OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Multi-Agent Systems

LLM Wiki Newsroom

LLM Wiki Newsroom is a local-first, command-driven multi-agent system that processes articles, documents and PDFs into a cross-linked Markdown wiki. Its five newsroom roles separate drafting, rule-based checks, independent review and publication routing, while a regrounding loop brings existing pages back into later work.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

LLM Wiki Newsroom — OpenViST project profile in Multi-Agent Systems.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use it when a document collection needs to become a structured, cross-referenced knowledge base that can be enriched as sources accumulate.

Who it is for

  • Researchers organizing a collection of articles, documents or PDFs into a persistent knowledge base.
  • People who want an AI agent to extract entities and relationships and synthesize information across sources.
  • Developers seeking a Python-based, local workflow for maintaining a linked Markdown wiki.

Documented uses

  • Ingest source documents and produce linked wiki pages.
  • Extract entities, concepts and relationships to structure a research collection.
  • Create cross-source analysis and per-topic synthesis.
  • Revisit existing pages as new sources are added and flag conflicting claims.
  • Browse wiki pages and their connections through the local graph browser.
Before you choose

Requirements & limits

The project is open source under the MIT license. Its Python tools run locally without external API keys. The README publishes a small example corpus as a browsable GitHub Wiki.

  • Claude Code is the primary documented agent and supports all nine slash commands and advanced features.
  • Codex and Gemini CLI are documented for the basic workflow; the README does not assign them Claude Code-only capabilities.
  • The generated wiki is maintained separately from the original source documents and operating rules.
  • The repository's example corpus is small; its GitHub Wiki is a static snapshot, while the interactive graph browser runs locally.
  • On platforms without igraph or leidenalg wheels, the README documents a pure-Python graph partition fallback after removing those requirements.

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

Install the local newsroom scaffold

Prepare the repository and install its Python requirements before using the documented agent workflow.

Before you start

  • Git
  • Python and pip
  • An environment where an AI agent can read and edit files and invoke tools

Steps

  1. Clone https://github.com/alfadur7/llm-wiki-newsroom.git.

  2. Change into the llm-wiki-newsroom directory.

  3. Run pip install -r requirements.txt.

  4. If igraph or leidenalg has no wheel for the platform, remove those two lines from requirements.txt; the graph builder falls back to a pure-Python partition.

Expected outcome

The repository and its Python requirements are prepared for the agent-driven workflow.

Guide limitations

  • This setup recipe does not document a complete ingestion run.
  • The README identifies Claude Code as the primary agent and describes only basic workflows for Codex and Gemini CLI.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
13 October 2026
Original website title
alfadur7/llm-wiki-newsroom · Official homepage title · retained in its source language
How we review sourcesSuggest a correction