OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Agent Memory & RAG

LLM Wiki Agent

A Python-based coding-agent skill that ingests source documents and maintains a persistent, interlinked Markdown wiki with knowledge extraction, synthesis and graph data.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

LLM Wiki Agent — OpenViST project profile in Agent Memory & RAG.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use it when a document collection is expected to grow and the useful result is a connected, maintained reference rather than a folder of independent files.

Who it is for

  • Researchers building a reference collection over time
  • Readers organizing books, papers or reports
  • Individuals maintaining a personal knowledge base
  • Teams collecting shared documents for structured intelligence

Documented uses

  • Ingest source documents into a structured wiki
  • Create and update entity and concept pages
  • Cross-reference information across sources
  • Flag contradictions and identify gaps
  • Query the accumulated wiki for synthesized answers
Before you choose

Requirements & limits

The repository is public and displays an MIT license. Documented setup uses a local clone and a supported coding agent; the project description states that no API key or separate Python setup is needed. API availability is recorded as No.

  • It works as a CLI and self-hosted workflow rather than a hosted knowledge service.
  • It is designed for Claude Code, Codex, OpenCode and Gemini CLI.
  • The documented ingestion flow supports Markdown plus PDF, DOCX, PPTX, XLSX, HTML, TXT, CSV, JSON, XML, RST, EPUB and more through automatic conversion.
  • The generated structure includes source, entity, concept and synthesis pages, along with an index and append-only operation log.
  • Graph output includes persistent node and edge data and an HTML visualization.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Set up LLM Wiki Agent for document ingestion

Prepare the repository for an agent to ingest source documents and maintain a wiki.

Before you start

  • A clone of the LLM Wiki Agent repository.
  • Claude Code, Codex, OpenCode, Gemini CLI, or another agent that reads a configuration file.

Steps

  1. Clone the repository with the command below.

    Documented command
    git clone https://github.com/SamurAIGPT/llm-wiki-agent.git

  2. Change into the repository directory with cd llm-wiki-agent.

  3. Open the directory in the selected agent; the documented agent-specific configuration files provide the workflow.

  4. Place source documents in raw/ or provide a document path to the agent for ingestion.

Expected outcome

The repository is prepared for the agent to read source material and build a persistent interlinked wiki.

Guide limitations

  • The evidence documents setup and ingestion triggers but does not verify a successful run.
  • Adding a new source format requires modification; parser interfaces are not documented.
  • Connecting the generated wiki to an external knowledge-management interface is experimental.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
1 October 2026
Original website title
SamurAIGPT/llm-wiki-agent · Official homepage title · retained in its source language
How we review sourcesSuggest a correction