Sage Wiki turns a pile of unstructured documents into a fully interlinked, searchable wiki by running them through a five-pass LLM compiler pipeline. Inspired by Andrej Karpathy's vision of LLM-compiled knowledge bases, the pipeline processes source files through diff detection, summarization, concept extraction, image captioning, and cross-reference discovery, with parallel LLM calls and checkpoint/resume for vaults scaling to 100,000+ documents. The typed ontology graph stores entities and relations with BFS traversal, configurable relation types, multilingual synonyms, and a promotion/demotion lifecycle backed by grounding verification and consensus scoring. Multi-format ingestion handles Markdown, PDF, Word, Excel, PowerPoint, EPUB, email, CSV, images, and code files without manual tagging. LLM provider support spans Anthropic, OpenAI, Gemini, Ollama, and any OpenAI-compatible API, with per-pass model routing enabling cost optimization by assigning cheaper models to simpler tasks. The built-in MCP server exposes 17 tools over SSE transport for integration with Claude, Cursor, and any MCP-compatible agent, while native Obsidian vault overlay ensures existing note workflows remain undisrupted. Team deployment supports Git-synced shared wikis, centralized server access, and hub federation across multiple projects. Ships as a single Go binary with Docker Compose multi-arch images serving the web UI on port 3333. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Save a link, a PDF, a YouTube video, or a bookmark export to Kompl and it reads the material on arrival, then writes it into cross-linked wiki pages instead of leaving it in a folder you never reopen. Save more on the same subject and the existing pages are rewritten, so source number fifty improves the pages it touches. Every claim carries a numbered citation back to the original text, and when two sources disagree the page records both sides with a confirm or dismiss button. A knowledge graph shows how topics connect, each link backed by the sentence that states it. An onboarding wizard stages pasted text, URLs, uploaded files, browser bookmarks, Twitter exports, Apple Notes, and Upnote exports for review before anything is compiled. Settings pick the compile model from DeepSeek or Gemini, cap daily spend, and show wiki health. Eight MCP tools let Claude Code, Cursor, Codex, and other agents search, read, and cite pages. Full backups export as one zip that restores without further model calls. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. Apache-2.0 licensed.