nvk/llm-wiki

LLM-compiled knowledge bases for any AI agent. Parallel multi-agent research, thesis-driven investigation, source ingestion, wiki compilation, querying, and artifact generation.

What it solves

It addresses the challenge of managing fragmented research and knowledge by providing a structured, AI-compiled wiki system. It allows users to capture rough ideas, conduct deep research, and transform that information into organized, actionable project briefs and delivery plans.

How it works

The system acts as a specialized skill for AI agents (such as Claude Code, OpenAI Codex, and OpenCode). It uses a hub-and-spoke model where agents ingest sources, perform parallel research, and compile findings into a local, Obsidian-compatible wiki. Users interact with it via natural language commands to research topics, collect media, track inventory, or verify specific theses.

Who it’s for

It is designed for researchers, developers, and power users who rely on AI agents to manage complex information, track project assets, or synthesize large amounts of data into structured knowledge bases.

Highlights

  • Multi-Runtime Support: Works across various AI agent environments including Claude Code, OpenAI Codex, OpenCode, and Pi.
  • Thesis-Driven Research: Automates the investigation of specific claims by gathering evidence for and against a topic to reach a verdict.
  • Obsidian Compatibility: Stores knowledge in a format that integrates directly with Obsidian for personal knowledge management.
  • Project Handoffs: Generates comprehensive, verified project checkpoints and knowledge briefs for transition into delivery.
  • Inventory Management: Tracks not just information, but physical assets, tools, and source queues within the wiki structure.

Related

  • Project
    sdyckjq-lab/llm-wiki-skill

    A system for building a structured, interconnected knowledge base from fragmented data, featuring an interactive knowledge graph and integration with AI CLI agents.

  • Project
    ussumant/llm-wiki-compiler

    A Claude Code and Codex plugin that compiles scattered markdown files and codebases into a synthesized, topic-based wiki to reduce AI agent context costs.

  • Project
    Astro-Han/karpathy-llm-wiki

    A reusable agent skill that enables LLMs to build and maintain a structured wiki of synthesized knowledge, moving beyond simple RAG by compiling sources into durable, cross-linked markdown pages.

  • Project
    shannhk/llm-wikid

    An AI-maintained knowledge base for Obsidian that compiles raw sources into a structured wiki, avoiding RAG by pre-building cross-references and compounding knowledge over time.

  • Project
    nashsu/llm_wiki

    A desktop application that automatically turns documents into a structured, interlinked personal wiki using LLMs, featuring a knowledge graph and automated deep research.