Skip to main content

Agent Native Toolkit for Monoco - Task Management & Kanban for AI Agents

Project description

Monoco Distro

Version License

The Headless Operating System for Agentic Engineering.

Monoco is a Linux-like Distribution for AI Agents. It provides the Package Manager, Init System, and Policy Kit that turns a raw LLM Kernel into a production-ready engineering workforce.


🐧 The "Distro" Metaphor

Monoco is built on a clear separation of concerns, inspired by the Linux ecosystem:

Component In Linux In Monoco Responsibility
Kernel Linux Kernel Kimi CLI / Kosong The raw execution engine. Handles LLM prompts, tool execution, and process isolation.
Distro Ubuntu / Arch Monoco The system manager. Orchestrates workflows, enforces policies, manages state (Issues), and installs capabilities (Skills).
Desktop GNOME / KDE VSCode / Zed The user interface. Connects to Monoco via standard protocols (LSP, ACP) to provide a visual experience.

🌟 Core Philosophy

1. Headless & Protocol-First

Monoco is designed to run silently in the background. It doesn't fight for your attention with a chat window. Instead, it exposes its state via LSP (Language Server Protocol) and ACP (Agent Client Protocol), allowing your favorite IDEs to become "Agent-Native".

2. Issue is the Unit of Work

Just as systemd manages Units, Monoco manages Issues. An Issue is not just a text file; it is a stateful object that defines the lifecycle of a task. The Agent cannot "freelance"—it must be assigned to an active Issue.

3. Governance as Code

Monoco acts as the "Policy Kit" for your AI workforce.

  • Guardrails: Prevent destructive actions.
  • Verification: Enforce linting and tests before submission.
  • Audit: Log every decision and tool call.

🚀 Quick Start

1. Installation

Install the Monoco Distro via pip:

pip install monoco-toolkit

2. Initialize System

Turn your project into a Monoco-managed workspace:

monoco init

3. Sync Kernel

Inject Monoco's policies into your Agent Kernel (e.g., Kimi CLI configuration):

monoco sync

4. Start a Session

Launch the Monoco Daemon to begin orchestrating work:

monoco session start

🛠️ Tech Stack & Architecture

  • Kernel Interface: Python (Interfacing with Kimi/Kosong)
  • Distro Logic: Python (State Management, Issue Tracking)
  • Protocols: LSP / ACP (for IDE integration)
  • Storage: Local Filesystem (Markdown/YAML)

📁 Project Structure

Monoco follows a "Distro" architecture that separates State (Issues/), Config (.monoco/), and Logic (monoco/).

For a detailed breakdown of the directory structure, see TREE.md.

🤝 Contributing

Monoco is open-source. We are building the standard distribution for the Agentic era.

📄 License

MIT © IndenScale

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

monoco_toolkit-0.4.0.tar.gz (9.0 MB view details)

Uploaded Source

Built Distribution

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

monoco_toolkit-0.4.0-py3-none-any.whl (339.2 kB view details)

Uploaded Python 3

File details

Details for the file monoco_toolkit-0.4.0.tar.gz.

File metadata

  • Download URL: monoco_toolkit-0.4.0.tar.gz
  • Upload date:
  • Size: 9.0 MB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.7

File hashes

Hashes for monoco_toolkit-0.4.0.tar.gz
Algorithm Hash digest
SHA256 e1ad71dd974de982600907deccba0de5b377410dd25a8b01baf5377d4af04c9f
MD5 1ddae01a3c391797a18f52d82c55d0de
BLAKE2b-256 0ffc9c9570625ce228e8832cd2133109942ad669bbebd5ac471f8d40557d6c81

See more details on using hashes here.

Provenance

The following attestation bundles were made for monoco_toolkit-0.4.0.tar.gz:

Publisher: publish-pypi.yml on IndenScale/monoco-toolkit

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

File details

Details for the file monoco_toolkit-0.4.0-py3-none-any.whl.

File metadata

  • Download URL: monoco_toolkit-0.4.0-py3-none-any.whl
  • Upload date:
  • Size: 339.2 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.7

File hashes

Hashes for monoco_toolkit-0.4.0-py3-none-any.whl
Algorithm Hash digest
SHA256 b4630c65b7cec70603604af352b0d0c0dbe48d0f297e00f9e510fda183331a9f
MD5 e6e9154eb18b3e9adfeb58a6f7eefee1
BLAKE2b-256 f6cf01c5418ed73791c9c1485b2223444b9f865332e5ceab459552725f126a28

See more details on using hashes here.

Provenance

The following attestation bundles were made for monoco_toolkit-0.4.0-py3-none-any.whl:

Publisher: publish-pypi.yml on IndenScale/monoco-toolkit

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