Portable LLM Wiki: Portable Personal Context for LLMs via URL and MCP

LinkTool

Portable LLM Wiki is a tool that turns bios, resumes, and personal notes into a structured wiki. It exposes this context to LLMs like ChatGPT, Claude, and tools like Cursor through a simple URL, a QR code, or the Model Context Protocol (MCP).

Key points

  1. Generates a personal wiki following a GitHub sign-in by ingesting text, resumes, or profile links.
  2. Processes diverse formats such as Slack threads, PDFs, screenshots, and audio memos while tracking provenance and wikilinks.
  3. Exposes context via a markdown briefing URL, a scannable QR code, or an MCP server configuration.
  4. Delivers cited answers grounded in markdown pages via graph-aware retrieval.
  5. Includes a linting mechanism with parallel agents checking for contradictions, stale data, missing pages, and data leaks without silent rewrites.

Why it matters

LLMs lack immediate personal context unless manually supplied. Portable LLM Wiki provides a vendor-neutral protocol to store, maintain, and share verifiable personal background information directly with LLMs and coding assistants.

Analysis

The service focuses on minimal friction by reducing its protocol to three operations: Ingest, Query, and Lint. Rather than enforcing vendor lock-in, it serves plain markdown briefs directly readable by chat interfaces alongside an MCP server configuration for IDEs like Cursor. Crucially, the maintenance layer flags contradictions and stale records for user review rather than mutating knowledge silently.

Mentioned links

Found in

Summary generated by AI (Gemini 3.8 Flash, 27 September 2026). It may contain errors – the original source is authoritative.

Related entries

Similar in content, found by the AI search.

  • Repository:upstash/context7

    Context7: Up-to-Date Code Documentation for LLMs via MCP

    Context7 by Upstash is an open-source platform and MCP server providing LLMs and AI code editors with version-specific, current documentation and code examples directly inside the prompt context.

    61.9kstarsTypeScript

    AI & LLMs· Tool

  • Link:unabyss.com

    Unabyss: Universal Context Layer for AI Tools via MCP

    Unabyss synchronises work context from platforms like Slack, GitHub, Gmail, and Notion, delivering it across multiple AI tools via the Model Context Protocol (MCP). It eliminates the need to repeatedly re-explain context in ChatGPT, Claude, Cursor, and other tools.

    AI & LLMs· Tool

  • Link:agentwikis.com

    Agent Wikis: Maintained Knowledge Bases for Humans and AI Agents

    Agent Wikis transforms fast-moving information sources such as repositories, changelogs, transcripts, and community Q&A into structured Markdown knowledge bases. Designed for both humans and AI agents, the content is accessible via an llms.txt entry point.

    AI & LLMs· Resource

  • Repository:thedotmack/claude-mem

    claude-mem: Persistent Cross-Session Memory for AI Agents

    The open-source project claude-mem (now also branded as Grok Mem) captures agent activity during active sessions, compresses it with AI, and injects relevant context back into future runs.

    93.1kstarsJavaScript

    AI & LLMs· Tool

Back to the knowledge base

Let's talk about your project

Get in touch

Locations

  • Mattersburg
    Johann Nepomuk Bergerstraße 7/2/14
    7210 Mattersburg, Austria
  • Vienna
    Ungargasse 64-66/3/404
    1030 Wien, Austria

Parts of this content were created with the assistance of AI.