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, etc...
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 probing,...
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 functional modules (...
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 effort has been wasted on repetitive computer operations, and OpenAdapt aims to solve this problem. It works originally ...
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 the operating system of a personal computer and understands and executes the user's natural language commands for various computer operations. The tool is not limited to browsers and can interact directly and deeply with the operating system to manage local files, access the Internet and perform cross-application tasks. The user is reached via a hovering desktop right...
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 have developed with Baidu Search's huge user traffic. At the core of the platform is MCP (Model Context Protocol), an open standard protocol for communicating large language models and external data sources. Developers...
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 identity verification process and claims to be able to complete integrations in less than five minutes. It focuses on automating the verification of user identities by combining optical character recognition (OCR), biometrics and vivo detection technologies to enhance the verification...
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 constantly updating its memory by processing real-time video (watching) and audio (listening) inputs, just like humans. This memory system doesn't just record what happened (situational memory), but can also be used from...
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 behavior and output of models more consistent with human expectations and values, such as ensuring that they are safe, truthful, unbiased, and harmless. With the ability of large models to ...
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 codebase 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 a variety of mainstream micro ...
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 that large-scale language models (LLMs) currently face in real-world applications: unpredictability and lack of controllability. When building AI intelligentsia, developers often encounter problems such as models ignoring system cues, producing hallucinatory answers, or failing to handle boundary cases. Parlan...
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 provides more accurate and contextually relevant information for Large Language Models (LLMs) by combining knowledge graphs with traditional vector retrieval techniques to improve...
Top
