Today is a big day, we're introducing the first version of the HF MCP server
OPEN SOURCE
-
Llama 3.2 Offline LLM Powers Local Smart Home Assistant
By
–
We had a fascinating question come in after our Llama 3.2 3B chatbot demo on Metis – what if you paired this fully offline LLM with @Home_Assistant
? Imagine a local AI assistant that controls your smart home, responds in real time, and never needs the cloud. Energy-efficient, -
GigaScale 3D Converts Single Photo Into Photorealistic 3D Model
By
–
Un seul cliché. Un modèle 3D photoréaliste.
— VISION IA (@vision_ia) 6 juin 2025
GigaScale 3D est en train de pulvériser toutes les limites connues en génération 3D à partir d’image.
Niveau de détail, textures, proportions : on frôle l’irréel.
Open source, en ligne, gratuit.
Le futur du design 3D commence ici.… https://t.co/XqXrJVOxew pic.twitter.com/iqzzqPqf7iUn seul cliché. Un modèle 3D photoréaliste. GigaScale 3D est en train de pulvériser toutes les limites connues en génération 3D à partir d’image. Niveau de détail, textures, proportions : on frôle l’irréel.
Open source, en ligne, gratuit. Le futur du design 3D commence ici. -
Open Source Solutions for Government Website Development
By
–
Open source solutions are recommended for government website builds. When competing priorities like cost, compliance, and community access are constraining your choices, #opensource offers the strongest foundation for a balanced website build https://
bit.ly/4jxIS0b #openweb -
Tencent Releases Open Source AI Avatar Animation Tool
By
–
Tencent vient de lâcher une nouvelle IA open source.
— VISION IA (@vision_ia) 5 juin 2025
Une seule image + un fichier audio : et votre avatar chante, parle, s’anime… avec émotions, lèvres synchronisées, gestes réalistes.
Extrait de ma dernière vidéo sur les outils IA : https://t.co/QpNiKxISKM pic.twitter.com/qAW9mf6tHfTencent vient de lâcher une nouvelle IA open source. Une seule image + un fichier audio : et votre avatar chante, parle, s’anime… avec émotions, lèvres synchronisées, gestes réalistes. Extrait de ma dernière vidéo sur les outils IA :
-
Annoy powered virtual friend in production at Hugging Face
By
–
Annoy was pretty cool we had it in prod at @huggingface in the early days, powered our virtual friend
-
AgenticSeek: Open-Source Private Web Browsing AI Agent
By
–
Open-source, private, local alternative to Manus AI! Introducing AgenticSeek, an autonomous agent that browses the web, writes code, and plans tasks, all on your device. It runs entirely on your hardware, ensuring complete privacy and zero cloud dependency. 100% Open Source
-
CapSpeech: Open-Source Pretraining Dataset and Models
By
–
CapSpeech is a fully open-source project for academic use, offering a large-scale pretraining dataset, high-quality fine-tuning subsets, & pretrained models.
-
Switch2 Day impacts Hugging Face team productivity
By
–
Switch2 Day has taken its toll on the @huggingface team’s productivity
-
Qwen unveils new high-performance multilingual embedding standard
By
–
Qwen silently dropped the new standard for embeddings on the Hub!
– 0.6B, 4B and 8B versions (probably would use only the 0.6B)
– 32k context length – 100 languages – SOTA on MTEB, but like real SOTA, with 10 points margin on the second bests https://
x.com/tomaarsen/stat
/tomaarsen/status/1930579927020994694
…