Adaptive Test-time Learning and Autonomous Specialization

Computer use for about $0.0002 a step: OCR the screen, classify the next action with TypeSafe, click. macOS.

Run frontier MoE models on hardware you already own — pure C, zero deps, experts streamed from disk. Tiny engine, immense model. 🐦

SIA is a Self Improving AI framework to autonomously improve the performance of any AI system (Model / Agent) on a benchmark task.

LiteMaaS is a proof-of-concept application for managing LLM subscriptions, API keys, and usage tracking. It seamlessly integrates with LiteLLM to provide a unified interface for accessing multiple …

A high-throughput and memory-efficient inference and serving engine for LLMs

Blazing-fast LLM inference in pure Rust. No PyTorch and Python runtime.

eLLM: Run Long-Horizon Inference Faster on CPUs Than on GPUs

A theoretical reconstruction of the Claude Mythos architecture, built from first principles using the available research literature.

Weighs the soul of incoming HTTP requests to stop AI crawlers

Medieval village economy simulation — up to 1000 LLM agents across multiple villages, driven by supply chains, hunger, tool degradation and market pressure.

A lightweight alternative to OpenClaw that runs in containers for security. Connects to WhatsApp, Telegram, Slack, Discord, Gmail and other messaging apps,, has memory, scheduled jobs, and runs dir…

"Quantum attention functions are the keys to quantum machine learning." ― Amit Ray

A CLI to estimate inference memory requirements for Hugging Face models, written in Python.

Professional Service Automation Platform for Small to Medium Sized Agencies

This repository contains a curated collection of 300+ case studies from over 80 companies, detailing practical applications and insights into machine learning (ML) system design. The contents are o…

Namer UI is a collection of reusable Next.js/React components made to empower developers to quickly build beautiful UIs.