Dev Debugger
Full-stack RAG-powered developer tool that ingests codebases, runs vector search, and answers debugging queries with AI — built on MERN with a dockerized backend.
Problem
Debugging across large codebases is slow — devs context-switch between docs, search, and code without a unified interface that understands the project.
Approach
Built a full MERN stack tool with an ingestion pipeline (POST /ingest) that indexes codebases into a vector store, a search layer (GET /search) with filters by username, project, and producer, and a RAG endpoint (POST /ai) that runs tool-call to vector search and returns an AI-generated answer.
Value
A project-aware debugging assistant that answers questions grounded in the actual codebase — not generic docs.
Snapshot
Ingest a codebase once, then query it: vector search returns relevant chunks, the RAG endpoint grounds the AI response in real code context.
Stack
- Next.js
- TypeScript
- Node.js
- Express
- Docker
- Vector Search
- RAG
- Tailwind CSS
Role
- Product design
- RAG pipeline
- API design
- Full-stack build
- Docker setup
Outcomes
- Codebase-aware AI responses via RAG
- Vector search with multi-field filtering
- Dockerized backend for easy deployment
- Clean REST API: /ingest, /search, /ai
Build notes
- POST /ingest accepts a JSON file or directory and indexes it into the vector store.
- GET /search supports filters: query, username, projectName, producer — returns ranked chunks.
- POST /ai runs a tool-call to vector search, then generates a grounded AI response.
- Docker Compose setup for backend — npm run dev for local dev across frontend and backend.
- shadcn-style component system on the frontend for clean DX.
Roadmap
- IDE plugin integration for in-editor querying.
- Multi-repo cross-project search.
- Error pattern library and replay mode.
Want something similar built for your product?
I'll scope the path, then ship with reliability in mind.