DroidDesk turns your Android phone into a real Linux desktop using Termux, Termux X11, TUR, and Proot. Run VS Code, Firefox, LibreOffice, Blender, and more with X11 or VNC support for monitor setup.

Headless streaming server for Moonlight clients, written in Rust.

A terminal graphics engine for rendering, effects, and animation. Built for games, engines, and visual frameworks.

bwrap + rstrict + nix = Nix-based CLI sandboxing (generalized claudebox)

A hypervisor and sandbox cloud for self-hosting AI agents and RL

Asterinas aims to be a production-grade Linux alternative—memory safe, high-performance, and more.

A daily-drivable experimental os, featuring finit as pid 1, to explore the NixOS design space

Multi-tenant Nix Binary Cache

An unofficial NixOS fork with a FreeBSD kernel

Write HTML. Render video. Built for agents.

The Fable Workflow: how Claude Fable 5 worked, distilled into skills any model can run, with the eval that keeps it honest. Think / act / prove.

ORB-SLAM3: An Accurate Open-Source Library for Visual, Visual-Inertial and Multi-Map SLAM

LMCache: Supercharge Your LLM with the Fastest KV Cache Layer

Claude Code skills for hardware design, validation, and bring-up

A from-scratch C++17/ggml port of Depth Anything 3 (ByteDance)

The coding agent that answers to you, your model, your machine, your rules.

User-friendly AI Interface (Supports Ollama, OpenAI API, ...)

Entirety of `rustc`, translated to C.

A feed-forward 3D foundation model for reconstructing scenes from streaming data

Claude Code skill for parametric 3D-printable model generation with CadQuery

agent multiplexer that lives in your terminal.

Secure environments for developers and their agents

Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.

A modernized, complete, self-contained TeX/LaTeX engine, powered by XeTeX and TeXLive.

MiMo Code: Where Models and Agents Co-Evolve

Interactive TUI that uses eBPF to live-inspect any Linux process — CPU, syscalls, network, I/O, memory, threads, and file descriptors.

AutoScientists: Self-Organizing Agent Teams for Long-Running Scientific Experimentation

Workspace-first multi-agent coordination platform for AI development, with shared Specs, Kanban orchestration, and MCP/ACP/ A2A support across web and desktop.