Skip to main content

FyodorOS: A Compiled AI Microkernel with Native Desktop Interface

Project description

FyodorOS

Version Python 3.8+ License: MIT

███████╗██╗   ██╗ ██████╗ ██████╗  ██████╗ ██████╗
██╔════╝╚██╗ ██╔╝██╔═══██╗██╔══██╗██╔═══██╗██╔══██╗
█████╗   ╚████╔╝ ██║   ██║██║  ██║██║   ██║██████╔╝
██╔══╝    ╚██╔╝  ██║   ██║██║  ██║██║   ██║██╔══██╗
██║        ██║   ╚██████╔╝██████╔╝╚██████╔╝██║  ██║
╚═╝        ╚═╝    ╚═════╝ ╚═════╝  ╚═════╝ ╚═╝  ╚═╝
          The Experimental AI Microkernel

FyodorOS is a local-first AI Operating System that runs on your metal. Unlike traditional OSs designed for humans (GUI/CLI) or servers (API), FyodorOS exposes the entire system state as a Document Object Model (DOM), allowing Agents to "perceive" and interact with the kernel natively.

🚀 Vision

We believe that for AI Agents to be truly useful and safe, they need an environment built for them. FyodorOS provides:

  • Structured Observation: The OS state (Filesystem, Processes, Users) is a queryable DOM tree.
  • Cognitive Loop: Built-in ReAct (Reasoning + Acting) loop at the kernel level.
  • Safety Sandbox: A strict, rule-based verification layer that constraints Agent actions before execution.
  • Agent-Native Apps: Standard tools (browser, explorer, calc) that return structured JSON/DOM instead of plain text, minimizing token usage and parsing errors.
  • Cloud Integration (v0.5.0): Native Docker and Kubernetes support.
  • Long-Term Memory (v0.7.0): Persistent semantic storage allowing agents to learn and recall information.
  • Desktop Interface (v0.8.0): A native desktop application bridging the Python kernel with a modern React UI.

📦 Installation

Option A: User (Recommended)

Download the installer for Windows, Mac, or Linux from the Releases page.

Option B: Developer (Legacy/Headless)

You can install FyodorOS as a Python package for headless or CLI-only usage.

pip install fyodoros
playwright install chromium

🛠️ Development

To build the full Desktop experience from source, you need Node.js, Rust, and Python installed.

  1. Clone the Repository

    git clone https://github.com/Kiy-K/FyodorOS.git
    cd fyodoros
    
  2. Install Frontend Dependencies

    cd gui
    npm install
    
  3. Run in Development Mode

    npm run tauri dev
    

🏗️ Architecture

FyodorOS v0.8.0 adopts a hybrid architecture to combine the flexibility of Python AI libraries with the performance and native capabilities of Rust.

graph LR
    User[User] <--> React[React UI (Shadcn)]
    React <--> Tauri[Tauri (Rust Sidecar)]
    Tauri <--> Nuitka[Nuitka (Compiled Python Kernel)]
    Nuitka <--> System[Host System (Sandboxed)]
  • React UI: A modern web-based interface for visualizing the OS state and Agent actions.
  • Tauri: Handles window management and communicates with the Python kernel via a sidecar protocol.
  • Nuitka Kernel: The Python core compiled into a standalone binary for performance and security, running the Agent loop and managing system resources.

🤝 Contributing

FyodorOS is an experimental sandbox. We welcome contributions to:

  • Expand the standard library of Agent Apps.
  • Improve the DOM representation of system state.
  • Implement more complex Sandbox rules.

Built for the future of Autonomous Computing.

Star History

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

fyodoros-0.8.0.tar.gz (71.6 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

fyodoros-0.8.0-py3-none-any.whl (85.3 kB view details)

Uploaded Python 3

File details

Details for the file fyodoros-0.8.0.tar.gz.

File metadata

  • Download URL: fyodoros-0.8.0.tar.gz
  • Upload date:
  • Size: 71.6 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.7

File hashes

Hashes for fyodoros-0.8.0.tar.gz
Algorithm Hash digest
SHA256 dacd20f664eb98db1c1aa547818f4e49b28d567d650223dd21936dedb7f5b69e
MD5 275033a4309b8cb36c8d0f90634f5047
BLAKE2b-256 da21eaf5e2c74c144f29315fe3c4331d58ece5dfae03cfc45773f740244e0fea

See more details on using hashes here.

Provenance

The following attestation bundles were made for fyodoros-0.8.0.tar.gz:

Publisher: python-publish.yml on Kiy-K/FyodorOS

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file fyodoros-0.8.0-py3-none-any.whl.

File metadata

  • Download URL: fyodoros-0.8.0-py3-none-any.whl
  • Upload date:
  • Size: 85.3 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.7

File hashes

Hashes for fyodoros-0.8.0-py3-none-any.whl
Algorithm Hash digest
SHA256 2dc729e26b0833225c856516242ef0aacf812a2832e92bf03895154a3b4f3efa
MD5 ac54632fb7e27f9d9cd986bcac6ae224
BLAKE2b-256 93d77fa9e0a82c0d8ebf3aa190877cb99927ab8249578105dfbb8408113b7c46

See more details on using hashes here.

Provenance

The following attestation bundles were made for fyodoros-0.8.0-py3-none-any.whl:

Publisher: python-publish.yml on Kiy-K/FyodorOS

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page