Article
KV Cache from scratch in nanoVLM
By
and 4 others
•
•
57Dhruv PRO
dhruv3006
AI & ML interests
None yet
Recent Activity
upvoted
an
article
2 minutes ago
KV Cache from scratch in nanoVLM
upvoted
an
article
4 days ago
Deep Tutorial on Cursor AI and the Model Context Protocol (MCP)
Organizations
dhruv3006's activity
upvoted
an
article
2 minutes ago
upvoted
3
articles
4 days ago
Article
Deep Tutorial on Cursor AI and the Model Context Protocol (MCP)
By
•
•
3
Article
xLSTM-based time series model TiRex significantly outperforms competing models in forecasting accuracy
By
•
•
12
Article
How to Build an MCP Server with Gradio
By
and 1 other
•
•
165
reacted to
evijit's
post with 🤗
4 days ago
Post
1614
The HF Policy Team submitted our response to the 2025 National Artificial Intelligence (AI) Research and Development (R&D) Strategic Plan.
Blog (with link to full pdf response):
https://huggingface.co/blog/evijit/us-ai-research-strategy-rfi
Blog (with link to full pdf response):
https://huggingface.co/blog/evijit/us-ai-research-strategy-rfi
nice work.
reacted to
ariG23498's
post with 👍
4 days ago
posted
an
update
4 days ago
Post
1056
Browser agents use computers the same way humans do, unlocking powerful use cases for personal assistants, browsers, and enterprise workflows.
Includes Manus AI,Athena Intelligence,c/ua,Stagehand .
Here is a definitive guide.
Courtesy of Theta.
Includes Manus AI,Athena Intelligence,c/ua,Stagehand .
Here is a definitive guide.
Courtesy of Theta.
reacted to
azettl's
post with 👀🤗
4 days ago
Post
1626
Agents & MCP Hackathon Day 1
Before starting with the second night of the Agents & MCP Hackathon, I briefly wanted to share my progress from last night. Not much sleep, but lots of progress!
So I managed to build the first MVP version of my custom Gradio component, https://huggingface.co/spaces/azettl/gradio_consilium_roundtable (https://pypi.org/project/gradio-consilium-roundtable/). This creates a visual roundtable component for AI consensus discussions. Displays AI participants as avatars positioned around an oval table (poker style!) with animated speech bubbles, thinking states, and real-time discussion updates.
Also, I managed to get a rough draft of the Gradio app + MCP server done, but not so much yet that I can share the space with you. You will be able to define your question the AI participants should discuss, decide on the protocol, do role assignments like having a devil's advocate on the table, and define the communication pattern. Lastly, you can decide which AI should be the moderator and how many rounds of discussions there should be. You can see my progress in the attached image.
Most of the options are just placeholders right now, and I will work on their implementation tonight. Hopefully, I can add an MVP tomorrow evening to the following space: Agents-MCP-Hackathon/consilium_mcp.
I am also very interested in the cool stuff you all are building; please let me know in the comments. :)
Before starting with the second night of the Agents & MCP Hackathon, I briefly wanted to share my progress from last night. Not much sleep, but lots of progress!
So I managed to build the first MVP version of my custom Gradio component, https://huggingface.co/spaces/azettl/gradio_consilium_roundtable (https://pypi.org/project/gradio-consilium-roundtable/). This creates a visual roundtable component for AI consensus discussions. Displays AI participants as avatars positioned around an oval table (poker style!) with animated speech bubbles, thinking states, and real-time discussion updates.
Also, I managed to get a rough draft of the Gradio app + MCP server done, but not so much yet that I can share the space with you. You will be able to define your question the AI participants should discuss, decide on the protocol, do role assignments like having a devil's advocate on the table, and define the communication pattern. Lastly, you can decide which AI should be the moderator and how many rounds of discussions there should be. You can see my progress in the attached image.
Most of the options are just placeholders right now, and I will work on their implementation tonight. Hopefully, I can add an MVP tomorrow evening to the following space: Agents-MCP-Hackathon/consilium_mcp.
I am also very interested in the cool stuff you all are building; please let me know in the comments. :)
- 1 reply
reacted to
awni's
post with 🤝🤗🤗👍🤯❤️
6 days ago
Post
First HF social post:
pip install -U mlx
pip install -U mlx
- 2 replies
reacted to
their
post with ❤️🚀🔥
6 days ago
Post
2530
App-Use : Create virtual desktops for AI agents to focus on specific apps.
App-Use lets you scope agents to just the apps they need. Instead of full desktop access, say "only work with Safari and Notes" or "just control iPhone Mirroring" - visual isolation without new processes for perfectly focused automation.
Running computer-use on the entire desktop often causes agent hallucinations and loss of focus when they see irrelevant windows and UI elements. App-Use solves this by creating composited views where agents only see what matters, dramatically improving task completion accuracy
What you can build: Research agents working in Safari while writing agents draft in Notes, iPhone automation for messages and reminders, parallel testing across isolated app sessions, or teams of specialized agents working simultaneously without interference.
Currently macOS-only (Quartz compositing engine).
Read the full guide: https://trycua.com/blog/app-use
Github : https://github.com/trycua/cua
App-Use lets you scope agents to just the apps they need. Instead of full desktop access, say "only work with Safari and Notes" or "just control iPhone Mirroring" - visual isolation without new processes for perfectly focused automation.
Running computer-use on the entire desktop often causes agent hallucinations and loss of focus when they see irrelevant windows and UI elements. App-Use solves this by creating composited views where agents only see what matters, dramatically improving task completion accuracy
What you can build: Research agents working in Safari while writing agents draft in Notes, iPhone automation for messages and reminders, parallel testing across isolated app sessions, or teams of specialized agents working simultaneously without interference.
Currently macOS-only (Quartz compositing engine).
Read the full guide: https://trycua.com/blog/app-use
Github : https://github.com/trycua/cua
posted
an
update
6 days ago
Post
2530
App-Use : Create virtual desktops for AI agents to focus on specific apps.
App-Use lets you scope agents to just the apps they need. Instead of full desktop access, say "only work with Safari and Notes" or "just control iPhone Mirroring" - visual isolation without new processes for perfectly focused automation.
Running computer-use on the entire desktop often causes agent hallucinations and loss of focus when they see irrelevant windows and UI elements. App-Use solves this by creating composited views where agents only see what matters, dramatically improving task completion accuracy
What you can build: Research agents working in Safari while writing agents draft in Notes, iPhone automation for messages and reminders, parallel testing across isolated app sessions, or teams of specialized agents working simultaneously without interference.
Currently macOS-only (Quartz compositing engine).
Read the full guide: https://trycua.com/blog/app-use
Github : https://github.com/trycua/cua
App-Use lets you scope agents to just the apps they need. Instead of full desktop access, say "only work with Safari and Notes" or "just control iPhone Mirroring" - visual isolation without new processes for perfectly focused automation.
Running computer-use on the entire desktop often causes agent hallucinations and loss of focus when they see irrelevant windows and UI elements. App-Use solves this by creating composited views where agents only see what matters, dramatically improving task completion accuracy
What you can build: Research agents working in Safari while writing agents draft in Notes, iPhone automation for messages and reminders, parallel testing across isolated app sessions, or teams of specialized agents working simultaneously without interference.
Currently macOS-only (Quartz compositing engine).
Read the full guide: https://trycua.com/blog/app-use
Github : https://github.com/trycua/cua