JiuwenClaw is an AI agent designed to bring large language model capabilities directly into daily communication applications. It acts as a personal AI butler, automating tasks and evolving based on user feedback, offering a flexible, self-hosted solution for enhanced productivity.

How It Works

This Python-based agent integrates LLMs with existing communication platforms like Huawei's Xiaoyi assistant and Lark. Its core design emphasizes understanding user intent for precise task scheduling and execution. A key differentiator is its "autonomous evolution" mechanism, where the agent automatically refines its skills based on user feedback and error correction, ensuring continuous improvement and alignment with user needs.

Quick Start & Requirements

• Installation: pip install jiuwenclaw
• Prerequisites: Python 3.11, 3.12, or 3.13.
• Setup: Run jiuwenclaw-init for first-time setup or after upgrades, followed by jiuwenclaw-start. A TUI version is available via pip install jiuwenclaw-tui and jiuwenclaw-tui.
• Documentation: Quick Start guides are available for both the main application and the TUI.

Highlighted Details

• Ecosystem Compatibility: Supports Huawei Cloud MaaS and other mainstream model platforms.
• Seamless Integration: Native integration with Huawei's Xiaoyi Open Platform.
• Data Sovereignty: Offers self-hosted deployment options.
• Multi-Platform Access: Interact via web interface, Lark, WhatsApp, and Xiaoyi.
• Autonomous Skill Evolution: Automatically refines skills based on user feedback.

Maintenance & Community

The project welcomes community contributions, including bug reports and feature suggestions. A Discord channel is available for community interaction.

Licensing & Compatibility

Licensed under the Apache License 2.0, permitting commercial use and integration with closed-source projects.

Limitations & Caveats

Upgrading older versions requires careful attention to the changelog for breaking changes; reinitialization of JiuwenClaw is mandatory in such cases, and data backup before upgrading is strongly recommended to prevent service failure.