RayFernando1337
Level up your AI skills and start building with a 12-year ex-Apple Engineer – latest AI app at https://TruthTorch.ai
Los Altos, CA
Pinned Repositories
ChatMLX
ChatMLX is a large model real-time conversation app implemented using MLX.🚧
claude_github_cloudflare_worker
cursor
Repo of cursor prompts
dotai
LLM-Calc
Instantly calculate the maximum size of quantized language models that can fit in your available RAM, helping you optimize your models for inference.
llm-cursor-rules
My go-to rules for using Cursor and LLMs in software development.
Migrate-GitHub-Forks-to-Org
Python Replit to migrate your GitHub Forks into an Org
MLX-Auto-Subtitled-Video-Generator
Generate accurate transcripts using Apple's MLX framework
transcript-chat
RayFernando1337's Repositories
RayFernando1337/MLX-Auto-Subtitled-Video-Generator
Generate accurate transcripts using Apple's MLX framework
RayFernando1337/LLM-Calc
Instantly calculate the maximum size of quantized language models that can fit in your available RAM, helping you optimize your models for inference.
RayFernando1337/llm-cursor-rules
My go-to rules for using Cursor and LLMs in software development.
RayFernando1337/transcript-chat
RayFernando1337/cursor
Repo of cursor prompts
RayFernando1337/dotai
RayFernando1337/Migrate-GitHub-Forks-to-Org
Python Replit to migrate your GitHub Forks into an Org
RayFernando1337/ChatMLX
ChatMLX is a large model real-time conversation app implemented using MLX.🚧
RayFernando1337/claude_github_cloudflare_worker
RayFernando1337/dailyreps-next
RayFernando1337/DistillerSDK
Fundation sdk for distiller one
RayFernando1337/hello-llama
A simple chat bot to play with Llama 3.1
RayFernando1337/MedicalChat
Chat with medical research papers. (Starting with sports medicine, not medical advice)
RayFernando1337/x-ai-content-filter-groq
Filter X content using LLM API requests, configurable, based on Groq API
RayFernando1337/hermes
🎥➡️📝 Hermes: Blazing-fast video transcription powered by AI gods! Transcribe 6.5 minutes of video in just 1 second using Groq's LPU. Choose your transcription deity: MLX Whisper (local), Groq (speed demon), or OpenAI (cloud classic). Convert speech to text faster than Hermes delivering messages on Olympus!
RayFernando1337/mckays-app-template
This is a full-stack app template for courses on Takeoff.
RayFernando1337/nextjs-notion-waitlist-template
A template repository for creating a waitlist using Next.js 14, Notion as a CMS, Upstash Redis for rate limiting and Resend for sending emails with a custom domain
RayFernando1337/o1-ai-playground
Come join the best place on the internet to learn AI skills. Use code "o1launchparty" for an extra 20% off.
RayFernando1337/SwiftUI-experiments
Examples with SwiftUI that showcase various interactions, animations and more