GitHub Trending 技术趋势 (2026-11-16)
Executive Summary
结论先行
2026-11-16,AI/ML 方向以 83% 的占比主导今日 GitHub Trending,GoogleChrome/modern-web-guidance-src 以 1,219 stars today 领跑热度榜。
支撑论点
- AI/ML 共收录 10 个项目,占全部 12 个趋势项目的 83%,AI 技术持续引领开源创新。
- 编程语言 Top 3 为 TypeScript(6)、Python(3)、Go(2),反映出当前主流技术栈偏好。
- 今日共计 6,475 新增 Stars,总 Stars 累计 213,434,开源社区活跃度强劲。
数据概览
技术方向分布
热度排行 Top 5
昨日对比
新上榜项目
退出趋势项目
连续上榜项目
热度变化 Top 5
增长明细
点击展开增长明细表
| 项目 | 排名 | Star 变化 | Fork 变化 | 热度变化 | 连续天数 |
|---|---|---|---|---|---|
| modern-web-guidance- | #1 → | +1,151 | +196 | -12 | Day 5 |
| univer | #2 ▲4 | +1,699 | +137 | +493 | Day 2 |
| plannotator | #3 ▲6 | +729 | +158 | +458 | Day 3 |
| chrome-devtools-mcp | #4 ▼1 | +694 | +53 | +53 | Day 3 |
| claude-trading-skill | #5 → | +762 | +183 | +153 | Day 3 |
| open-code-review | #6 ▼4 | +717 | +210 | -202 | Day 3 |
| LoopForge | #7 ▲7 | +678 | +66 | +390 | Day 2 |
| ag-ui | #8 ▲7 | +574 | +156 | +346 | Day 2 |
AI 发展趋势洞察
主导方向与驱动力: 今日 Trending 以 AI/ML 方向最为突出,共 10 个项目上榜。其中 GoogleChrome/modern-web-guidance-src 热度最高(1,219 stars today),体现出社区对该领域的持续关注。
编程语言偏好: 今日热门项目中,TypeScript(6 项目)、Python(3 项目)、Go(2 项目) 位列前三。
值得关注的项目: modern-web-guidance-src、univer、plannotator 等项目今日增长迅猛,建议开发者持续跟踪其发展动态。
跨领域融合: 当前 Trending 涵盖 AI/ML、Web开发、编程语言/工具 等方向,反映出技术生态日益交叉融合的趋势。AI 能力正加速渗透到 DevOps、安全、数据库等各基础设施层面。
AI/ML
dream-num/univer
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.
ag-ui-protocol/ag-ui
AG-UI: the Agent-User Interaction Protocol. Bring Agents into Frontend Applications.
google-labs-code/stitch-skills
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.
backnotprop/plannotator
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.
ChromeDevTools/chrome-devtools-mcp
Chrome DevTools for coding agents
alibaba/open-code-review
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.
Tencent/LoopForge
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.
GoogleChrome/modern-web-guidance-src
Keep your coding agent up to date with the latest web best practices
NVIDIA/SkillEvaluator
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.
Web开发
dream-num/univer
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.
ag-ui-protocol/ag-ui
AG-UI: the Agent-User Interaction Protocol. Bring Agents into Frontend Applications.
google-labs-code/stitch-skills
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.
backnotprop/plannotator
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.
ChromeDevTools/chrome-devtools-mcp
Chrome DevTools for coding agents
alibaba/open-code-review
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.
elementalsouls/Claude-BugHunter
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.
GoogleChrome/modern-web-guidance-src
Keep your coding agent up to date with the latest web best practices
tradermonty/claude-trading-skills
Claude Code skills for equity investors and traders — market analysis, technical charting, economic calendars, screeners, and trading strategy development.
编程语言/工具
dream-num/univer
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.
google-labs-code/stitch-skills
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.
backnotprop/plannotator
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.
ChromeDevTools/chrome-devtools-mcp
Chrome DevTools for coding agents
alibaba/open-code-review
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.
elementalsouls/Claude-BugHunter
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.
DevOps/云原生
backnotprop/plannotator
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.
alibaba/open-code-review
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.
elementalsouls/Claude-BugHunter
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.
移动开发
ag-ui-protocol/ag-ui
AG-UI: the Agent-User Interaction Protocol. Bring Agents into Frontend Applications.
Tencent/LoopForge
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.