Sage-Wiki: An LLM-compiled personal knowledge base
sage-wiki is a tool that uses large language models (LLMs) to automatically compile personal documents into a structured, searchable, and interlinked knowledge base. It supports a wide range of file formats and integrates with existing workflows, including Obsidian and LLM agents via MCP. The system scales to large collections, offers natural language querying, and enhances search through indexing and re-ranking techniques.
- ▪sage-wiki converts documents like PDFs, Markdown, and code into a searchable, interconnected wiki using LLMs.
- ▪It supports over 100,000 documents with tiered compilation for fast indexing and selective updates.
- ▪The tool integrates natively with Obsidian, works with various LLMs, and allows natural language questions with cited answers.
- ▪Users can deploy sage-wiki via CLI, Docker, or a web interface, and it supports vision models for image content extraction.
- ▪Compilation can be triggered on demand, and the system improves over time as new sources enrich existing knowledge.
Opening excerpt (first ~120 words) tap to expand
English | 中文 | 日本語 | 한국어 | Tiếng Việt | Français | Русский sage-wiki An implementation of Andrej Karpathy's idea for an LLM-compiled personal knowledge base. Developed using Sage Framework. Some lessons learned after building sage-wiki here. Drop in your papers, articles, and notes. sage-wiki compiles them into a structured, interlinked wiki — with concepts extracted, cross-references discovered, and everything searchable. Your sources in, a wiki out. Add documents to a folder. The LLM reads, summarizes, extracts concepts, and writes interconnected articles. Scales to 100K+ documents. Tiered compilation indexes everything fast, compiles only what matters. A 100K vault is searchable in hours, not months. Compounding knowledge. Every new source enriches existing articles.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at GitHub.