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.
Hacker News (Front Page) files mainly under programming. We currently carry 788 of its stories. Top-voted stories on Hacker News.
Story provenance
Source · retrieval · rights · ranking — open for full record
inspect →
Story provenance
Attribution is not the same as permission. This drawer separates discovery metadata, excerpts, WeSearch-generated summaries, reuse status, and whether the publisher receives the visit. Nothing here claims a legal grant the publisher has not made.
Record
| Original publisher | GitHub |
| Canonical URL | https://github.com/xoai/sage-wiki |
| Publication time | Tue, 28 Apr 2026 12:41:28 +0000 |
| Retrieval time | 2026-04-28T12:49:31.928Z |
| Last seen | 2026-04-28T12:49:31.928Z |
| Headline source | Publisher (no WeSearch rewrite) |
| Excerpt source | publisher body |
| Excerpt method | First ~120 words (~800 chars) of extracted publisher body, fair-use limited. |
| Summary | WeSearch · cerebras-chat (WeSearch summarizer) |
| Summary source text | contentText |
| Citation coverage | Summary is a WeSearch-generated derivative; primary citation is the original publisher URL. |
| Cluster | zHSf7saMS9kP |
| Cluster logic | Grouped by semantic title/content similarity across sources within a rolling window. Same-publisher template collisions are excluded from coverage comparison. |
| Ranking reason | Story pages are not engagement-ranked. Hub feeds use recency, with optional source-diversified chronological ordering (cap consecutive stories per source). No personalized ranking. |
| Publisher visit | Yes — open original |
| Substitutes article? | No — link-out required for full text |
Rights status (four layers)
WeSearch handling by dimension
| Indexing | May the item be indexed (stored, ranked, made findable)? | Allowed |
| Snippet | May a short excerpt of the publisher's text be shown? | Allowed |
| AI summary | May WeSearch generate its own short summary of the article? | Limited |
| Retrieval / RAG | May the content be exposed for third-party retrieval-augmented generation? | Not asserted |
| Model training | May the content be used to train AI models? | Not asserted |
| Commercial reuse | May the content be reused commercially? | Not permitted |
Basis: Derived from the published RSS/Atom feed. Contact: [email protected]. Reviewed: 2026-07-24.
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.