Stars
MLS-encrypted conversations template for Emissary
kenneth-ge / FastFlowLM-NPU1
Forked from FastFlowLM/FastFlowLMRun LLMs on AMD Ryzen™ AI NPUs in minutes. Just like Ollama - but purpose-built and deeply optimized for the AMD NPUs.
Train the smallest LM you can that fits in 16MB. Best model wins!
Distributed Peer-to-Peer Web Search Engine and Intranet Search Appliance
A repo to train your own small sarvam-30b model
Training neural networks on Apple Neural Engine via reverse-engineered private APIs
A Messaging Layer Security (RFC 9420, MLS) implementation in TypeScript
The most atomic way to train and inference a GPT in pure, dependency-free JavaScript. This repository covers the complete algorithm. Everything else is just efficiency. Inspired by Karpathy's micro…
Framework-agnostic, browser-based components for photo and video editing with WebGL and WebCodecs
Complete guide to running large language models locally on AMD Ryzen AI Max+ 395 (Strix Halo) with 128GB unified memory. Covers BIOS config, kernel setup, ROCm installation, and llama.cpp deploymen…
Full-featured MP4 format, MPEG DASH, HLS, CMAF SDK and tools
Run LLMs on AMD Ryzen™ AI NPUs in minutes. Just like Ollama - but purpose-built and deeply optimized for the AMD NPUs.
Cordova Cell Triangulation Plugin
Helper package for using quantized versions of the Indic ASR Model by AI4Bharat.
The most powerful local music generation model that outperforms almost all commercial alternatives, supporting Mac, AMD, Intel, and CUDA devices.
Conditional Memory via Scalable Lookup: A New Axis of Sparsity for Large Language Models
LiteGPT: A 124M Small Language Model (SLM) pre-trained on FineWeb and fine-tuned on Alpaca.
Memory layer for AI Agents. Replace complex RAG pipelines with a serverless, single-file memory layer. Give your agents instant retrieval and long-term memory.
A mongod-compatible server with an sqlite backend. Meant for small-scale applications that don't need replication or sharding.
✅Browser ❌Cloudflare ✅Host — Generator of customized Cloudflare error pages (unofficial)
Weighs the soul of incoming HTTP requests to stop AI crawlers
Unofficial implementation of Titans, SOTA memory for transformers, in Pytorch