ghuntley/overalls

[experimental] An AI-first developer platform that you own. Overalls launches on 3 November 2026.

What it solves

Overalls provides a self-hosted, persistent development environment platform designed specifically for AI agents. It solves the problem of managing ephemeral development machines by ensuring that your workspace, including its disk and network address, remains intact even when you stop, move, or resize the environment.

How it works

It uses Firecracker microVMs to host development environments running NixOS, Ubuntu, or Windows. Each environment is persistent and can be accessed via browser, SSH, VS Code, or a dedicated CLI. The platform includes a built-in AI agent that can operate on these machines independently, continuing tasks even after you disconnect. It also comes pre-configured with AI coding tools like Claude Code and Codex, managing authentication and token usage centrally.

Who it’s for

This platform is for developers and teams who want to host their own AI-integrated development infrastructure, allowing them to spin up fresh, shareable environments for specific repositories or pull requests across different geographic regions.

Highlights

  • Self-hosted platform that you own and control.
  • Persistent Firecracker microVMs that retain state across sessions.
  • Built-in AI agent capable of background task execution.
  • Pre-installed AI coding assistants with centralized token management.
  • One-click environment creation for repositories, branches, or pull requests.

Related

  • Project
    LodyAI/Lody

    Lody is an open‑source, cross‑platform workspace that lets teams share and coordinate AI coding agents (Claude Code, Codex, Kimi, etc.) across desktop, mobile, web and CLI. It syncs conversations, Git worktrees, files and visual feedback using CRDTs, enabling collaborative, version‑controlled AI‑driven development.

  • Project
    morganlinton/BeautifulRust

    Beautiful Rust is a package of three AI-agent skills (best-practices, review, port) plus a clippy lints config that teach coding agents to write, review, and port idiomatic Rust. It distills five published Rust style guides, works with major coding agents, and is validated by real model-run tests showing measurable improvement.

  • Project
    Xilinx/Vitis-Tutorials

    A collection of in-depth tutorials for the AMD Vitis Unified Software Platform, teaching developers how to build applications for FPGA, Arm processor, and AI Engine architectures.

  • Project
    nicobailon/pi-mcp-adapter

    Pi MCP Adapter is a Pi‑agent plugin that replaces Pi’s built‑in MCP support with a lightweight proxy. It launches MCP servers only when needed, caches tool metadata, reduces token and memory usage, stores OAuth tokens securely, and adds semantic tool search and UI features.