A local AI creative studio and video editor that uses an LLM-directed workflow to automate the production of music videos and short films.

A visual, infinite canvas workspace that integrates multiple AI APIs and local ComfyUI workflows for collaborative generative AI content creation.

pxpipe is a local proxy that compresses large text context (system prompts, tool outputs, old chat history) into PNG images before sending requests to vision‑enabled LLMs like Claude Code and Gemini, typically saving ~60‑70 % of input tokens. It includes a dashboard, offline export, and a Node API, but the rendering is lossy and works best on dense, code‑like content.

ComfyUI‑KJNodes is a plug‑in for the visual Stable Diffusion UI (ComfyUI) that adds utility nodes, cross‑sub‑graph Set/Get handling, and many keyboard/mouse shortcuts to make large generation graphs easier to build and maintain.

PenEcho is a visual canvas app that integrates with LLM agents via the Model‑Canvas‑Protocol (MCP). It lets you draw, annotate, embed widgets, and have AI agents read and edit the canvas, creating a tight feedback loop between conversation and visual work. Available as a desktop app or npm package, it supports both local and cloud‑hosted models and offers versioned projects, sharing, and a built‑in assistant.

An official inference framework for 1-bit (ternary) LLMs that enables fast, energy-efficient, and lossless inference on CPUs and GPUs.

An AI-native, CLI-first React component library that delivers raw source code for 160+ animated components, featuring a native MCP server for AI agent integration.

An open-source software factory for agentic coders that provides a controlled and repeatable environment for AI coding workflows while keeping credentials and repository access local.

An open-source developer platform for Kubernetes that provides high-level abstractions for developers and AI agents to build and deploy apps without managing low-level cluster primitives.

A local-first Markdown editor with a built-in agent surface and MCP server, allowing AI agents to safely automate and interact with your personal knowledge base.

A comprehensive open-source library of AI skills, personas, and Python tools that enables professional workflows across engineering, product management, and regulated compliance domains.

A community-maintained Linux distribution of the official OpenAI ChatGPT desktop app that adds optional Linux-specific features and multi-distro package support.

MiniMind‑O is a genuine open‑source, tiny (≈0.1 B) end‑to‑end omni model that jointly handles text, speech and images as inputs and produces text and streamed speech outputs. It provides full PyTorch code, training scripts, mini/full datasets, pretrained weights, voice‑cloning prompts, and demo interfaces (CLI, Gradio, phone‑mode UI). The repository is clearly an AI/ML project, not an off‑topic list.

A security auditor for AI agent configurations that scans Claude Code setups for secrets, permission misconfigurations, and prompt injection vectors.

A collection of 14 expert skills and an enforcement layer for Claude, teaching it how to build production-ready n8n workflows and deploy self-hosted instances using the n8n-mcp MCP server.

An open-source desktop app that uses AI agents and a local SQL engine to analyze and actually operate on social chat histories from multiple platforms privately.

FlagTree is a unified open-source compiler for multiple AI chips that enables a "develop once, run anywhere" workflow by unifying various Triton-based backends.

An MCP server that enables AI agents to connect to running Flutter apps to inspect the UI, perform interactions, and conduct automated smoke testing.

A public experiment and marketplace where AI agents perform real commercial work for real money, tracking their success and failure rates in a public ledger.

A code-first Go toolkit for building, evaluating, and deploying modular AI agents and multi-agent systems.

An open-source AI voice input tool for macOS, Windows, and Linux that provides app-aware dictation, voice Q&A, and text rewriting.

A context engineering tool that converts entire codebases into structured prompts for LLMs, featuring a CLI, Python SDK, and MCP server.

An open‑source set of AI‑Agent skills that automate the end‑to‑end workflow of writing, reviewing, formatting, illustrating and publishing WeChat public‑account articles, while pausing for user confirmation at each step.

A CUDA-accelerated library for Visual Odometry and SLAM that provides real-time, high-accuracy tracking and mapping across various camera and IMU configurations.

A comprehensive reinforcement learning platform for fluid dynamics that provides a Gymnasium-compatible interface to over 60 CFD environments across six different solver backends.

A real-time audio translation tool for Windows that captures system audio and microphone input to provide live translated subtitles via an LLM-powered overlay.

An AI-powered multi-agent travel planning platform that creates personalized itineraries by distilling real user data from Xiaohongshu and integrating real-time weather, hotels, and mapping services.

An enterprise security system for AI agents that provides discovery, observability, and threat detection to secure employee-facing and customer-facing agentic AI tools.

A methodology and set of patterns for structuring AI agent workflows using a filesystem hierarchy instead of complex orchestration frameworks, enabling human-in-the-loop review and high observability.

A self-hosted AI agent harness that allows agents to automatically build, test, and reuse their own tools in a sandboxed environment.

A visual conversation workbench for DeepSeek Harness that organizes chat sessions, follow-ups, and branches into an interactive, zoomable map.

A loop engineering framework that turns existing AI agents into long-running computer-use systems by wrapping them in a structured plan-act-verify cycle across GUI and CLI environments.

A comprehensive reverse engineering toolkit for Web interfaces that helps analyze obfuscated JS and restore API signatures using an anti-detection browser workflow.

An MCP server that integrates Lanhu design and requirement documents into AI IDEs, enabling shared team knowledge and automated UI asset extraction.

A multimodal toolset for AI agents to generate and edit professional images, videos, and audio via a schema-driven architecture powered by muapi-cli.

An open-source evolutionary coding agent that uses LLMs and MAP-Elites to autonomously discover and optimize algorithms and hardware-specific code.

A scalable platform for running AI agent environments using Firecracker microVMs, featuring rapid snapshot-based booting and high-density resource management.

Toolcraft is an open‑source starter kit and UI library for building custom, browser‑based design tools (image filters, gradient generators, animation editors, etc.). It ships a React + TypeScript + Tailwind stack, a pan/zoom canvas, a rich component library, layer/timeline support, export utilities, and a set of prompts that let AI coding assistants (Codex, Claude, Cursor) scaffold and extend the app via a simple CLI (`npx @pixel-point/toolcraft create`). The generated project runs locally (default http://localhost:3002) and can be deployed anywhere. MIT‑licensed, cross‑platform, and intended for developers who want AI‑assisted rapid prototyping of niche design workflows.

PhotoPrism is an open‑source, self‑hosted web app that uses on‑device AI to automatically tag, search, and organize personal photos and videos while keeping all data private.

SkillAlchemy is an open‑source framework that automatically builds reusable, installable agent skills from vague task briefs by mining public documentation, papers, and code. It discovers hidden requirements, extracts evidence‑backed procedures, judges their scope, and packages them for LLM agents like Claude Code or Codex. Evaluated on 87 benchmark tasks, it reaches a 55.8 % pass rate, outperforming existing automated skill creators and rivaling human‑curated skills. Install via `npx skills add agentsope/SkillAlchemy` and invoke the agent to generate a skill.

An observable and replaceable enterprise RAG infrastructure that provides a controllable pipeline for document parsing, chunking, and retrieval with built-in regression testing.

A session cleaner and prompt injection tool for AI coding assistants (Codex, Claude Code, OpenCode) designed to bypass refusal responses during security testing and CTF competitions.

A scalable reinforcement learning algorithm that uses world models to master diverse control tasks with a fixed set of hyperparameters.

Hunter Community Edition is an open‑source, Docker‑compose‑deployed financial AI agent platform. With a single LLM API key it provides real‑time market data (32+ sources), 23 pre‑built analysis SKILLs, a local “investment thesis” memory, and plug‑and‑play model compatibility (DeepSeek, Claude, Qwen, etc.). Everything runs on the user’s machine—data, chat history, and thesis stay on local disk—while remaining extensible via custom Markdown SKILLs or user‑provided MCP data services.

A one-stop AI quantitative trading platform that provides tools and strategies for everything from learning and simulation to real-market deployment across multiple asset classes.

An AI-native, open-source backend-as-a-service providing Postgres, auth, serverless functions, and an AI gateway with built-in MCP server support for AI agents.

A high-performance sandboxed Python interpreter written in Rust designed for the safe and efficient execution of AI-generated code.

JimuReport is a free, open‑source web platform for building reports, dashboards, and big‑screen visualizations. It offers an Excel‑style drag‑and‑drop designer, supports 30+ data sources, and includes JimuChatBI – a conversational AI that generates or edits visualizations from natural‑language prompts using any OpenAI‑compatible model.