Daily AI brief
Daily AI brief: November 12, 2026
The AI brief for November 12, 2026: 10 new repos, 8 stories people are discussing, 8 new papers. Each item links to its source.
What moved in AI over the last day, pulled from GitHub, Hacker News and arXiv at 10:02 AM GMT+2. Every item links to its source. Repo descriptions are the projects' own words; star and point counts are as of that time.
Repos to watch
New open-source projects created since November 5, tagged llm or ai-agents on GitHub, ranked by stars.
- dabingfy-dot/solo-to-team-skills · 713 stars. Skills for human-led AI teams: delegate tasks, verify evidence, explain steps clearly, and learn from real cases. 一个人统筹 AI 团队:派活、核证、清楚说明、经验复用。
- dhruvthakur11/youtube-ai-video-editing-system · 483 stars · HTML. Eyeline teleprompter meets editing agents: JSON-driven animation and motion graphics workflow
- alexeyw/lot-map · 462 stars · TypeScript. A live map beside the chat that shows what Claude Code is doing: tool calls, model steps, hooks, skills and subagents light up as they happen. Local only, in...
- Dodaios/ste80-humanizer · 420 stars · Python. STE80 Humanizer: agent skill that removes AI tells and rewrites text 80% of the way to ASD-STE100 (Simplified Technical English), the method Andrej Karpathy...
- shanselman/sandbox-mcp · 414 stars · JavaScript. Fresh, throwaway Windows machines for testing your apps: an MCP server and CLI that automate Windows Sandbox
- nishant-Tiwari24/cracked · 257 stars · TypeScript. Skills for getting hired. Company-wise mock interviews, OAs with hidden tests and brutal resume roasts for 470+ companies, straight from your terminal.
- SsKanDon/blender-ai-mcp-addon · 207 stars. AI assistant and MCP server for Blender: visual chat, scene tools, multi-agent workflows. Works with ChatGPT/GPT, Claude, Gemini, Ollama, OpenCode. Blender AI...
- bookleme/bookleme · 143 stars · Python. 读了么(BookLeme)· 把一本书编译成 Agent Skill, , 双引擎 + 可插拔体裁插件 + 逐字忠实度回验
- huawei-csl/MACaQ · 140 stars · C++. SOTA model-agnostic quantization for GGUF, local inference and beyond. Quantize and run text, image, video and audio models with llama.cpp, vLLM, Diffusers...
- DevCrabs-Inc/yandex-metrika-mcp · 130 stars · TypeScript. Read-only MCP server for Yandex Metrika (Яндекс Метрика): verifiable reports, period comparisons, time series and exports for Claude, Cursor, VS Code and Codex.
What people are talking about
The most upvoted AI stories on Hacker News in the past 24 hours.
- My AI agents found an unmapped Maya site? (pietromiotti.com) · 976 points · 355 comments
- United Airlines bans AI agents from booking flights on behalf of travelers (cbsnews.com) · 525 points · 515 comments
- Retirement Savings Are Fueling the AI Bubble (lpeproject.org) · 154 points · 162 comments
- AI, activity, and outcomes in software engineering (cabird.com) · 116 points · 103 comments
- OSS projects banning AI-generated contributions (osssaysno.com) · 63 points · 107 comments
- Launch HN: Pomerado (YC F26), Turn any website into an MCP for agents (news.ycombinator.com) · 54 points · 43 comments
- Laser-armed AI submarine robots patrol Norwegian salmon farms, killing sea lice (tomshardware.com) · 30 points · 9 comments
- Tech Allies Rally Behind Jensen Huang, Calling Him Vital in AI Race (Gift Link) (nytimes.com) · 17 points · 17 comments
New research
The latest papers submitted to arXiv's artificial intelligence category. Preprints are not peer reviewed.
- Medical Image Segmentation: Foundation Model Adaptation versus Task-Specific Training · Emre Kutlusan, Yongmin Li. From the abstract: "Foundation models pretrained on large natural-image collections are increasingly adapted for medical image segmentation..."
- Toward Foundation Detection Models via Example-Based Grounding in EM-DETR · Sheethal Bhat, Bogdan Georgescu, Awais Mansoor and others
- Contrastive Discovery: Open-Ended Scientific Discovery over Competing Explanations · Ziang Liu, James J. Kim, Yijia Dai and others
- Comparative Analysis of Agent Evaluation Frameworks: Stability, Detection, and Discovery in Enterprise Analytics Agents · Howard Zhang, Chuck Arvin, Logan Brown and others
- ReTrace: Distilling Tool-Using Agents into Planner-Free Workflows · Kaiyuan Hou, Yang Ping Kuo, Indranil Bhattacharya and others
- Re-Search: Dissecting LLM Ideation Through a Two-Player Questioning Game · Muhan Gao, Hangxiao Zhu, Xinqi Su and others
- One Policy for 100 Household Tasks: Our Solution for the 2026 BEHAVIOR Challenge · Ilia Larchenko, Gleb Zarin, Atindra Nair and others
- Two Communities, One Problem: Branch-and-Bound vs. A for Resource-Constrained Project Scheduling · Izack Cohen, Dominik Kress, Lara Nehrke and others
