Superpowers is an underlying skills framework and standard software development workflow tool built for AI programming intelligences (e.g. Claude Code, Cursor, Codex, Gemini, etc.) and open-sourced by developer obra. It is built on proven software engineering methodologies and aims to address current...
Antigravity-Tools-LS is a high-performance native AI protocol adaptation gateway specially customized for Antigravity IDE. It breaks the conventional reverse proxy model and adopts the “pure native LS path” technical architecture to take over the native AI protocol by deeply simulating the IDE's internal plugin protocol...
OpenClaw Zero Token is a spin-off version of the famous open source project OpenClaw, whose core goal is to eliminate the high cost of API Token fees and achieve completely free access to all major AI platforms. Through Playwright browser automation technology to take over the user's local ...
OpenClaw (formerly Clawdbot/Moltbot) is a free and fully open-source autonomous artificial intelligence agent (AI Agent) system capable of performing a variety of complex tasks directly on the user's local device using a large language model. Unlike traditional AIs that can only engage in text-based conversations, OpenClaw is designed to be “truly...
Lossless Claw is an open source Lossless Context Management (LCM) plugin for OpenClaw intelligences developed by Martian Engineering. Based on Voltropy's LCM research paper, it is designed to address the problem of “sliding windows” that intelligences experience when having long conversations or running overnight workflows, due to...
LobsterAI (Chinese name: Youdao Lobster) is a desktop-level full-scene personal assistant intelligent body (AI Agent) launched by NetEase Youdao open source. With the traditional “question-and-answer” chat model is different, LobsterAI's core positioning is “direct hands-on work”, it can act as a user's digital alter ego, autonomy to take over and operate the personal electric ...
InkoS (Ink Operating System) is a Multi-Agent automated writing system for long stories, open-sourced by developer Narcooo in 2026. In the face of traditional AI in the generation of long texts often appear character memory loss, broken strokes, logical contradictions and vocabulary ...
TavilyProxyManager is an open source transparent reverse proxy system designed for Tavily API . Its core function is to developers in the hands of multiple Tavily API key (Key) unified aggregation to a proxy pool , only a custom Master Key exposed to the outside ...
ProxyLLM is an open source Electron application that runs on the user's computer. Its core logic is very straightforward: open the official web pages of ChatGPT, Claude, Gemini and other big models through a built-in browser window, listen to and capture the network packets generated by the user's interactions with the web page in real time (e.g., ...
Antigravity-Manager is a desktop tool. It helps users to manage multiple AI accounts. Users can easily switch accounts. The tool supports models such as Gemini and Claude. The core is to provide a local API staging area. Users don't have to worry about account limits. The tool is built with Tauri v2 and React...
LittleCrawler is a modern social media data collection framework built on Python asynchronous programming techniques. It is designed for developers and data analysts who need to obtain public social media data, and is able to automate the collection of information from mainstream social platforms (currently supporting Xiaohongshu, Zhihu, and Idle Fish/Small Yellow Fish). With the traditional single ...
OceanBase SeekDB is a vector retrieval engine in the core of the OceanBase database, built specifically for the AI era. Rather than being a standalone database product that requires separate operations and maintenance, it fully embeds the capabilities of a vector database within OceanBase, a mature distributed relational database. From...
Code2Video is a pioneering video generation framework from the NUS Show Lab, with a core philosophy of "code-centric" generation of high-quality educational videos. Unlike traditional AI video models that generate pixels directly (e.g., Sora), Code2Video does not "draw" the video directly...
ChatTutor is an open source visual and interactive AI teaching assistant tool. Traditional chatbots interact mainly through text, which is sufficient in most scenarios, but in science and engineering learning, the information that can be conveyed by plain text is very limited.ChatTutor aims to solve this problem by equipping the AI with a wide range of teaching like whiteboards...
ALLWEONE presentation-ai is an open source artificial intelligence presentation generation tool positioned as an alternative to the well-known app Gamma.app. Users only need to input a topic and the tool can automatically create a set of professional slides with complete content and beautiful design in a few minutes. It integrates advanced AI...
Drawnix is a powerful open source online whiteboard tool that integrates mind mapping, flowcharting, and hand-drawing functionality on an infinite canvas, providing users with the freedom to create. The tool is free and can be used directly in the browser without complex installation and deployment.Drawnix is developed on a pluginized architecture, which makes it...
DeepAnalyze is an intelligent agent large language model designed for autonomous data science. Without human intervention, it can independently perform tasks across the entire data science process, which include data preparation, analysis, modeling, visualization, and report generation.DeepAnalyze is able to drill down into a wide range of data sources, whether...
GEPA (Genetic-Pareto) is a framework for optimizing various types of text components in AI systems. These textual components can be prompts, code snippets or configuration files of AI models. It uses an approach called Reflective Text Evolution to analyze and reflect on the behavior of AI systems through Large Language Models (LLMs). With ...
DeepSeek-OCR is an optical character recognition (OCR) tool developed and open sourced by DeepSeek-AI. It proposes a new approach called “Contextual Optical Compression”, which rethinks the role of the visual coder from the perspective of the Large Language Model (LLM). The tool does not simply recognize graphs...
Top
