OceanBase SeekDB: A Distributed Database Engine with Hybrid SQL and Vector Retrieval Support
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...
OneAIFW: A Lightweight Open Source Firewall for Protecting the Privacy of Big Model Data
OneAIFW (aifw) is an open source tool developed by Funstory.ai that aims to address data privacy issues in Large Language Modeling (LLM). In current big model applications, users often need to send text containing personally identifiable information (PII) or trade secrets to cloud-based models (e.g. ChatGPT, Claude ....
Serversage: a GPT-driven automated penetration testing and offensive security platform
ServerSage™ is an offensive security platform based on GPT technology designed to provide organizations with continuous, automated penetration testing services. Unlike traditional periodic security scans, ServerSage mimics the workflow of a human Red Team, utilizing AI to intelligently perform reconnaissance, system probes .....
Qoris AI: AI operating system that unifies multi-intelligence collaboration, automation platform that integrates sales, customer service and knowledge base
Qoris AI is a unified "AI Operating System" designed for enterprises to address the current fragmentation of enterprise AI tools. Unlike traditional single-function chatbots, Qoris AI combines sales, customer service, knowledge base management and marketing...
Anannas: a single API gateway for free access to 500+ AI models
Anannas AI is a unified API gateway. It gives users access to over 500 large-scale language models through a single API. These models come from different providers such as OpenAI, Anthropic, Mistral, Gemini, and DeepSeek.The platform provides fail-safe routing capabilities. It can control ...
LLaMA-Factory Online
LLaMA-Factory Online: no code, easy fine-tuning 1. Introduction: (Out-of-the-box, low-code, full-link functionality coverage of the online large model training and fine-tuning service platform) LLaMA-Factory Online is the official cooperation with the star open-source project LLaMA-Factory ...
OpenAI Agent Builder: Creating AI Intelligence Without Writing Code
OpenAI Agent Builder (also known as AgentKit at the Developer Conference) is a no-code visualization tool designed primarily to help developers and enterprise users create, customize, and deploy AI intelligences. The platform provides a drag-and-drop interface that allows users to connect different...
Doraverse: an AI assistant that integrates multiple AI models and office applications
Doraverse is a work platform that integrates a variety of AI features and is positioned as an "all-in-one AI colleague" for office work. It combines more than 15 mainstream AI models (e.g. Grok, Claude, GPT, etc.) and more than 50 popular office applications (e.g. Gmail, Google Drive, No...
OpenAdapt: an open source tool for automated manipulation of computer applications using large models
OpenAdapt is an open-source software tool that connects powerful Large Multimodal Models (LMMs) to a computer's Graphical User Interface (GUI) with the aim of automating processes. Traditionally, a great deal of mental labor has been wasted on repetitive computer operations, and OpenAdapt aims to solve this...
ZenMux: A Development Tool for Collaborating Multiple AI Models to Aid Programming
ZenMux is an AI orchestration development tool with the Zen MCP (Model Context Protocol) server at its core. It allows developers to connect and collaborate a major AI (e.g. Claude) with multiple other top AI models (including Gemini, OpenAI O3, etc.). ...
Step AI desktop intelligences: desktop intelligences that use natural language to operate computers
Step AI Desktop Partner is an artificial intelligence assistant that runs on your PC's operating system and understands and executes the user's natural language commands for various computer operations. This tool is not limited to browsers and can interact directly with the operating system in depth to manage local files, access the Internet and...
Baidu MCP Plaza: a distribution platform that connects AI applications to Baidu's search traffic
Baidu MCP Square is an open platform designed for developers to help them connect the AI apps or services they develop with the huge user traffic of Baidu Search. The core of the platform is MCP (Model Context Protocol), an open standard for communicating large language models and external data sources...
X-faces: an AI authentication service for 5-minute integration
X-faces is a platform that provides artificial intelligence identity verification (KYC) services for web applications. The platform is dedicated to streamlining the user authentication process and claims to be able to complete the integration in less than 5 minutes. It does this primarily by combining Optical Character Recognition (OCR), biometrics and vivisection technologies to enable the use of...
M3-Agent: a multimodal intelligence with long-term memory and capable of processing audio and video
M3-Agent is a multimodal intelligent body framework developed by the ByteDance SEED team. Its core feature is a long-term memory capability, capable of building and continuously updating its memory by processing real-time video (watching) and audio (listening) inputs, just like humans. This memory system does not just record...
AlignLab: A Comprehensive Toolset for Aligning Large Language Models
AlignLab is an open source project developed by the OpenAlign team that provides a complete set of frameworks and tools dedicated to aligning large language models. By "alignment", we mean making the model's behavior and output more consistent with human expectations and values, such as ensuring its safety, authenticity, unbiasedness, and...
AI Proxy Worker: a secure proxy tool for deploying AI services on Cloudflare
AI Proxy Worker is a serverless proxy script deployed on Cloudflare Workers. It is primarily used to solve a core problem: how to securely invoke AI model services in a front-end application or client without exposing critical API keys. This tool takes the user's API secret...
Qwen3-FineTuning-Playground: a ready-to-use code base for fine-tuning Qwen3's big models.
Qwen3-FineTuning-Playground is an open source project that provides a complete code base dedicated to fine-tuning the Qwen3 family of large language models. The basis of this project is to provide clear, professional and easily extensible fine-tuning code examples so that developers and researchers can easily practice...
Parlant: an open source framework for providing reliable control of large language model intelligences
Parlant is an open-source framework for AI intelligentsia that aims to address the core challenges faced by current large-scale language models (LLMs) in real-world applications: unpredictability and lack of controllability. When building AI intelligences, developers often encounter models that ignore system prompts, produce hallucinatory answers, or are unable to handle edge...
LightRAG: A Lightweight Framework for Building Retrieval Augmented Generation (RAG) Applications
LightRAG is an open-source Python framework developed by a team from the School of Data Science at the University of Hong Kong to simplify and accelerate the process of building Retrieval Augmented Generation (RAG) applications. It does this by combining knowledge graphs with traditional vector retrieval techniques to provide more accurate and contextualized Large Language Models (LLMs)...
Top
