Verified project record

crestalnetwork/intentkit

A self-hosted, cloud-native framework for managing a collaborative team of AI agents with a focus on resource efficiency and secret-key isolation. It is suited for developers who need extensible, API-driven agent orchestration without relying on managed services.

Project overview

Project type: AI Agent · Workflow
Use cases: Automation
Deployment: Refer to project documentation
License: MIT

Best for

Developers and AI engineers seeking a self-hosted framework to build and extend collaborative AI agent clusters via Python or API.

Key capabilities

Multiple agents can call and interact with each other within the framework.
Agents are fundamentally unable to access any of your secret keys.
You can easily add new capabilities to the agents as needed.
You can import and extend the framework, or use it to add agent cluster capabilities to your existing projects.
You can interact with agents from external applications via the built-in API endpoints.

Limitations and risks

The project currently does not accept code contributions via Pull Requests.

Getting started

Setup is of medium difficulty and requires reading the deployment guide and self-hosting instructions.

Evidence and sources

README: <a href="https://hub.docker.com/r/crestal/intentkit" target="_blank"><img src="https://img.shields.io/docker/v/crestal/intentkit?label=Docker" alt="Docker"></a>
Release: v2.6.3
README: IntentKit is an open-source, self-hosted cloud agent cluster that manages a collaborative team of AI agents for you.
README: Cloud-Native: Similar to modern web apps, these run in the cloud, consume minimal local resources, require zero maintenance, and offer high reliability for completing tasks.
README: 🔒 **Secure by Design:** Agents are fundamentally unable to access any of your secret keys.

Reviewed at: 2026-07-15T16:10:11Z