GitHub今日趋势
· 去GitHub看原榜 → · 中文标题为机器翻译
- 1用 Univer Office SDK 搭建你自己的 AI 办公室。将编辑、计算、协作和文件处理能力接入你的产品，同时服务于人和 AI 智能体。基于可扩展的开源内核构建。Build your own AI office with Univer Office SDK. Bring editing, calculation, collaboration, and file processing into your product for people and AI agents. Built on an extensible open-source core.dream-num/univer今日 +1,041
- 2AG-UI：智能体与用户交互协议，将智能体引入前端应用。AG-UI: the Agent-User Interaction Protocol. Bring Agents into Frontend Applications.ag-ui-protocol/ag-ui今日 +393
- 3一套为 Stitch MCP 服务器设计的智能体技能库。每项技能都遵循 Agent Skills 开放标准，可兼容 Antigravity、Gemini CLI、Claude Code、Cursor 等编程智能体。A library of Agent Skills designed to work with the Stitch MCP server. Each skill follows the Agent Skills open standard, for compatibility with coding agents such as Antigravity, Gemini CLI, Claude Code, Cursor.google-labs-code/stitch-skills今日 +248
- 4一个让你随时掌握并统领智能体工作的工作空间：塑造方向、做出决策、制定计划、添加批注、审查代码、与团队共享，并可一键将所有反馈发送给智能体。The workspace to stay in the loop and on top of agents - shape, decide, plan, annotate, review code, share with team, and send all feedback to agents with one click.backnotprop/plannotator今日 +860
- 5面向编程智能体的 Chrome DevToolsChrome DevTools for coding agentsChromeDevTools/chrome-devtools-mcp今日 +718
- 6安全、高效、经过阿里巴巴超大规模实战检验。混合架构代码审查工具：确定性流水线加 LLM 智能体，可精确到行级的评论，内置多语言规则集（空指针、线程安全、XSS、SQL 注入），兼容 OpenAI 与 Anthropic 接口。Secure, fast, efficient, battle-tested at Alibaba's scale. Hybrid architecture code review tool: deterministic pipelines + LLM Agent, precise line-level comments, built-in multi-language ruleset (NPE, thread-safety, XSS, SQL injection), OpenAI & Anthropic compatible.alibaba/open-code-review今日 +688
- 7面向编程智能体交付的自托管工作流。通过脚本和人工审批关卡编排 CodeBuddy、Codex 和 Claude Code，包含面向编程助手的本地工作流。Self-hosted workflows for coding-agent delivery. Orchestrate CodeBuddy, Codex and Claude Code with scripts and human approval gates. Includes Local workflows for coding assistants.Tencent/LoopForge今日 +484
- 8机器学习张量计算库Tensor library for machine learningggml-org/ggml今日 +154
- 9一套用于漏洞挖掘和外部红队工作的 Claude Code 技能包，包含 82 项技能、15 个斜杠命令，以及从 24 类核心漏洞中整理出的 681 种已披露报告模式，另含企业身份与基础设施攻击矩阵。A Claude Code skill bundle for bug hunting and external red-team work - 82 skills, 15 slash commands, 681 disclosed-report patterns curated across 24 core vulnerability classes, plus enterprise identity + infrastructure attack matrices.elementalsouls/Claude-BugHunter今日 +124
- 10让你的编程智能体及时掌握最新的 Web 最佳实践。Keep your coding agent up to date with the latest web best practicesGoogleChrome/modern-web-guidance-src今日 +1,220
- 11面向股票投资者与交易者的 Claude Code 技能包，涵盖市场分析、技术图表、经济日历、选股筛选器和交易策略开发。Claude Code skills for equity investors and traders — market analysis, technical charting, economic calendars, screeners, and trading strategy development.tradermonty/claude-trading-skills今日 +707
- 12一个多层级的 AI 智能体技能评估框架，具备质量关卡、语义重叠检测、合成评估数据集生成，以及衡量技能如何影响智能体行为的实时智能体评估。Multi-tier framework for evaluating AI agent skills with quality gates, semantic overlap detection, synthetic evaluation dataset generation, and live agent evaluation that measures how skills affect agent behavior.NVIDIA/SkillEvaluator今日 +133