workflowstacks
multi-agent

Orchestrate AI Agents with Omnigent

Swap harnesses without rewriting code with Omnigent, a framework for startup founders. 5.6k+ GitHub stars
advanced1-2 hours💵 Free + LLM API costs
9,394 stars1,453 forksPythonHealth Score 9/10Updated 8/28/2026100% free · open source
What it is

Use multiple AI tools in one place.

What you can make with it

Automations like when a new Stripe customer signs up, add them to Notion and send a welcome email via Resend.

How it helps

Omnigent helps you switch between different AI tools without rewriting your code, making it easy to collaborate in real-time from any device.

Real use case example

"A founder who wants to automate their customer onboarding process uses Omnigent to connect to Stripe, Notion, and Resend. They create an automation in Omnigent that adds new customers to Notion and sends a welcome email via Resend. Overnight, this automation is active and working."

If you're new

Pick up this skill when you have a basic understanding of AI tools and want to explore more.

If you're senior

Reach for this when you need a flexible way to orchestrate multiple AI tools without rewriting code.

Common confusion cleared up

Omnigent is not a single AI tool, but rather a framework that helps you work with multiple AI tools together.

Best inside these AI tools
Claude CodeCodex CLICursor
Pairs with
Stripe webhookNotion databaseClaude API
Why we list it on WorkflowStacks: Omnigent is included in this marketplace because it's free and open-source.
What it does

Omnigent is a framework that allows startup founders to swap AI agent harnesses without rewriting code, enabling real-time collaboration and policy enforcement across various agents.

Install / run
pip install omnigent
When to use it
  • When integrating multiple AI agents, such as Claude Code, Codex, or custom agents, into a single workflow
  • When needing to enforce policies and sandboxing across different AI agents
  • When requiring real-time collaboration on AI agent outputs from any device
Quick start
  1. 1Clone the Omnigent repository using `git clone https://github.com/omnigent-ai/omnigent.git`
  2. 2Navigate into the repository using `cd omnigent`
  3. 3Create a new agent configuration using `omnigent init`
  4. 4Start the Omnigent server using `omnigent start`
  5. 5Access the Omnigent dashboard to orchestrate and collaborate on AI agent outputs
Ready-to-paste prompt
omnigent run --agent claude --prompt 'Write a Python function to generate a random number'
Heads up: Ensure you have Python 3.8 or later installed, as Omnigent is not compatible with earlier Python versions
Saves to your device

Topics

agent-framework
agent-governance
agent-orchestration
agents
ai
ai-agent
ai-agents
claude-code
codex
coding-agents
developer-tools
llm
ml
multi-agent
python
sandbox
What's inside — free to inspect
No purchase needed

Read the entire source before you build — unlike paid marketplaces that hide it behind a buy button.

26
top-level files
14
folders
133.3M
source size
Apache-2.0
license
Key files
.pre-commit-config.yaml
AGENTS.md
package.json
README.md
File tree
.claude/
.github/
deploy/
designs/
dev/
docs/
editors/
examples/
integrations/
omnigent/
scripts/
sdks/
tests/
web/
.coverage
.gitattributes
.gitignore
.pre-commit-config.yaml
.python-version
AGENTS.md
CHANGELOG.md
CLAUDE.md
CONTRIBUTING.md
DCO
Quick Actions
Details
Creator
omnigent-ai
Language
Python
Category
multi-agent
Published
6/11/2026

Are you the creator of this tool? Claim your listing → and earn 85% of every sale.