tools around them rather than modifying the model itself.

A network observability tool for Kubernetes that uses eBPF to index traffic and provides AI-driven troubleshooting via MCP integration.

Swival is an open-source coding agent that works with local and online AI models, featuring built-in security filters and context management for long-term tasks.

A Chinese-language educational resource that adapts the Hands-On Large Language Models book with optimized code environments, video tutorials, and localized tools to help developers learn LLM implementation without network or hardware barriers.

A Git-based memory standard that allows AI agents to maintain persistent, linked knowledge across sessions, users, and agent swarms.

FineEnvs is a genuine open‑source suite of RL environments for training LLM agents, offering end‑to‑end code, hosted Spaces, datasets, and reproducible training pipelines across multiple frameworks.

Open Browser Use is an open‑source, runtime‑agnostic browser‑automation layer for AI agents. It pairs a Chrome extension with a CLI and provides JavaScript, Python, and Go SDKs plus an MCP server, enabling agents to list tabs, open URLs, navigate, and run CDP actions. Install via npm or Homebrew, run `open-browser-use setup` to register the native host, then add the skill to agents like Codex or Claude‑Code. MIT‑licensed.

Vigil is an open-source, agentic SOC platform that uses readable Markdown workflows and MCP-based integrations to automate security operations while ensuring human oversight.

A distributed, scalable graph database designed for large-scale graph analytics and millisecond latency in applications like knowledge graphs and recommendation systems.

An open-source AI video creation workbench that uses an infinite canvas and a natural-language assistant to manage the pipeline from script to final video.

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 plugin for OpenCode that enables long-running, goal-oriented agent behavior with persistent state, automated task continuation, and strict safety guardrails.

CORAL is an open-source infrastructure for autonomous AI agent organizations to perform autoresearch by running experiments and sharing knowledge to evolve solutions.

A cognitive-driven autonomous security agent for authorized penetration testing that uses causal graph reasoning and a Planner-Executor-Observer architecture to ensure traceable, evidence-backed security research.

A command‑line AI‑DevOps framework that orchestrates specialized agents to turn natural‑language intent into verified software‑delivery outcomes, with Git‑based context, safe automation (Pulse/workers), model‑routing, and security features.

OSWorld is an open‑source benchmark that lets you run multimodal LLM agents inside real Ubuntu/Windows virtual machines. It provides a Python library (`desktop‑env`) to launch VMs via VMware, VirtualBox, Docker, AWS, Modal, or Daytona, a set of realistic desktop tasks, reference GPT‑4o agents, and tools for scoring and visualising results.

An MCP server that integrates the SearXNG API to give AI assistants privacy-respecting web search and URL reading capabilities without requiring paid API keys.

gemini-web-to-api is a Go-based proxy server that exposes Google Gemini's web interface as standardized REST APIs. It lets you use Gemini's latest models without an API key by authenticating with browser cookies, while providing OpenAI, Claude, and Gemini-compatible endpoints.

A TypeScript‑typed collection of JavaScript libraries for interacting with Hugging  Face: managing Hub repos, calling inference APIs (chat, text‑generation, image generation, etc.), parsing model file formats, and building tiny LLM agents, all runnable in browsers or modern Node/Deno runtimes.

AgentFS is a SQLite-based filesystem designed for AI agents that provides persistent storage, key-value state management, and a full audit trail of tool calls in a single portable file.

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.

A curated directory of AI persona skills that distill the communication styles, decision-making frameworks, and expertise of specific individuals or roles into reusable, interactive digital agents.

A curated, actively maintained list of 64 AI-focused tools for building beautiful user interfaces, organized into five categories (skills for AI assistants, apps, MCP plugins, non-AI design tools, and learning resources), with editor's choice picks and a contribution invite.

A curated, bilingual library of 135 professional AI prompts organized by scenario, designed to provide clean, copy-pasteable templates for tasks ranging from marketing and content creation to learning and technical workflows.

A curated directory of AI tools, frameworks, and datasets designed to accelerate scientific research, covering everything from literature management and document parsing to autonomous research agents.

A single-person maintained directory of free LLM APIs, curating both providers and recommended models. Only OpenAI-format endpoints are listed, with per-provider rate limits and model names. Selection prioritizes long-term stability, rate-limit style, source diversity, and model quality. Community submissions are welcome, and the visual table is LLM-generated.

dsh‑commandcode‑provider is an unofficial DeepSeek Harness plugin that adds Command Code as an LLM provider. It offers UI integration, multi‑account rotation, plan‑aware model picking, vision support, cost estimates, quota display, web‑search, and optional zero‑data‑retention, working with dsh 0.2.x.

An open-source AI marketing plugin providing a standardized 12-part strategy flow and 163 skills to help agencies and in-house teams manage large brand portfolios consistently.

LLM4AD Next is a Python library that uses a conversational LLM to turn a natural‑language problem description into a complete, runnable evolutionary‑algorithm search pipeline. It ships with multiple GA‑style search methods, modular “algorithm‑design skills”, an advisor that can suggest code blocks to evolve, and an online demo. Install via `uv sync` (Python 3.12+), configure an LLM provider, then run `llm4ad chat` to generate a project and `llm4ad run <config>` to evolve the best algorithm.

Firefox DevTools MCP is an open‑source Model Context Protocol server that lets AI agents control a local Firefox browser—including its developer tools—via WebDriver BiDi. It enables agentic browsing and AI‑assisted web development, exposing tools like navigation, form filling, network inspection, console access, and JavaScript evaluation. The server runs locally (via `npx @mozilla/firefox-devtools-mcp@latest`), works with Claude Code, Codex, Cursor, etc., and offers security‑focused presets to limit capabilities.

A curated list of ChatGPT-related GitHub repositories, with a search tool and integrations for AI coding assistants.

FastEmbed is a lightweight, fast Python library for generating embeddings (numerical representations of meaning) from text, images, and documents. It uses ONNX Runtime instead of PyTorch, runs on CPUs without a GPU, and supports dense, sparse, late-interaction, image, and multimodal embedding models, plus rerankers. It integrates with the Qdrant vector database and is designed for serverless environments.