Daily AI brief
Daily AI brief: November 17, 2026
The AI brief for November 17, 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 10:58 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 10, tagged llm or ai-agents on GitHub, ranked by stars.
- hitkeeen/blender-ai-mcp-addon · 2,333 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...
- berkantay/gpucanvas · 508 stars · TypeScript. Put thousands of live DOM nodes on an infinite canvas: the GPU draws them, an editor selects, moves and resizes them, shaders and transitions run on them, and...
- YellowLaborerMarket/Gemini-Config-Checker- · 474 stars · Makefile. Chain region scanner: find proxy configs that get you into Google AI Studio and Gemini (signed-in browser check, anti-DPI, Windows/macOS/Linux/Android)
- VortexHostFeel/Gemini-Config-Checker- · 473 stars · Makefile. Chain region scanner: find proxy configs that get you into Google AI Studio and Gemini (signed-in browser check, anti-DPI, Windows/macOS/Linux/Android)
- Visionbeyondtrack/Gemini-Config-Checker- · 473 stars · Makefile. Chain region scanner: find proxy configs that get you into Google AI Studio and Gemini (signed-in browser check, anti-DPI, Windows/macOS/Linux/Android)
- TurtleReside/Gemini-Config-Checker- · 473 stars · Go. Chain region scanner: find proxy configs that get you into Google AI Studio and Gemini (signed-in browser check, anti-DPI, Windows/macOS/Linux/Android)
- WinnerSpecialist/Gemini-Config-Checker- · 473 stars · Makefile. Chain region scanner: find proxy configs that get you into Google AI Studio and Gemini (signed-in browser check, anti-DPI, Windows/macOS/Linux/Android)
- weightcashiercupola/Gemini-Config-Checker- · 473 stars · Makefile. Chain region scanner: find proxy configs that get you into Google AI Studio and Gemini (signed-in browser check, anti-DPI, Windows/macOS/Linux/Android)
- WharfBoulderColander/Gemini-Config-Checker- · 473 stars · Makefile. Chain region scanner: find proxy configs that get you into Google AI Studio and Gemini (signed-in browser check, anti-DPI, Windows/macOS/Linux/Android)
- WyrmClimberManacle/Gemini-Config-Checker- · 473 stars · Makefile. Chain region scanner: find proxy configs that get you into Google AI Studio and Gemini (signed-in browser check, anti-DPI, Windows/macOS/Linux/Android)
What people are talking about
The most upvoted AI stories on Hacker News in the past 24 hours.
- Ask HN: If AI tools are so good, why isn't your bug backlog empty? (news.ycombinator.com) · 52 points · 75 comments
- Show HN: Coral, Open-source gateway where agents write their own tools (github.com) · 52 points · 24 comments
- Caltech professor no longer grades homework's because everyone uses AI (businessinsider.com) · 47 points · 59 comments
- FBI says Artex AI open-source hacking tool used to breach networks (techcrunch.com) · 45 points · 9 comments
- Generative AI Usage in the Games Industry (gameworkers.co.uk) · 42 points · 93 comments
- U.S. tightens controls on remote access to AI technology amid Nvidia fallout (npr.org) · 30 points · 3 comments
- The Fed Is Worried AI Agents Could Trigger a Bank Run (gizmodo.com) · 26 points · 11 comments
- Kubernetes Is Strengthening Its Position as the AI Platform of Choice (cloudnativenow.com) · 22 points · 8 comments
New research
The latest papers submitted to arXiv's artificial intelligence category. Preprints are not peer reviewed.
- Latent Lattice Language Models · Shivam Duggal, Zongze Wu, William T. Freeman and others. From the abstract: "Language models typically increase per-token computation through deeper or looped layers and latent reasoning..."
- ViRA: Toward Ultra-High-Resolution Visual Agents via Cross-Input Relative Policy Optimization · Huawei Lin, Jinting Liu, Tongyan Wang and others
- Mitigating Catastrophic Forgetting with Physics-Indexed Specialist Memory: the Evolutionary Neuroplastic Agent · Blas Eugenio Vicco Zarate, Miguel Hernán Vicco
- ScenarioForge: Resource-Grounded Generation and Execution Validation of Cyber Exercises · Jaime C. Acosta, Anantaa Kotal, Aritran Piplai
- When Tool Names Are Not Identities: Measuring Provider Misbinding in MCP-Based AI Agents · Zeynab Anbiaee, Sajjad Dadkhah, Ali A. Ghorbani
- Severe but Harmless: Stress-Testing Shift Severity for Frozen Time-Series Forecasters · Korede R. Bishi, Dominic Okonkwo, Adetayo Okunoye
- TRACE: Topological Representations for Anomaly detection through Contrastive Embeddings · Sydney Johns
- Right Reason, Wrong Advice: Evaluating Recourse in LLM Explanations of Denied Requests · Arunkumar V
