Source-backed discovery

New Term Radar

Discover names and concepts appearing in public sources, with dated evidence, source coverage and comparable growth.

Saved terms stay in this browser and do not sync to your account. Source collection continues on the server without this page being open.

Collection coverage · Limited historyCurrent / previous observed days 7 / 4

Counts use complete UTC days. First observed means first seen by this collection, not when a term was coined.

Current window：2026-10-30 → 2026-11-06 (end excluded) · History 12 days

Observed source coverage by seven-day window
Source	Current days	Previous days	Last success
arXiv	6	4	Nov 6, 2026, 12:30 AM UTC
arXiv	7	3	Nov 5, 2026, 10:01 AM UTC
Ask HN	7	4	Nov 6, 2026, 3:30 AM UTC
Ask HN	7	4	Nov 6, 2026, 2:45 AM UTC
Ask HN	7	4	Nov 6, 2026, 3:30 AM UTC
Ask HN	7	4	Nov 6, 2026, 3:30 AM UTC
GitHub	7	4	Nov 6, 2026, 12:30 AM UTC
GitHub Issues	7	4	Nov 6, 2026, 4:00 AM UTC
GitHub Releases	7	2	Nov 6, 2026, 12:15 AM UTC
GitHub	7	4	Nov 6, 2026, 2:30 AM UTC
GitHub Issues	7	4	Nov 5, 2026, 4:15 PM UTC
GitHub Releases	7	4	Nov 5, 2026, 4:15 PM UTC
GitHub	7	4	Nov 6, 2026, 2:30 AM UTC
GitHub Issues	7	4	Nov 5, 2026, 4:45 PM UTC
GitHub Releases	7	4	Nov 5, 2026, 4:15 PM UTC
GitHub Discovery	1	0	Nov 6, 2026, 3:30 AM UTC
GitHub Trending	7	4	Nov 6, 2026, 1:00 AM UTC
Google	7	3	Nov 5, 2026, 10:00 AM UTC
Hugging Face	7	3	Nov 5, 2026, 8:15 AM UTC
Hugging Face Spaces	1	0	Nov 6, 2026, 3:30 AM UTC
Hacker News	7	4	Nov 6, 2026, 1:00 AM UTC
Hacker News	7	4	Nov 6, 2026, 3:45 AM UTC
Hacker News	7	4	Nov 6, 2026, 3:45 AM UTC
Hacker News	1	0	Nov 6, 2026, 3:30 AM UTC
Show HN	1	0	Nov 6, 2026, 3:30 AM UTC
MIT News	7	3	Nov 5, 2026, 4:15 PM UTC
OpenAI	7	4	Nov 5, 2026, 11:30 AM UTC
Product Hunt	7	4	Nov 6, 2026, 1:00 AM UTC
量子位	6	4	Nov 4, 2026, 10:15 AM UTC
OpenRouter	1	0	Nov 6, 2026, 4:07 AM UTC
Hugging Face Models	1	0	Nov 6, 2026, 4:07 AM UTC
HF Daily Papers	1	0	Nov 6, 2026, 4:07 AM UTC
OpenRouter	1	0	Nov 6, 2026, 4:07 AM UTC
SEC EDGAR	7	4	Nov 5, 2026, 10:30 PM UTC
Sequoia Capital	7	3	Nov 5, 2026, 10:00 AM UTC
Simon Willison	1	0	Nov 5, 2026, 3:13 PM UTC
TechCrunch	7	4	Nov 6, 2026, 2:45 AM UTC
Contracts Finder	7	4	Nov 5, 2026, 7:45 PM UTC
V2EX	7	4	Nov 6, 2026, 2:45 AM UTC

Counts describe monitored public sources, not the whole web or search demand.
Both weeks need adequate, comparable collection coverage.

Seven-day figures use the complete UTC window above. Priority is a research triage score, not search volume, market size or a probability of success.

Named entityNewly observed
家庭试卷工作台
初衷很简单：要在网上搜试卷，打印给妹妹做（成绩实在惨不忍睹了）。偶然发现小红书上资源挺不错，一开始就是个简单网页，后来嫌操作繁琐——先用浏览器脚本下载图片，再本地合成 PDF 打印，有时候还得调整图片。趁着 ZCode 还在送 token ，干脆让它直接做成了程序。中间经历了几次迭代，有些功能边界我自己可能都没用到，目前基本功能差不多了，感兴趣的可以试试。它能做什么采集浏览：在小红书笔记页手动采集试卷图片（单篇手动、有节流，仅限个人学习用途）试卷库 + 整理打印：页序调整、补页，直接打印或导出 A4 PDF （纵/横混排）试卷批阅：本地导入或手机扫码上传作答照片（局域网直传，先进暂存区核对才入库），支持人工批阅和 AI 批阅双路径 AI 批阅：推荐走外部批阅——生成 PDF + 配套提示词，丢给
First observed Oct 30, 2026 · V2EX

7d mentions
1 previous 0
7d sources
1
7d growth
Not comparable
Priority
32 / 100
Named entityNewly observed
之前看到
之前看到一个 AI 服装图集的点子，就自己做了个在线版本。最开始只是想方便找衣服、看搭配，后来干脆加上了 AI 换装，前后端也一起开源了。先看效果：服装参考图 + 人物原图 → AI 换装结果。 ① 服装参考图 ② 人物原图 ③ AI 换装效果目前做了什么 1407 张服装参考图：支持中英文搜索、分类筛选、放大查看。 AI 一键换装：上传人物照，选一套服装作为参考，生成试穿效果。多模型可选：GPT Image 、Gemini 、豆包等，API Key 、Base URL 和模型名可以自己配置。本地模型：加入了 ComfyUI 工作流，可以用自己的显卡跑，不一定要调用付费云端 API 。部署和二开：前端是静态页面，后端用 GoFrame v2 ，提供 Docker Compose 部署方式
First observed Oct 30, 2026 · V2EX

7d mentions
1 previous 0
7d sources
1
7d growth
Not comparable
Priority
32 / 100
Named entityNewly observed
代码并形成总结
昨天在小红书看到的开发者锤闭源软件，今天看到抄袭方的回应感到有点好奇。传统的净室开发一般应该是类似通过公开文档来自行实现对其接口的兼容吧？ AI 在这方面的总结再开发，是否可以认定净室开发的“未接触源代码”的要求不复存在？因为 AI 的总结已经把源代码的实质性内容描述出来了小红书双方原帖： [1] SpektraLab 抄袭开源项目，不遵守开源协议？昨晚，我... https://xhslink.cn/o/9OusrrM9znh [2] 关于 SpektraLab iOS 版本的正式说明 https://xhslink.cn/o/4dTlS78YVn1 [3] SpektraLab 利用开源项目，并谎称净室重写 1 ｜为何违反... https://xhslink.cn/o/6TI5o2hfiob
First observed Oct 30, 2026 · V2EX

7d mentions
1 previous 0
7d sources
1
7d growth
Not comparable
Priority
32 / 100
Named entityNewly observed
具身智能规模化落地新路径
让机器人成为彼此的“老师”
First observed Oct 30, 2026 · 量子位

7d mentions
1 previous 0
7d sources
1
7d growth
Not comparable
Priority
32 / 100
Named entityNewly observed
后第一周
说明：我是作者本人，此帖为自荐/广告性质，商品在 Gumroad 售卖。事实部分：这是一个部署工具包，内容是把一个最小可用的 Cloudflare Worker 订阅聚合面板从零部署到上线的模板、脚本与文档。缘起是自己部署同类面板时反复遇到三个问题：重部署后无法确认新代码是否生效、KV 绑定丢失、接口 503 时无法判断故障层级。包的核心是把「部署后验证」做成脚本化的硬判据，而不是靠刷新页面确认。包含内容： Worker 模板（单文件）：/health、/sub（Base64 订阅输出）、/sub/plain、/api/status；token 未配置时接口按设计拒绝服务 deploy-check.sh ：部署后验证脚本，检查线上版本号与本次部署版本是否一致、KV 绑定是否存在、订阅可否拉取解码、错误 t
First observed Oct 30, 2026 · V2EX

7d mentions
1 previous 0
7d sources
1
7d growth
Not comparable
Priority
32 / 100
Named entityNewly observed
两周后即迎来
阶跃终端旗下大模型原生智能体手机 STEPX Neo 在发布两周后即迎来首次升级
First observed Oct 30, 2026 · 量子位

7d mentions
0 previous 1
7d sources
0
7d growth
Not comparable
Priority
32 / 100
Named entityNewly observed
NextGen WAF
First observed Nov 6, 2026 · Show HN

7d mentions
0 previous 0
7d sources
0
7d growth
Not comparable
Priority
32 / 100
Named entityNewly observed
Announcing Project ProtoStar
First observed Oct 30, 2026 · Hugging Face

7d mentions
0 previous 1
7d sources
0
7d growth
Not comparable
Priority
32 / 100
Named entityNewly observed
Send21
First observed Oct 30, 2026 · Hacker News

7d mentions
1 previous 0
7d sources
1
7d growth
Not comparable
Priority
32 / 100
Named entityNewly observed
两周即迎
阶跃终端旗下大模型原生智能体手机 STEPX Neo 在发布两周后即迎来首次升级
First observed Oct 30, 2026 · 量子位

7d mentions
0 previous 1
7d sources
0
7d growth
Not comparable
Priority
32 / 100
Named entityNewly observed
Taskivities
First observed Nov 6, 2026 · Show HN

7d mentions
0 previous 0
7d sources
0
7d growth
Not comparable
Priority
32 / 100
Named entityNewly observed
登顶全球第一
解析一切
First observed Oct 30, 2026 · 量子位

7d mentions
1 previous 0
7d sources
1
7d growth
Not comparable
Priority
32 / 100
ConceptNewly observed
协议
昨天在小红书看到的开发者锤闭源软件，今天看到抄袭方的回应感到有点好奇。传统的净室开发一般应该是类似通过公开文档来自行实现对其接口的兼容吧？ AI 在这方面的总结再开发，是否可以认定净室开发的“未接触源代码”的要求不复存在？因为 AI 的总结已经把源代码的实质性内容描述出来了小红书双方原帖： [1] SpektraLab 抄袭开源项目，不遵守开源协议？昨晚，我... https://xhslink.cn/o/9OusrrM9znh [2] 关于 SpektraLab iOS 版本的正式说明 https://xhslink.cn/o/4dTlS78YVn1 [3] SpektraLab 利用开源项目，并谎称净室重写 1 ｜为何违反... https://xhslink.cn/o/6TI5o2hfiob
First observed Oct 30, 2026 · V2EX

7d mentions
1 previous 0
7d sources
1
7d growth
Not comparable
Priority
32 / 100
Named entityNewly observed
Paper
First observed Nov 6, 2026 · Hacker News

7d mentions
0 previous 0
7d sources
0
7d growth
Not comparable
Priority
31 / 100
Named entityNewly observed
用热榜聚合站
用热榜聚合站的朋友大概都有同感：平台越接越多，界面越来越满，个性化推荐、历史快照、关键词订阅一层层叠上去之后，打开它本身变成了一件需要“做决定”的事。所以做了 REBANG （ https://top.open2hub.com ）。做了简单的订阅功能了一片红，不多说了，难受。。。
First observed Nov 6, 2026 · V2EX

7d mentions
0 previous 0
7d sources
0
7d growth
Not comparable
Priority
31 / 100
Named entityNewly observed
面向海外市场
大家好，最近刚上线了一个面向海外市场的 AI 图像二次创作与美化工具： Repixly ，发出来请大家体验拍砖。为什么做这个工具？平时自己在做海外项目配图、社媒素材或者处理人像/商品图时，经常遇到两个痛点：直接用文生图（Text-to-Image）很难控制原有的构图、姿态和人物面部特征，抽卡成本太高，而且很容易出现一眼假的“塑料 AI 感”。如果为了保结构去本地搭 ComfyUI 或 WebUI 跑 ControlNet，调节点、配权重和去噪参数又太重了，有时候只是想快速改个光影或转个风格，操作成本完全不划算。所以就做了 Repixly ，核心思路就是把底层复杂的模型管线封装成一个打开即用的轻量工作台。主要做了哪些东西？保留原图结构与真实质感：底层基于 Flux 和 SDXL，配合 Contro
First observed Nov 6, 2026 · V2EX

7d mentions
0 previous 0
7d sources
0
7d growth
Not comparable
Priority
31 / 100
Named entityInsufficient data
sakurartro/luma
First observed Oct 29, 2026 · Hacker News

7d mentions
0 previous 1
7d sources
0
7d growth
Not comparable
Priority
17 / 100
Named entityInsufficient data
CopilotKit/OpenBot
Open-source AI coworkers that each get a computer of their own: a browser, files and tools, with every action decided before it happens and recorded after. Bring any AG-UI agent.
First observed Oct 29, 2026 · GitHub Trending

7d mentions
0 previous 0
7d sources
0
7d growth
Not comparable
Priority
17 / 100
Named entityInsufficient data
kaplanelad/shellfirm
First observed Oct 29, 2026 · Hacker News

7d mentions
0 previous 1
7d sources
0
7d growth
Not comparable
Priority
17 / 100
Named entityInsufficient data
ahmadrosid/nakama
First observed Oct 29, 2026 · Hacker News

7d mentions
0 previous 1
7d sources
0
7d growth
Not comparable
Priority
17 / 100
Named entityInsufficient data
asharma327/sheetgraph
Hi guys, I built a tool www.lovespreadsheets.com earlier this year and a huge problem we kept running into is processing messy, real-world, complex spreadsheets for AI agents. Even a "medium" sized spreadsheet converts to about 1m+ tokens if read fully, which immediately blows up the current context windows of most models. So I noticed most agents
First observed Oct 29, 2026 · Hacker News

7d mentions
0 previous 1
7d sources
0
7d growth
Not comparable
Priority
17 / 100
Named entityInsufficient data
phpclaw-php/phpclaw-monorepo
First observed Oct 29, 2026 · Hacker News

7d mentions
0 previous 1
7d sources
0
7d growth
Not comparable
Priority
17 / 100
Named entityInsufficient data
milind-soni/OpenMausBot
Open-source Grok Bot alternative with a virtual machine that bots can use
First observed Oct 29, 2026 · GitHub Trending

7d mentions
0 previous 0
7d sources
0
7d growth
Not comparable
Priority
17 / 100
Named entityInsufficient data
Donchitos/Claude-Code-Game-Studios
Turn Claude Code into a full game dev studio — 49 AI agents, 72 workflow skills, and a complete coordination system mirroring real studio hierarchy.
First observed Oct 29, 2026 · GitHub Trending

7d mentions
0 previous 0
7d sources
0
7d growth
Not comparable
Priority
17 / 100
Named entityInsufficient data
Canva Brush
A vision-language model that edits your designs
First observed Oct 24, 2026 · Product Hunt

7d mentions
0 previous 1
7d sources
0
7d growth
Not comparable
Priority
17 / 100
Named entityInsufficient data
TopAgent
Drive B2B event attendance with an AI agent
First observed Oct 29, 2026 · Product Hunt

7d mentions
0 previous 0
7d sources
0
7d growth
Not comparable
Priority
17 / 100
Named entityInsufficient data
oimo-ai/apgar
Hey HN, We build financial AI agents, and Apgar is the tool we wrote to see whether a harness change made an agent better or worse in production. Our offline evals can't cover every kind of question or session real users bring, and the LLM judge we run in Langfuse is too expensive to use on more than a small slice of traffic, so some failures get through. Ap
First observed Oct 29, 2026 · Hacker News

7d mentions
0 previous 1
7d sources
0
7d growth
Not comparable
Priority
17 / 100
Named entityInsufficient data
thedotmack/claude-mem
Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes
First observed Oct 29, 2026 · GitHub Trending

7d mentions
0 previous 0
7d sources
0
7d growth
Not comparable
Priority
17 / 100
Named entityInsufficient data
agens-field/nuvrail
First observed Oct 28, 2026 · Hacker News

7d mentions
0 previous 1
7d sources
0
7d growth
Not comparable
Priority
16 / 100
Named entityInsufficient data
Scape
An intelligent email inbox that works for you
First observed Oct 29, 2026 · Product Hunt

7d mentions
0 previous 0
7d sources
0
7d growth
Not comparable
Priority
16 / 100