---
name: "Coordinate multi-harness agent sessions with Omnigent"
slug: "coordinate-multi-harness-agent-sessions-with-omnigent"
description: "Run Claude Code, Codex, Cursor, OpenCode, Pi, and custom agents behind one governed orchestration layer with shared sessions, policies, and sandbox options."
github_stars: 7435
verification: "security_reviewed"
source: "https://github.com/omnigent-ai/omnigent"
author: "Omnigent AI"
publisher_type: "organization"
category: "Templates & Workflows"
framework: "Multi-Framework"
tool_ecosystem:
  github_repo: "omnigent-ai/omnigent"
  github_stars: 7435
---

# Coordinate multi-harness agent sessions with Omnigent

Run Claude Code, Codex, Cursor, OpenCode, Pi, and custom agents behind one governed orchestration layer with shared sessions, policies, and sandbox options.

## Prerequisites

Python 3.12+, uv or pipx, optional Node.js/tmux for coding-agent harnesses, supported sandbox provider if used

## Installation

Use the upstream install or setup path that matches your environment:
- uv tool install omnigent # or: pip install "omnigent"
- uv tool install "omnigent[databricks,modal]"
- brew install omnigent-ai/tap/omnigent
- uv tool install -q --python 3.12 git+https://github.com/omnigent-ai/omnigent.git

Requirements and caveats from upstream:
- Omnigent needs **Python 3.12+**. Install the omnigent package:
- <summary>Toolchain and prerequisites (if the installer reports a missing tool)</summary>
- **uv** (required). https://docs.astral.sh/uv/getting-started/installation/

Basic usage or getting-started notes:
- One command installs Omnigent and everything it needs:
- <details>
- <summary>Optional integrations and extras</summary>

- Source: https://github.com/omnigent-ai/omnigent
- Extracted from upstream docs: https://raw.githubusercontent.com/omnigent-ai/omnigent/HEAD/README.md

## Documentation

- https://github.com/omnigent-ai/omnigent

## Source

- [Agent Skill Exchange](https://agentskillexchange.com/skills/coordinate-multi-harness-agent-sessions-with-omnigent/)
