Activity, over time
Daily observations from the public event archive.
Attention
Daily stars & forks
Star accumulation
Cumulative stars
Pull requests
Daily opens & merges
Conversations
Daily issues & comments
Community
Daily accounts & reviews
Releases
Daily releases
Trending history
Daily top 10 · last 90 days · UTC
Mentions
Stars
Forks
Contributors
Latest stargazers
The last 10 distinct accounts we observed this year.
Most active participants
PR, issue, comment & review events in the past year.
Packages
Scan pending.
Live mentions badge
Show how many posts mention your project in the last 30 days.
Live mentions · last 30 days
Mentions
I made a fully local AI Physics Tutor for my daughter I put a 1950s radio announcer voice clone and the voice agent pipeline runs fully locally with MLX on my M4 Pro running the model. The device I made uses an Arduino ESP32 chip setting up a secure WebSocket with the Macbook. Latency around 1-2s on my M4 Pro Model: huggingface.co (~9GB) GitHub: akdeb/OpenToys
Built this for my son: Fully, locally running Sméagol! I've been building Voice AI devices this past year on the ESP32 chip with Arduino and I was blown away by how realistic AI Voice clones sound with latest TTS models. I put this project together that sets up a secure websocket with a Rust Mac App running inference with MLX in a local Voice AI pipeline with Qwen3-TTS and Qwen3.8-27B. My son loves the LOTR characters, specifically Smeagol, and I thought I'd share a test of the audio quality and expressivity with the voice clone. I have open-sourced it below. TTS Model: huggingface.co (works with 10 languages) GitHub: akdeb/open-toys
Made a fully local AI Physics Tutor for my niece I used a fun 1950s radio announcer voice clone and the voice agent pipeline runs fully locally with MLX on my M4 Pro running the model. The device I made uses an Arduino ESP32 chip setting up a secure websocket with the Macbook. This is the model I am using (~9GB): huggingface.co GitHub: akdeb/OpenToys