Hype
RSSCory Land ↗

Open AI

Repositories, models, and discussions from across the community.

Updated 29m ago
A brass signal beacon above a quiet sea at sunset
  1. 01
    prunaai/flux-fast

    This is the fastest Flux endpoint in the world.

    Replicate·45.2M runs·
  2. 02
    Lightricks/LTX-2.5

    image to video · 1.7M downloads

    Hugging Face·7.3K likes·
  3. 03
    Talorys – A self-hosted personal AI agent on Cloudflare's free tier

    142 comments · submitted by rociiu

    Hacker News·308 points·
  4. 04
    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.

    GitHub·2.1K stars·
  5. 05
    prunaai/z-image-turbo

    Z-Image Turbo is a super fast text-to-image model of 6B parameters developed by Tongyi-MAI.

    Replicate·57.2M runs·
  6. 06
    abenzerps/Qwen-Image-2.1-Uncensored-GGUF

    text to image · 2.2M downloads

    Hugging Face·3.9K likes·
  7. 07
    Nvidia in talks to acquire US 'open' model startup Reflection AI

    108 comments · submitted by arkj

    Hacker News·170 points·
  8. 08
    NousResearch/hermes-official-plugins

    ☤ The official plugins for Hermes Agent, built and maintained by Nous Research: Home Assistant, Spotify, Claude Subscription DirectSDK and more, one install away from the Hermes plugin catalog.

    GitHub·114 stars·
  9. 09
    prunaai/p-image-edit

    A sub 1 second 0.01$ multi-image editing model built for production use cases. For image generation, check out p-image here: https://replicate.com/prunaai/p-image

    Replicate·43.6M runs·
  10. 10
    autotrust/JEV-27B-VL

    image text to text · 1.5M downloads

    Hugging Face·3.8K likes·
  11. 11
    500B Tokens Later: Letting AI Agents Decompile a First-Person Shooter

    88 comments · submitted by davikr

    Hacker News·118 points·
  12. 12
    Ayzzz123/mcd-coupon-strategist

    麦麦省钱助手 —— 基于麦当劳 MCP 的点餐成本优化 Skill。算出当前门店最省钱的点餐方案，并主动提示凑单陷阱。

    GitHub·93 stars·
  13. 13
    prunaai/p-image

    A sub 1 second text-to-image model built for production use cases.

    Replicate·21.5M runs·
  14. 14
    Venastine-Research/Xing4.0-29B-A4B-GGUF

    text generation · 48K downloads

    Hugging Face·689 likes·
  15. 15
    AI is creating a 'human premium' for art created by people

    75 comments · submitted by colinprince

    Hacker News·59 points·
  16. 16
    lawrencewzen/wx-bot

    把微信接入你的 AI Agent（Grok / Muse / Claude 等）· Connect WeChat to your personal AI agent via official iLink

    GitHub·96 stars·
  17. 17
    prunaai/p-video

    Fast video generation with built-in draft mode for rapid creative iteration. Text-to-video, image-to-video, and audio-to-video in a single endpoint.

    Replicate·4.4M runs·
  18. 18
    nerkyor/Qwen3.8-27B-Coder390-EfficientThink-Opus5.5-GPT6Astra-Grok4.7-DSV4Pro-K3-SFT-RLOO-MTP-DFlash2

    image text to text · 57K downloads

    Hugging Face·220 likes·
  19. 19
    Five months treating bugs like patients and coding agents like a medical team

    76 comments · submitted by rafiss

    Hacker News·173 points·
  20. 20
    longsurf-ai/openchart

    OSS trading workspace with agents

    GitHub·158 stars·
  21. 21
    prunaai/p-image-upscale

    Fastest image upscaler in the world (<1s) supporting outputs up to 128 MP. contact Pruna AI for dedicated endpoints.

    Replicate·2.8M runs·
  22. 22
    huihui-ai/Huihui-Qwen3.8-27B-abliterated-GGUF

    image text to text · 2.2M downloads

    Hugging Face·1.3K likes·
  23. 23
    Nicolas Cage says he won't work with Amazon again over AI dispute

    2 comments · submitted by Bluestein

    Hacker News·24 points·
  24. 24
    THUROI0787/absent-author

    Research and writing can be automated. Authorship cannot. Evidence list + agent skills for spotting AI-produced papers no human stood behind.

    GitHub·130 stars·
  25. 25
    prunaai/p-video-2

    P-Video-2 is the quality-focused successor to P-Video from $0.025/s

    Replicate·603.4K runs·
  26. 26
    Cloudflare/clef

    image text to text · 14K downloads

    Hugging Face·2K likes·
  27. 27
    Retrofitting language models to operate over bytes

    17 comments · submitted by theanonymousone

    Hacker News·88 points·
  28. 28
    chenxiachan/paperfold

    Zoom any paper for your better understanding

    GitHub·123 stars·
  29. 29
    prunaai/p-video-avatar

    p-video-avatar is the fastest and cheapest avatar/lipsync video model on the market.

    Replicate·347.1K runs·
  30. 30
    Comfy-Org/Qwen-Image-2.1

    8.7M downloads

    Hugging Face·1.1K likes·