Vibe Coding DiscoverLaunchStack
View on GitHubAI-powered StartUp Accelerator Engine built with Next.js, LangChain, PostgreSQL + pgvector. Upload, organize, and chat with documents. Includes predictive missing-document detection, role-based workflows, and page-level insight extraction.
Self-hostable TypeScript engine plus Next.js app for AI-native document workflows: OCR ingestion, pgvector hybrid RAG, knowledge graph, LLM abstractions, and Inngest background jobs. Ships a startup-accelerator reference app with role-based access and missing-document detection.
Use Cases
Chat with uploaded company documentsRAG question answering over business filesOCR ingestion of PDFs and Office documentsPage-level insight extractionKnowledge graph construction from documentsPredictive missing-document detectionRole-based document access workflowsSelf-hosted AI document platformEmbedding index management per companyBackground ingestion pipelines
Built With
- Language
- TypeScript
- Frameworks
- Next.js · LangChain · PostgreSQL · pgvector · Drizzle ORM · Neo4j · Inngest · Docker · Better Auth · Tailwind CSS
Tags
rag · pgvector · knowledge-graph · document-ingestion · ocr · hybrid-search · embeddings · self-hosted · nextjs · typescript · postgresql · llm-abstractions · workflow-automation · docker · background-jobs · multi-tenant