Trending AI projects

An AI-powered long-form novel writing engine that uses structured cards, knowledge graphs, and a custom context DSL to maintain consistency across millions of words.

CPA Usage Keeper is a self‑hosted dashboard that records, stores, and visualises usage data from the CLIProxyAPI (CPA) – an AI model proxy. It persists request logs in SQLite, shows cost breakdowns, latency metrics, and quota health, and can be deployed via Docker‑Compose, Homebrew, or native binaries.

An MCP server that enables AI agents to build and modify Power BI semantic models using natural language, supporting bulk operations and DAX validation.

Vigolium is an open‑source, high‑performance vulnerability scanner that offers both a fast native Go‑based scan engine with hundreds of modules and an AI‑augmented “agentic” mode that plans and executes attacks using an internal olium agent framework.

A speaker diarization pipeline that combines OpenAI Whisper for transcription with NVIDIA NeMo for speaker identification to determine who spoke which words in an audio file.

An AI-powered academic workstation for researchers that provides high-speed translation, OCR, and agentic analysis of academic papers while preserving original formatting.

TipTour is a macOS agent that automates desktop tasks by allowing AI models to see your screen and perform actions like clicking, typing, and navigating apps based on voice or text commands.

A plugin for the OpenClaw framework that prevents context loss by using a DAG-based summarization system to store and retrieve conversation history in a local SQLite database.

A Python-centric observability platform built on OpenTelemetry that provides deep visibility into application behavior using SQL-based querying and Pydantic integration.

A reconstruction of Joseph Weizenbaum's original 1965 ELIZA chatbot, running on an emulated IBM 7094 computer and the Compatible Time-Sharing System (CTSS).

A specialized GitHub CLI wrapper designed for autonomous AI agents that provides token-efficient, non-interactive, and structured access to GitHub repository management tasks.

An open-source LLM load balancer and serving platform that enables self-hosted inference, deployment, and scaling of LLMs on private infrastructure.

twinny is an open‑source VS Code extension that adds LLM‑powered code completion, chat, inline edits, code review, commit‑message generation and experimental agent mode. All model inference runs on a server you control – locally, on another device, via a hosted API, or through a team‑wide gateway. The gateway handles per‑user keys, usage logs, optional policies, and can be deployed via Docker or Helm. Free for up to five developers; paid seats add enterprise features.

Open Storyboard Canvas is a cross‑platform desktop app (macOS/Windows) built with Tauri, React and Rust that provides a node‑based canvas for AI‑generated images, videos and 3‑D storyboard scenes. It includes a chat‑based Agent (beta) that can manipulate the canvas, submit generation jobs to multiple providers, track task status and show diagnostics. The tool bundles provider configuration, prompt libraries, director‑studio 3‑D scenes and full project persistence, targeting creators who want an integrated local workflow for AI‑driven visual storytelling.

An ASI plugin for OptiScaler that enables DLSS and DLSS-FG inputs in supported games without spoofing, reducing crashes and performance overhead for AMD and Intel users.

DeepInverse is an open-source PyTorch-based library designed to solve imaging inverse problems using deep learning through a modular framework of operators and algorithms.

An automation script for Blue Archive that uses YOLOv8 for character detection to automate combat, daily tasks, and resource management.

An Agent Skill that transforms text content into structured motion-video productions, featuring a professional two-phase workflow for planning and asset generation.

dstack is a unified control plane that orchestrates GPU resources across cloud providers, Kubernetes, and on-premise clusters to streamline AI development, training, and inference.

Zero-WAM is a causal video-action policy that enables robots to perform unseen tasks zero-shot by using human demonstration videos or language as in-context specifications.

Taiwan Legal RAG is an open‑source Python CLI that queries a hosted semantic‑search service containing ~22 million Taiwanese judgments, statutes and administrative rules. It returns results as a JSON bundle that can be fed to any LLM, and includes a deterministic citation‑check to ensure the model only cites material actually present in the bundle. No LLMs or API keys are required; the heavy retrieval work runs on the remote TLR server.

Pup is a Rust‑based CLI that wraps Datadog’s full API surface, delivering JSON/YAML output and OAuth2‑secured access so AI agents or scripts can query, create, and manage metrics, logs, monitors, security data, incidents, CI/CD, cost, and many other observability resources.

A collection of practical examples and demonstrations for the Eino framework, covering AI agents, multi-agent orchestration, and RAG applications.

A desktop app for filmmakers to extract pose, depth, and camera movement from reference videos to create control bundles for AI video generation pipelines.

A diffusion-based framework for 6-DOF robotic grasp generation that supports multiple gripper types and provides real-time, collision-aware grasp predictions from 3D point clouds or meshes.

An anime scene search engine that identifies the specific anime, episode, and timestamp of a screenshot using image vector search.

A free, open-source AI chat platform that provides instant, no-signup access to multiple language models with local browser storage for privacy.

An extension for the Antigravity IDE that provides real-time AI quota monitoring, conversation cache management, and workflow automation tools.

An AI-powered digital marketing platform that builds a contextual brand brain to generate consistent, grounded content across blogs, social media, and video scripts.

Parlant is an open-source platform for building reliable, policy-compliant customer-facing AI agents that you control. It replaces expensive, closed CX platforms by allowing you to define agent behavior in code while providing the necessary infrastructure for testing, hosting, and analytics.

A Python framework for data scientists and ML engineers to build and deploy production-ready AI and data-driven web applications without needing frontend expertise.

Ui.Vision is an open‑source browser extension (with optional desktop modules) for recording and running automation macros. It supports classic Selenium‑style commands, OCR/image‑based visual actions, and a Model Context Protocol (MCP) bridge that lets LLM assistants (Claude Code, Cursor, etc.) generate, edit, and execute macros via the `uiv.*` JavaScript API.

An open-source, local AI tool that transforms long YouTube videos into viral short-form clips with automatic cropping, dynamic captions, and face tracking.

An open-source, enterprise-ready embedded BI platform that combines interactive dashboards, paginated reports, and AI-driven natural language analytics.

The Microsoft 365 Agents SDK is a flexible framework for building and deploying AI agents across various channels like Microsoft 365 Copilot and Microsoft Teams, allowing developers to use their preferred AI services and technology stacks.

A governance and engineering system that transforms rough workflows and prompts into reusable, cross-platform AI agent skill packages with built-in evaluation and release gates.

Strands Agents Samples provides Python and TypeScript example projects that demonstrate how to build, deploy, and integrate AI agents using the Strands model‑driven SDK. It includes tutorials ranging from a simple hello‑world agent to advanced patterns like multi‑agent systems, RAG, cloud deployment, and edge/robotics integration.

Microsoft Agent Framework for Go is a production‑grade SDK that lets Go developers build, orchestrate, and observe multi‑agent AI workflows. It supports multiple LLM providers (Azure OpenAI, OpenAI, Microsoft Foundry), middleware, graph‑based workflow patterns, OpenTelemetry tracing, and skill‑based knowledge bases. The repo includes install instructions, a quick‑start haiku example, and a rich set of sample projects. It’s in public preview and aligns with the broader MAF ecosystem (.NET/Python).

An agentic operating system that lets a single human act as CEO of a virtual company staffed by collaborating AI employees to deliver professional-grade products.

This project provides pre-compiled, nightly builds of the llama.cpp inference engine with integrated AMD ROCm support, allowing users to run AI models on AMD hardware without needing to manually install complex software dependencies.

A scalable reinforcement learning framework for LLM agents that enables training across diverse agent types and sandboxes with token-level trajectory recording.

yutu is a Go‑based CLI, MCP server, and AI‑agent that automates the full YouTube workflow—from uploading videos and editing metadata to handling comments, live streams, and channel branding. It integrates with Gemini or OpenAI models, offers an OpenCode skill, and can be installed via Homebrew, npm, Docker, or Go.

A portability layer and operation set for ML models that enables interoperability between different ML frameworks and ML compilers.

SuperSplat Viewer is a PlayCanvas‑based web app that renders Gaussian‑splatting (AI‑generated 3D) scenes. It runs as a static site, uses WebGPU (fallback WebGL), supports AR/VR, and is fully configurable via URL parameters. Install with npm, run `npm run develop`, and embed via its API.

A bridge that lets AI agents (Claude, Codex, etc.) call freee’s business‑software APIs via a secure MCP server and a set of “Agent Skills” describing each endpoint.

Solace Agent Mesh is an agent development and runtime platform that hosts AI agents, runs their tools, and coordinates them over an event broker. The repository currently provides Agent Mesh Desktop (a free app with the `sam` CLI) and examples, not the source code yet. Production requires a commercial license via Kubernetes or Agent Mesh Cloud.

A hardened, minimal Linux operating system purpose-built for running AI agents securely with dedicated orchestration daemons and reproducible image builds.

A collection of generative models from Sony AI for creating high-quality sound effects via text-to-audio and video-to-audio generation.