Summary

Pallas-Bot is a specialized chatbot designed for Arknights (《明日方舟》) players, functioning as a "learning repeater" that mimics group chat interactions. It targets users seeking a unique, character-driven bot experience within their communities, offering a blend of user-generated content and optional AI enhancements for engaging group dynamics.

How It Works

The core of Pallas-Bot is its "learning repeater" mechanism, which memorizes and reuses group member messages to generate responses. This approach prioritizes authentic community interactions, with optional integration of Large Language Models (LLMs) to augment, rather than replace, the learned user corpus. Its architecture is plugin-based, allowing for modular extensions, and managed via a WebUI. This design aims to preserve the bot's quirky personality derived from its users.

Quick Start & Requirements

• Prerequisites: Python 3.12+, PostgreSQL, and a functional OneBot v11 protocol endpoint (e.g., NapCat).
• Installation: Clone the repository, install dependencies using uv sync, copy and edit the example configuration (config/pallas.example.toml to config/pallas.toml), and run using uv run pallas.
• Access: The WebUI is accessible at http://<host>:8088/pallas/ using a token from the startup logs.
• Documentation: Detailed setup and configuration are available on the documentation site.

Highlighted Details

• "Learning repeater" core prioritizing user-generated chat logs.
• Optional LLM integration for enhanced conversational capabilities.
• Plugin system for custom functionality and local extensions.
• Web-based console for configuration, plugin management, and permissions.

Maintenance & Community

The project actively encourages community contributions via Issues and PRs, with detailed contribution guidelines available. Support and discussion occur in dedicated QQ groups for developers and general users. Community statistics and an online bot presence are maintained via separate services.

Licensing & Compatibility

Pallas-Bot is licensed under the AGPL-3.0 (GNU Affero General Public License v3.0). This strong copyleft license requires that any network-distributed derivative works or modifications must also be made available under the AGPL-3.0, which may impose restrictions on integration into proprietary or closed-source systems.

Limitations & Caveats

The V4 core is described as being in its early stages ("just started, still rough, occasionally awkward, not mature yet"). The project's primary focus is on its unique "learning repeater" functionality, rather than serving as a general-purpose AI chatbot. It requires specific technical prerequisites for setup.