DEV.co
RAG Frameworks · afx-team

petercat

PeterCat is an open-source TypeScript application for creating conversational Q&A chatbots tied to GitHub repositories. It provides self-hosted deployment options (AWS + Supabase), automatic knowledge ingestion from GitHub issues and documentation, and multi-platform integration (web SDK, GitHub App). The system uses RAG and LLM APIs (OpenAI, Gemini) to power intelligent responses.

Source: GitHub — github.com/afx-team/petercat
1.5k
GitHub stars
84
Forks
TypeScript
Primary language
MIT
License (OSI-approved)

Key facts

Objective fields from the source. Values we can't verify are shown as “Unknown” rather than guessed.

FieldValue
Repositoryafx-team/petercat
Ownerafx-team
Primary languageTypeScript
LicenseMIT — OSI-approved
Stars1.5k
Forks84
Open issues35
Latest release1.0.0 (2024-12-04)
Last updated2025-06-11
Sourcehttps://github.com/afx-team/petercat

What petercat is

Built in TypeScript with React frontend, Node.js backend, and Supabase for persistence. Integrates GitHub APIs for content extraction, uses WHISKER RAG service for knowledge retrieval, supports OpenAI/Gemini LLM backends, and includes GitHub App OAuth authentication via Auth0. Docker and PyPI build targets available.

Quickstart

Get the petercat source

Clone the repository and explore it locally.

terminalbash
git clone https://github.com/afx-team/petercat.gitcd petercat# follow the project's README for install & configuration

Need it deployed, integrated, or customized instead? DEV.co ships production installs.

Best use cases

GitHub Repository Documentation Support

Automatically index resolved issues and markdown docs to power community Q&A bots, reducing duplicate support requests and providing 24/7 first-line answers.

Self-Hosted Open Source Project Support

Deploy on your own AWS + Supabase infrastructure to maintain data control while providing intelligent issue triage, discussion replies, and PR summaries without third-party SaaS lock-in.

Multi-Platform Chatbot Integration

Embed a conversational UI on project websites via SDK, install as GitHub App for issue/PR automation, and leverage built-in features (code review, issue search/creation) beyond simple Q&A.

Implementation considerations

  • Requires valid OpenAI/Gemini API keys and WHISKER RAG service endpoint; costs scale with conversation volume and knowledge ingestion.
  • GitHub App registration requires OAuth credentials (App ID, Client ID/Secret) and GitHub secret key management via AWS Secrets Manager.
  • Auth0 tenant setup is mandatory for user authentication; no alternative auth backends are documented.
  • Supabase database schema and migrations must be deployed; no out-of-the-box SQL setup script is visible in README.
  • Knowledge ingestion pipeline involves load→split→embed→store workflow; performance/cost trade-offs for large repos are not benchmarked.

When to avoid it — and what to weigh

  • Proprietary / Closed-Source Knowledge Bases — PeterCat is tightly coupled to GitHub APIs and workflows. Knowledgebase sourcing from non-GitHub systems requires custom integration and is not natively supported.
  • Zero External LLM Dependencies — The system requires paid third-party LLM APIs (OpenAI, Gemini) and WHISKER RAG service. There is no offline or open-weight LLM fallback documented.
  • Minimal DevOps / Deployment Capacity — Self-hosting requires managing AWS, Supabase, Auth0, and multiple environment variables. No single-command Docker Compose or fully managed SaaS option is documented.
  • Non-English or Highly Domain-Specific Language — While multilingual UI is offered (Chinese, English, Japanese), real-world quality depends on underlying LLM capabilities and WHISKER RAG embedding model performance. Not documented.

License & commercial use

MIT License. Permissive, OSI-approved. Allows commercial use, modification, and distribution with attribution.

MIT license is permissive and clearly allows commercial use. However, commercial deployment typically requires paid third-party services (OpenAI, Gemini, WHISKER RAG, Supabase, Auth0). No proprietary licensing restrictions on the code itself, but operational dependencies may constrain business models.

DEV.co evaluation signals

Editorial assessment — not user reviews. Directional, with an explicit confidence level.

SignalAssessment
MaintenanceActive
DocumentationAdequate
License clarityClear
Deployment complexityHigh
DEV.co fitGood
Assessment confidenceHigh
Security considerations

GitHub API keys, LLM tokens, and Supabase credentials are handled via AWS Secrets Manager or environment variables. Auth0 integration for user auth. No documented security audit, penetration test, or vulnerability disclosure policy. WHISKER RAG API key is transmitted in requests (bearer token). Admin/user role separation is not clearly defined. Review AWS/Supabase/Auth0 security postures separately.

Alternatives to consider

Langchain / LlamaIndex + Custom Backend

Full control over RAG pipeline, LLM choice, and deployment; requires more engineering effort but avoids vendor lock-in on WHISKER RAG.

GitHub Copilot for Repositories (GitHub native)

GitHub-native, zero setup, but limited customization and no GitHub App automation or web SDK. Suitable for users preferring GitHub-hosted solutions.

Mintlify / Gitbook + Chatbot Plugin

Documentation-first platforms with native chatbot integrations; simpler for pure docs support but less flexible for issue/PR automation.

Software development agency

Build on petercat with DEV.co software developers

Review PeterCat's architecture, cost model, and deployment complexity with your infrastructure team. Verify WHISKER RAG, LLM, and auth provider availability in your region. Start with local dev setup before committing to production.

Talk to DEV.co

Related open-source tools

Surfaced by semantic similarity across the DEV.co open-source index.

Related on DEV.co

Explore the category and the services that help you build with it.

petercat FAQ

Can I use PeterCat without AWS?
Technically yes for local dev, but production deployment relies on AWS Secrets Manager, S3, and CloudFront as documented. Supabase and Auth0 also required. Alternative cloud or self-managed setups would require code/config changes not documented.
What are the costs?
Not clearly stated. Depends on OpenAI/Gemini API usage, WHISKER RAG calls, Supabase compute/storage, and AWS S3/CloudFront. No pricing or cost calculator provided.
Can I deploy this on Kubernetes or Docker Compose?
Docker image is available. Kubernetes/Compose files are not documented. You would need to define your own orchestration and handle service networking.
Does PeterCat work with private GitHub repositories?
Unknown. GitHub App permissions and token scope for private repos are not explicitly documented.

Work with a software development agency

DEV.co helps companies turn open-source tools like petercat into production software. Our software development services cover the full lifecycle — architecture, web development, integration, and maintenance — delivered by software developers and web developers who ship. Engage our software development agency to implement or customize it for your rag frameworks stack.

Ready to Deploy a GitHub-Powered Q&A Bot?

Review PeterCat's architecture, cost model, and deployment complexity with your infrastructure team. Verify WHISKER RAG, LLM, and auth provider availability in your region. Start with local dev setup before committing to production.