PeterCat provides a conversational Q&A agent configuration system, self-hosted deployment solutions, and an all-in-one SDK for creating intelligent Q&A bots for GitHub repositories. It targets community maintainers and developers seeking to enhance technical support ecosystems by integrating AI-powered Q&A into their projects.

How It Works

PeterCat automates the creation of Q&A bots by taking a GitHub repository URL or name. It then generates bot configurations (prompts, names, avatars, etc.) and initiates a knowledge base ingestion process. This process involves loading, splitting, embedding, and storing data from resolved issues and Markdown files within the repository, enabling the bot to answer questions based on this curated knowledge.

Quick Start & Requirements

• Installation: Clone the repository, install dependencies with yarn run bootstrap.
• Running:
  • Client: yarn run client
  • Assistant: yarn run assistant
  • Server: yarn run server
• Prerequisites: Node.js, Yarn, Docker (for building Docker images), AWS account (for deployment), Supabase account, Auth0 account, OpenAI API key, Tavily API key, WHISKER RAG service URL and API key.
• Setup: Requires extensive environment variable configuration for API keys, AWS, Supabase, Auth0, and LLM services.
• Docs: petercat.ai

Highlighted Details

• Automated knowledge ingestion from GitHub issues and Markdown files.
• Multi-platform integration options including SDKs and GitHub Apps.
• Self-hosted deployment solutions using AWS and Supabase.
• Supports multiple LLMs (OpenAI, Gemini) and search APIs (Tavily).

Maintenance & Community

• Actively maintained with CI/CD pipelines and code coverage reporting.
• Community interaction via GitHub Issues and Discussions.
• Sponsorship from Ant Design.

Licensing & Compatibility

• License: MIT@ PeterCat.
• Permissive MIT license allows for commercial use and integration into closed-source projects.

Limitations & Caveats

The project is described as being in a "development stage" ("猫猫还在养成阶段"), implying potential instability or incomplete features. Extensive configuration of multiple external services (AWS, Supabase, Auth0, LLMs) is required for operation.