GP-Tree: A Gaussian Process Classifier for Few-Shot Incremental Learning

Accuracy-based Learning Classifier Systems (XCS)

Efficient reliable UDP unicast, UDP multicast, and IPC message transport

The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.

A collection of awesome resources related AI security

A library for doing homomorphic encryption operations on tensors

PYthon For Homomorphic Encryption Libraries, perform encrypted computations such as sum, mult, scalar product or matrix multiplication in Python, with NumPy compatibility. Uses SEAL/PALISADE as bac…

A Python library for fully homomorphic encryption

Home to the Signal Protocol as well as other cryptographic primitives which make Signal possible.

Omnigrok: Grokking Beyond Algorithmic Data

Code for NeurIPS'24 paper 'Grokked Transformers are Implicit Reasoners: A Mechanistic Journey to the Edge of Generalization'

LLM101n: Let's build a Storyteller

SilentEye is a cross-platform application design for an easy use of steganography

MarkLLM: An Open-Source Toolkit for LLM Watermarking.（EMNLP 2024 Demo）

An open-source digital image forensic toolset

TFHE: Fast Fully Homomorphic Encryption Library over the Torus

Korvus is a search SDK that unifies the entire RAG pipeline in a single database query. Built on top of Postgres with bindings for Python, JavaScript, Rust and C.

Python SDK, Proxy Server (LLM Gateway) to call 100+ LLM APIs in OpenAI format - [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthropic, Sagemaker, HuggingFace, Replicate, Groq]

Opiniated RAG for integrating GenAI in your apps 🧠 Focus on your product rather than the RAG. Easy integration in existing products with customisation! Any LLM: GPT4, Groq, Llama. Any Vectorstore: …

Build a Perplexity-Inspired Answer Engine Using Next.js, Groq, Llama-3, Langchain, OpenAI, Upstash, Brave & Serper

Run any open-source LLMs, such as Llama, Mistral, as OpenAI compatible API endpoint in the cloud.

A framework for serving and evaluating LLM routers - save LLM costs without compromising quality

AI wearables

A library for building fast, reliable and evolvable network services.

Minimal, clean code for the Byte Pair Encoding (BPE) algorithm commonly used in LLM tokenization.

Community plugins list, theme list, and releases of Obsidian.

My favorite C programming practices.