Search AI Products and News

JD.com open-sources the multi-agent system JoyAgent-JDGenie, leading the industry with a 75.15% accuracy rate on the GAIA benchmark. The system features end-to-end multi-agent collaboration capabilities, supports multi-modal processing such as text and images, and uses a memory optimization mechanism to improve efficiency. The framework includes sub-agent modules for report generation, code, PPT, etc., allowing developers to expand and customize functions. It adopts the Apache 2.0 open-source license, provides complete code and documentation support, and is convenient for secondary development. Its modular design and multi-agent collaboration capabilities

Stanford University opensourced the AI tool OctoTools, integrating 11 professional tools to address complex reasoning tasks. The tool adopts a standardized tool card design, including functional modules such as image recognition and mathematical calculations. It follows a three-stage workflow: the planner analyzes the task, the executor operates the tool, and the validator ensures the results. Testing shows its outstanding performance in 16 benchmark tests, enabling efficient handling of cross-disciplinary issues such as mathematics and science, significantly improving the reliability and multi-step reasoning capabilities of AI systems. Open-source repository: github.com/oct

The open source AI framework CrewAI received 34,000 stars on GitHub and has become a popular choice among developers. This Python framework includes two core modules: Crews for multi-agent collaboration, simulating team division in enterprises; and Flows for event-driven task management, supporting workflow orchestration. The framework adopts a four-layer architecture (Crew, AI Agent, Process, Tasks), featuring role definition, tool customization, and intelligent collaboration. It has already been adopted by over 100,000 developers.

Open-source RL framework ART released, enhancing AI Agent training with GRPO tech. Features Python support, small model compatibility, and client-server architecture for multi-step tasks like email automation and game AI.....

OpenAI launches ChatGPT Agent, enabling AI to autonomously execute tasks like web browsing and form filling. Powered by GPT-4o, it achieves 71.3% accuracy in investment modeling. Currently available for Pro/Plus/Team users, with enterprise expansion planned.....

MiniMax launches a revolutionary AI development tool called MiniMax Agent, allowing users to automatically generate a complete e-commerce website with just natural language descriptions, including front-end, back-end, database, and payment interface functionalities. This technology significantly lowers the development barrier, supports international payments, real-time data updates, and automatic deployment, making it especially suitable for start-ups and individual entrepreneurs. This innovation will change traditional development models, making it possible to rapidly bring ideas to life and offering new opportunities in the e-commerce field.

OpenAI is about to launch a revolutionary Agent Mode, integrating Operator browser operations and Deep Research file analysis capabilities. This mode supports automated web operations (such as form filling and searching) and cloud file analysis (supporting platforms like Google Drive), and can generate professional reports. The core technology uses CUA and o3 models, featuring GUI interaction and data analysis capabilities, and is equipped with multiple security protections. It is suitable for scenarios such as personal travel planning and business market analysis, and will future expand to...

Jackywine's AI companion 'Bella' redefines human-machine interaction with emotional intelligence and personalized responses, evolving through three developmental stages.....

MiniMax Agent by Xiyu Tech offers a full-stack dev tool with Supabase backend, Stripe payments, and task scheduling, boosting efficiency for API-rich apps.....

Recently, Kunlun Tech Skywork and Nanyang Technological University jointly launched an innovative hierarchical multi-agent collaboration framework called AgentOrchestra, which is referred to as the 'AI Symphony Orchestra,' marking a significant step forward in agent collaboration within the field of general artificial intelligence. Faced with complex tasks in the real world that challenge single models or agents, AgentOrchestra enables intelligent agents with distinct expertise to collaborate and tackle challenges together, by mimicking the collaborative model of a symphony orchestra. Traditionally, general AI

Aliyun open-sources the network agent WebSailor. Its 32B and 72B versions performed well in the BrowseComp evaluation, surpassing multiple closed-source models, ranking just behind OpenAI DeepResearch. The project has been released on GitHub with construction plans and datasets, promoting open innovation in the AI field and providing developers with a smarter web interaction tool.

Apple released SceneScout AI agent, which provides environmental descriptions for visually impaired individuals by analyzing street scene images. The technology includes two modes: route preview and virtual exploration, with an accuracy rate of 72%-95%. User studies showed that it effectively improves environmental awareness, while suggesting the addition of personalized descriptions and real-time feedback features. Although still in the research phase, it demonstrates the potential of AI in assisting visually impaired individuals with navigation.

ByteDance open-sourced Trae-Agent, an LLM-based AI tool for software engineering tasks via natural language commands. Currently in alpha, it supports CLI and integrates multiple tools/LLM services. Aiming to foster an AI agent ecosystem, the GitHub project invites developer contributions.....

Since July, Xiaomi App Store will gradually open AI intelligent agent distribution services to users. After opening the Xiaomi App Store APP, users can click on the newly added 【Intelligent Agent】 entry at the bottom to directly access the special zone and browse and experience various practical and interesting AI intelligent agent products. At the same time, users can also quickly locate the desired service through the search function. The entire process does not require downloading or installing, truly achieving the convenient experience of "instant use." This innovative model not only lowers the threshold for users to access AI services, but also enhances the efficiency of service delivery through scenario-based recommendations. It is worth noting that

The TEN Agent team recently announced that its core models **TEN Voice Activity Detection (VAD)** and **TEN Turn Detection** are now open source, providing powerful technical support for building real-time, multimodal speech AI agents. This move marks a significant advancement in the TEN framework's efforts to promote the democratization and open-source collaboration of speech interaction technology. The following is the latest information compiled by AIbase, offering an in-depth analysis of these two core models.