AI 资讯
Google and Industry Partners Announce Agentic Resource Discovery Specification for AI Agents
Google and industry partners announced Agentic Resource Discovery (ARD) Specification, an open standard for publishing, discovering, and verifying AI tools, APIs, and agents. ARD introduces a discovery layer built on catalogs and registries, enabling dynamic capability discovery while leveraging existing protocols such as MCP and OpenAPI for execution and emphasizing trust and interoperability. By Leela Kumili
开发者
What's the difference between active noise canceling and passive?
The frustrating science of keeping your ears from doing their job.
科技前沿
Boomers, not Gen Z, are the generation cutting back most on alcohol
New research overturns assumption that abstinent younger drinkers are behind weak demand.
开源项目
🔥 python / cpython - The Python programming language
GitHub热门项目 | The Python programming language | Stars: 73,794 | 438 stars this week | 语言: Python
开源项目
🔥 jackwener / wx-cli - WeChat local data CLI with daemon architecture
GitHub热门项目 | WeChat local data CLI with daemon architecture | Stars: 4,006 | 85 stars today | 语言: Rust
开源项目
🔥 AIEraDev / Clypra - A modern video editor built with Tauri, React, and TypeScrip
GitHub热门项目 | A modern video editor built with Tauri, React, and TypeScript. Focus on building free capabilities of premium capcut functionalities | Stars: 2,462 | 66 stars today | 语言: TypeScript
开源项目
🔥 HenryNdubuaku / maths-cs-ai-compendium - Become a cracked AI/ML Research Engineer
GitHub热门项目 | Become a cracked AI/ML Research Engineer | Stars: 4,930 | 69 stars today | 语言: TypeScript
开源项目
🔥 rpamis / comet - Comet: agent skill harness for turning ideas into evaluated
GitHub热门项目 | Comet: agent skill harness for turning ideas into evaluated workflows | Stars: 2,264 | 26 stars today | 语言: JavaScript
开源项目
🔥 songquanpeng / one-api - LLM API 管理 & 分发系统,支持 OpenAI、Azure、Anthropic Claude、Google Ge
GitHub热门项目 | LLM API 管理 & 分发系统,支持 OpenAI、Azure、Anthropic Claude、Google Gemini、DeepSeek、字节豆包、ChatGLM、文心一言、讯飞星火、通义千问、360 智脑、腾讯混元等主流模型,统一 API 适配,可用于 key 管理与二次分发。单可执行文件,提供 Docker 镜像,一键部署,开箱即用。LLM API management & key redistribution system, unifying multiple providers under a single API. Single binary, Docker-ready, with an English UI. | Stars: 35,709 | 30 stars today | 语言: JavaScript
开源项目
🔥 cactus-compute / needle - 26m function call model that runs on incredibly small device
GitHub热门项目 | 26m function call model that runs on incredibly small devices | Stars: 3,071 | 113 stars today | 语言: Python
开源项目
🔥 PrimeIntellect-ai / verifiers - Our library for RL environments + evals
GitHub热门项目 | Our library for RL environments + evals | Stars: 4,344 | 15 stars today | 语言: Python
开源项目
🔥 Arindam200 / awesome-ai-apps - A collection of projects showcasing RAG, agents, workflows,
GitHub热门项目 | A collection of projects showcasing RAG, agents, workflows, and other AI use cases | Stars: 13,132 | 18 stars today | 语言: Python
开源项目
🔥 3b1b / manim - Animation engine for explanatory math videos
GitHub热门项目 | Animation engine for explanatory math videos | Stars: 88,514 | 133 stars today | 语言: Python
开源项目
🔥 Vexa-ai / vexa - Open-source meeting transcription API for Google Meet, Micro
GitHub热门项目 | Open-source meeting transcription API for Google Meet, Microsoft Teams & Zoom. Auto-join bots, real-time WebSocket transcripts, MCP server for AI agents. Self-host or use hosted SaaS. | Stars: 2,520 | 74 stars today | 语言: Python
开发者
EverQuest’s biggest fans are leading its revival
Live-service games and the companies that run them are in big trouble. Games and their developers are getting shut down and gutted, and publishers' huge promises are dubious. Meanwhile, EverQuest, one of the original live-service games, is thundering back more than 25 years later. EverQuest Legends is currently in preorder beta with an upcoming release […]
AI 资讯
Meta's Noninvasive Brain–Computer Interface Brain2Qwerty Achieves 61% Accuracy
Meta recently open-sourced Brain2Qwerty v2, a noninvasive Brain–Computer Interface (BCI) that can decode sentences from thoughts using electroencephalography (EEG) or magnetoencephalography (MEG) signals from the brain. In evaluations, the system achieved a word accuracy rate 61% on average, compared to 8% for other non-invasive methods. By Anthony Alford
开发者
An Update on Igalia's Layer Based SVG Engine in WebKit (Reducing Layer Overhead)
AI 资讯
U of Chicago law school bans laptops from classes amid AI backlash
AI 资讯
Proof of care in the age of AI
开发者
Tensor Is the Might