Intent-based AI Agent Platform - Core Package
How to install intentkit?
crestalnetwork/intentkit
$git clone https://github.com/crestalnetwork/intentkitInstalls into the current project.
›Prefer a prompt? Paste this to your agent
Install intentkit by running `git clone https://github.com/crestalnetwork/intentkit`, then use it for the current task and follow its documentation at https://github.com/crestalnetwork/intentkit.
README.md
| 1 | # IntentKit |
| 2 | |
| 3 | <div align="center"> |
| 4 | <img src="frontend/src/app/icon.svg" alt="IntentKit" width="20%" height="20%"/> |
| 5 | </div> |
| 6 | <div align="center"> |
| 7 | <h3>Your Cloud-Native Agent Team</h3> |
| 8 | </div> |
| 9 | <div align="center"> |
| 10 | <a href="https://opensource.org/licenses/MIT" target="_blank"><img src="https://img.shields.io/pypi/l/intentkit" alt="PyPI - License"></a> |
| 11 | <a href="https://pypi.org/project/intentkit/#history" target="_blank"><img src="https://img.shields.io/pypi/v/intentkit" alt="PyPI Version"></a> |
| 12 | <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> |
| 13 | <a href="https://intentcat.com/docs" target="_blank"><img src="https://img.shields.io/badge/docs-intentcat.com-blue" alt="Documentation"></a> |
| 14 | </div> |
| 15 | |
| 16 | IntentKit is an open-source, self-hosted cloud agent cluster that manages a collaborative team of AI agents for you. |
| 17 | |
| 18 | ## Why IntentKit |
| 19 | |
| 20 | Current AI agents generally follow two paths: |
| 21 | |
| 22 | 1. **Local-First** (e.g., OpenClaw): These serve as personal assistants or experimental tools. However, they often require expensive hardware and extensive local permissions. |
| 23 | 2. **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. |
| 24 | |
| 25 | If you are looking for a robust, cloud-native solution, IntentKit is for you. |
| 26 | |
| 27 | ## Features |
| 28 | |
| 29 | - ☁️ **Cloud-Native:** Ultimate resource efficiency. |
| 30 | - 🔒 **Secure by Design:** Agents are fundamentally unable to access any of your secret keys. |
| 31 | - 🤖 **Collaborative AI:** Multiple agents that can call and interact with each other. |
| 32 | - 🔄 **Out-of-the-Box Ready:** Fully configured and ready to use. |
| 33 | - 🔗 **Crypto-Friendly:** Optional Web3 and blockchain integrations. |
| 34 | - 🐦 **Social Media Integration:** Seamlessly connects with social platforms. |
| 35 | - 🛠️ **Extensible Skill System:** Easily add new capabilities. |
| 36 | |
| 37 | ## Documentation |
| 38 | |
| 39 | Please check out the [Documentation](https://intentcat.com/docs/) before getting started. |
| 40 | |
| 41 | ## Deployment |
| 42 | |
| 43 | Read the [Deployment Guide](https://intentcat.com/docs/deployment/) to get started with your setup. |
| 44 | |
| 45 | ## Other Use Cases |
| 46 | |
| 47 | Besides self-deploying IntentKit, you can also use the project in the following ways: |
| 48 | |
| 49 | - **As a Python Library:** Import and extend IntentKit, or use it to add agent cluster capabilities to your existing projects. |
| 50 | - **Via API:** Regardless of the deployment method, you can interact with agents from external applications via the built-in API endpoints. |
| 51 | |
| 52 | ## Contributing |
| 53 | |
| 54 | Due to the rapid pace of AI development, we currently do not accept code contributions via Pull Requests. However, submitting feature requests and reporting bugs in the GitHub Issues section is highly appreciated and the best way to contribute. |
| 55 | |
| 56 | ## License |
| 57 | |
| 58 | This project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details. |
Related
6 picksType
- langchain-mcp-adaptersMake Anthropic Model Context Protocol (MCP) tools compatible with LangChain and LangGraph agents.Jul 2026
- mcporterTypeScript runtime and CLI for connecting to configured Model Context Protocol servers.Jul 2026
- mcp-proxyA MCP server which proxies requests to a remote MCP server over streamable HTTP or SSE.Jul 2026
- mcp-atlassianThe Model Context Protocol (MCP) Atlassian integration is an open-source implementation that bridges Atlassian products (Jira and Confluence) with AI language models following Anthropic's MCP specification.Jul 2026
- open-webuiOpen WebUIJul 2026
- rulesyncUnified AI rules management CLI tool that generates configuration files for various AI development toolsJul 2026
