Modular Python SDK and monorepo for AI agents, LLM integrations, tools, parsers, embeddings, vector stores, and extensible application workflows.

Experimental microkernel for fun in Python

Переработка ядра PearKernel

泰逢 · 动 agent 的天地气 —— 可嵌入的 Python LLM Agent 微内核(skill=markdown,LLM=调度器,cache-aware 压缩)。

🖥️ NullSec Linux Micro Edition - Portable security station for Mini PCs & Intel NUC

reallyMach — Mach, but not with unnecessary layers.

a modern operating system written with a Odin microkernel and Rust higher superstructure.

A lightweight, driver-based microkernel for orchestrating internal services in long-running Python systems.

A capability-secure operating system derived from mathematical first principles — machine-checked noninterference proof in Z3, a full reference implementation, compile-time unforgeable capabilities in Rust, and a kernel that boots on bare metal enforcing its own proven guarantees.

A modular wrapper for llama.cpp focused on home-lab scaled hardware, low-latency, and KV slot pinned users.

Official skill registry for OpenVole — behavioral recipes for AI agents

An OS kernel that's not as good (or as fast) as Mach.

A self-modifying operating system for an autonomous agent - the LLM is the CPU. Persistent processes, a priority scheduler (single or multi-core), a knowledge base, and gated self-evolution (build in a worktree, verify, promote, re-exec).