Trending AI on October 29, 2026

1. 1
   Hacker News Leak Exposes 41,000 Homeland Security Workers–Including Undercover ICE Agents

   Hacker News story from wired.com, 168 comments

   Peak score 99 · best #1 · 4 of 20 hourly runs in top 10 · +112 points in 24h

2. 2
   GitHub patch-gg/anymove

   Motion capture for any creature from one AI video: two cameras in one frame, a DINOv2 joint reader, the rig fitted in both views, a GLB out.

   Peak score 99 · best #1 · 11 of 20 hourly runs in top 10 · +23 stars in 24h

3. 3
   Hacker News Claude Code burns ~15–20% of your tokens on a 3-word status line

   Hacker News story from gist.github.com, 30 comments

   Peak score 99 · best #1 · 1 of 20 hourly runs in top 10 · +46 points in 23h

4. 4
   Hacker News Claude Code regularly sends each background agent’s transcript to its model

   Hacker News story from gist.github.com, 208 comments

   Peak score 99 · best #1 · 8 of 20 hourly runs in top 10 · +46 points in 23h

5. 5
   Hacker News Gemini 4 Carbon is the new #1 on the Artificial Analysis Intelligence Index v5

   Hacker News story from artificialanalysis.ai, 210 comments

   Peak score 99 · best #1 · 3 of 20 hourly runs in top 10 · +8 points in 23h

6. 6
   Hacker News Mistral Large 4 (Le Chonk) is now Open Weight

   Hacker News story from mistral.ai, 65 comments

   Peak score 99 · best #1 · 1 of 20 hourly runs in top 10 · +466 points in 23h

7. 7
   Hacker News Zombie stats: Where the numbers AI quotes come from

   Hacker News story from trakkr.ai, 54 comments

   Peak score 99 · best #1 · 3 of 20 hourly runs in top 10 · +27 points in 23h

8. 8
   Hacker News LLM Voice

   Hacker News story from martinfowler.com, 155 comments

   Peak score 99 · best #1 · 5 of 20 hourly runs in top 10 · +220 points in 23h

9. 9
   GitHub ChannelCooperStart/capri-ai

   Capri — Edgerunners-inspired AI agent for your desktop. Works with Claude Code, Codex, Antigravity & more.

   Peak score 99 · best #1 · 1 of 20 hourly runs in top 10 · +46 stars in 23h

10. 10
    Hacker News Claude Duet is the first personal-assistant-type harness that feels useful

    Hacker News story from fig.blue, 65 comments

    Peak score 98 · best #1 · 2 of 20 hourly runs in top 10 · +11 points in 23h

11. 11
    Hacker News Gemini 4 Carbon

    Hacker News story from blog.google, 761 comments

    Peak score 98 · best #2 · 8 of 20 hourly runs in top 10 · +148 points in 23h

12. 12
    Hacker News AI execs may be too out of touch to build for the general public

    Hacker News story from techcrunch.com, 60 comments

    Peak score 98 · best #2 · 6 of 20 hourly runs in top 10 · +19 points in 23h

13. 13
    Hugging Face Diffuspace/Clover-35B-A3B-Preview

    text-generation model on Hugging Face

    Peak score 98 · best #2 · 3 of 20 hourly runs in top 10 · +17 likes in 24h

14. 14
    Hacker News We're releasing the weights of Mistral Large 4

    Hacker News story from mistral.ai, 322 comments

    Peak score 98 · best #2 · 7 of 20 hourly runs in top 10 · +466 points in 23h

15. 15
    Hacker News We ran AI agent swarms in Minecraft and Mindustry

    Hacker News story from labs.ycombinator.com, 27 comments

    Peak score 97 · best #1 · 1 of 20 hourly runs in top 10 · +129 points in 24h

16. 16
    Hugging Face nvidia/NVIDIA-Nemotron-3.5-Transcribe-30B-A4B

    automatic-speech-recognition model on Hugging Face

    Peak score 97 · best #2 · 17 of 20 hourly runs in top 10 · +68 likes in 24h

17. 17
    Hugging Face LiquidAI/LFM3-Audio-2B

    any-to-any model on Hugging Face

    Peak score 97 · best #3 · 2 of 20 hourly runs in top 10 · +23 likes in 24h

18. 18
    GitHub qybaihe/bla

    ️ BLA (Blind LLM Agents) — Adversarial defense shield that protects binaries, Electron apps, JS bundles, Python, and WebAssembly against AI…

    Peak score 97 · best #2 · 9 of 20 hourly runs in top 10 · +169 stars in 24h

19. 19
    GitHub C4rohan/Lampline

    Build AI phone agents on your own computer and test every change with an AI caller. Open source, runs free with no API keys, cents per call…

    Peak score 97 · best #2 · 6 of 20 hourly runs in top 10 · -1 stars in 24h

20. 20
    Hugging Face baidu/Unlimited-OCR-2

    image-text-to-text model on Hugging Face

    Peak score 97 · best #2 · 4 of 20 hourly runs in top 10 · +54 likes in 24h

21. 21
    GitHub AienTech/dossier

    A self-hosted job search app that writes tailored resumes and cover letters from your profile.

    Peak score 97 · best #3 · 8 of 20 hourly runs in top 10 · +231 stars in 23h

22. 22
    GitHub yzlin286-wq/Deepscient

    让 AI 与人类一起攻克真正的科学难题 —— 12 阶段 55 门 · 36 工具 · 98 条技能 · 证据链与可复现

    Peak score 97 · best #3 · 2 of 20 hourly runs in top 10 · +107 stars in 24h

23. 23
    Hugging Face tencent/Hy-SimulMT-30B-A3B-FP8

    translation model on Hugging Face

    Peak score 97 · best #4 · 8 of 20 hourly runs in top 10 · +163 likes in 23h

24. 24
    Hugging Face mistralai/Mistral-Large-4-1T-A52B

    image-text-to-text model on Hugging Face

    Peak score 96 · best #3 · 7 of 20 hourly runs in top 10 · +54 likes in 24h

25. 25
    GitHub Entelligence-AI/agentplay

    Replay your coding agent sessions as a map and a timeline

    Peak score 96 · best #4 · 1 of 20 hourly runs in top 10 · +0 stars in 24h

26. 26
    Hacker News Dayjob: Tax – evaluating AI agents on 50 professional tax assignments

    Hacker News story from surgehq.ai, 154 comments

    Peak score 96 · best #4 · 3 of 20 hourly runs in top 10 · +39 points in 23h

27. 27
    GitHub reason-machines/reason-network

    Reason Network: your team's coding agents, talking to each other. The engine behind `reason network`.

    Peak score 96 · best #4 · 1 of 20 hourly runs in top 10 · +32 stars in 24h

28. 28
    GitHub LosaLosSantos/aurelio-finance

    Open-source personal finance app with an AI financial advisor: track your net worth, investments, ETFs, cash and debts on your own computer.

    Peak score 96 · best #4 · 1 of 20 hourly runs in top 10 · +2 stars in 24h

29. 29
    GitHub daveebbelaar/bama

    BAMA: Build Any Mac App. Agent skills to research, clone, design, build, optimize, and test native macOS apps with Swift and SwiftUI.

    Peak score 96 · best #3 · 10 of 20 hourly runs in top 10 · +191 stars in 24h

30. 30
    Hugging Face RecursiveSI/flint

    text-generation model on Hugging Face

    Peak score 96 · best #3 · 1 of 20 hourly runs in top 10 · +23 likes in 24h

31. 31
    Hugging Face LiquidAI/LFM3-1.7B-GGUF

    text-generation model on Hugging Face

    Peak score 96 · best #3 · 1 of 20 hourly runs in top 10 · +28 likes in 24h

32. 32
    Hugging Face pyannote/speaker-diarization-community-1

    automatic-speech-recognition model on Hugging Face

    Peak score 96 · best #4 · 2 of 20 hourly runs in top 10 · +26 likes in 23h

33. 33
    GitHub Leonxlnx/earshot

    Ears for coding agents: let AI hear, review and make sound. CPU-only, open source.

    Peak score 96 · best #5 · 1 of 20 hourly runs in top 10 · +78 stars in 24h

34. 34
    GitHub trhhubsd/ARTEX

    ARTEX · AI autonomous penetration testing system (multi-agent LLM, Go + Next.js) · AI 自主渗透测试系统 · 百度 agent+ 攻防挑战赛冠军

    Peak score 96 · best #5 · 1 of 20 hourly runs in top 10 · +28 stars in 24h

35. 35
    Hugging Face OliviaRossi/Minimax-h3_Singularity-x-10Eros-Max_PRISM

    Model on Hugging Face

    Peak score 95 · best #3 · 1 of 20 hourly runs in top 10 · +17 likes in 24h

36. 36
    Hugging Face hi3d-official/Hi3Dv1.0

    image-to-3d model on Hugging Face

    Peak score 95 · best #4 · 1 of 20 hourly runs in top 10 · +4 likes in 8h

37. 37
    Hugging Face LiquidAI/LFM3-Omni-2B

    any-to-any model on Hugging Face

    Peak score 95 · best #5 · 4 of 20 hourly runs in top 10 · +42 likes in 24h

38. 38
    GitHub feder-cr/git-ai

    Git designed for AI agents.

    Peak score 95 · best #6 · 1 of 20 hourly runs in top 10 · +13 stars in 24h

39. 39
    GitHub HelixDB/helix-foundry

    Connect your company's data, let an agent draft an ontology over it, and load it into HelixDB as one graph you can explore and ask…

    Peak score 94 · best #5 · 1 of 20 hourly runs in top 10 · +34 stars in 24h

40. 40
    Hacker News Manifestos, Fear, and 'Loser Thinking': Inside Proton's AI Reckoning

    Hacker News story from 404media.co, 32 comments

    Peak score 94 · best #5 · 2 of 20 hourly runs in top 10 · +79 points in 23h

41. 41
    GitHub Charonyuu/whatsmyagentdoing

    See what every Claude Code and Codex agent on your machine is doing — live, in a little office.

    Peak score 94 · best #6 · 1 of 20 hourly runs in top 10 · 284 stars since launch, 9 days ago

42. 42
    GitHub jddevtime/open-lakehouse-compute-fabric

    Open Lakehouse Compute Fabric: an open-source lakehouse platform with Microsoft Fabric Compute Extension.

    Peak score 94 · best #7 · 1 of 20 hourly runs in top 10 · 275 stars since launch, 21 days ago

43. 43
    GitHub mashanglinyu/luanyujia-workbench

    多场景 AI 工作台：六层总纲 + 拓扑连线图 + 公开版工作台模板（四场景可跑，源码照搬即用）+ 记忆机制。配套集市：https://www.mydsh.xyz 。作者：https://linyujia.me 。注意：不是装完就能用，场景要按自己的内容调试。

    Peak score 94 · best #5 · 1 of 20 hourly runs in top 10 · +40 stars in 22h

44. 44
    GitHub Graphicle-AI/graphicle

    Code graph and memory for your coding agents, in one Rust program. For Claude Code, Codex, Cursor and any MCP client.

    Peak score 93 · best #7 · 1 of 20 hourly runs in top 10 · +8 stars in 24h

45. 45
    GitHub emanuele-em/kanzo

    Self-hosted kanban for humans and agents. One 4 MB binary, starts in 2 ms, zero setup.

    Peak score 92 · best #8 · 1 of 20 hourly runs in top 10 · +396 stars in 24h

46. 46
    Hugging Face unsloth/Qwen3.8-27B-GGUF

    Model on Hugging Face

    Peak score 92 · best #8 · 1 of 20 hourly runs in top 10 · +14 likes in 24h

47. 47
    Hugging Face openbmb/MiniCPM-OCR-1.0

    image-text-to-text model on Hugging Face

    Peak score 91 · best #9 · 2 of 20 hourly runs in top 10 · +4 likes in 24h

48. 48
    Hugging Face deepseek-ai/DeepSeek-V4.1-Flash-1017

    image-text-to-text model on Hugging Face

    Peak score 91 · best #9 · 1 of 20 hourly runs in top 10 · +422 likes in 24h

49. 49
    GitHub ctoldigital/axuse

    Accessibility-first browser & computer use for AI agents — one MCP server for every harness (Codex, Claude Code, OpenCode, Antigravity).…

    Peak score 91 · best #9 · 1 of 20 hourly runs in top 10 · +10 stars in 24h

50. 50
    Hacker News Sleep framework: A new way for LLMs to retain knowledge in continual learning

    Hacker News story from research.google, 3 comments

    Peak score 91 · best #8 · 1 of 20 hourly runs in top 10 · +48 points in 23h

51. 51
    Hugging Face LiquidAI/LFM3-1.7B

    text-generation model on Hugging Face

    Peak score 90 · best #9 · 3 of 20 hourly runs in top 10 · +117 likes in 24h

52. 52
    Hugging Face ccore/Qwen3.5-4B-3D-Coder

    Model on Hugging Face

    Peak score 90 · best #8 · 1 of 20 hourly runs in top 10 · +89 likes in 24h

53. 53
    Hugging Face LiquidAI/LFM3-VL-2B

    image-text-to-text model on Hugging Face

    Peak score 89 · best #9 · 1 of 20 hourly runs in top 10 · +20 likes in 24h

54. 54
    Hacker News New York Times adds more AI features to its Cooking app. Users aren't thrilled

    Hacker News story from niemanlab.org, 74 comments

    Peak score 89 · best #9 · 1 of 20 hourly runs in top 10 · +3 points in 23h

55. 55
    Hacker News Kentucky man becomes the first humanist granted religious exemption from AI

    Hacker News story from religionnews.com, 504 comments

    Peak score 85 · best #8 · 2 of 20 hourly runs in top 10 · +50 points in 23h

56. 56
    Hacker News Google AI gets cagey when asked who won the 2020 elections

    Hacker News story from arstechnica.com, 65 comments

    Peak score 79 · best #9 · 1 of 20 hourly runs in top 10 · +16 points in 23h

57. 57
    npm @modelcontextprotocol/sdk

    npm package

    Peak score 78 · best #10 · 8 of 20 hourly runs in top 10 · 14.8M downloads/day, 1.20× 7-day avg

58. 58
    Hacker News The Agent SDK

    Hacker News story from cursor.com, 112 comments

    Peak score 76 · best #9 · 1 of 20 hourly runs in top 10 · +40 points in 23h

59. 59
    PyPI anthropic

    Python package

    Peak score 66 · best #10 · 11 of 20 hourly runs in top 10 · 4.8M downloads/day, 0.74× 7-day avg

60. 60
    PyPI pydantic-ai

    Python package

    Peak score 63 · best #10 · 1 of 20 hourly runs in top 10 · 136.7K downloads/day, 0.61× 7-day avg

← 2026-10-28 2026-10-30 →