quality_assurance · saas · workflow
PeterCat: Building an AI assistant for GitHub with RAG, LangChain, and Supabase
Developers waste hours searching GitHub issues and search engines for answers, then wait days for maintainer responses; general-purpose LLMs like ChatGPT hallucinate when asked about niche open-source repositories or specific framework quirks.
How it works
Common implementation structure
How this type of workflow is generally built, generalized across documented cases — not tied to any one vendor's stack. Click any stage to read what happens there. Specific products that implement these stages appear in “Tools commonly seen” below.
Stage 1 · Repository content vectorized
Valuable repository content including code and historical issues is vectorized and stored in a vector database.
Tools used
LangChainFastAPISupabaseAWS LambdaRAGChatGPTOpenAIGitHub App
Outcome
Within three months of its September 2024 open source release, PeterCat garnered over 850 stars and was adopted by 178 open source projects; in one documented case it saved a developer hours of frustration resolving Ant Design table component issues.
What failed first
The initial prototype simply relocated the language model service without addressing its inherent weaknesses for repository-specific knowledge.
Results
Time savedover 850
Volume178
Running sinceSeptember 2024
Grounding & classification
Source type: technical build writeup
33 fields verified against source quotes.
ai agentknowledge searchmulti agent workflowragsummarizationcode diff prknowledge basebuilder submittedfailure mode describedmetric backedproduction runtime claimedtools describedworkflow describedsoftwarethroughput increasetime savedtechnical build writeupit supportquality assuranceagentic task executionrag answering