Browse / LLM wiki / Second brain / llm-wiki-agent

llm-wiki-agent

Cafeynman

A text-first workflow for building persistent, traceable Obsidian-style knowledge bases with LLM agents.

Open Cafeynman/llm-wiki-agent → Checked against the four rules.

Works with any agent

ships AGENTS.md, the cross-tool instruction file.

In its own words

README.mdCafeynman/llm-wiki-agent

Build and maintain a persistent, traceable Markdown knowledge base with an LLM agent.

Just drop your files in the inbox, and let your agent build the wiki.

📖 Usage Guide · 🤖 Agent Rules · 🧠 Wiki Rules · ⚙️ Project Context

⚡ Quick Start: Zero to Wiki

Clone or download this repository, then initialize the environment:

*Note: For a separate working directory, including an existing Obsidian vault, pass that path like .\scripts\init.ps1 -VaultRoot "C:\path\to\your\workspace". The target becomes the working root and receives the package-managed agent files, local skills, scripts, docs, and runtime structure. Package-managed files are replaced by the package copy; workspace-specific preferences belong in PROJECT.md.*

Quoting 17% of the README. Read the rest on GitHub ↗

Read from the repository's git tree on 2026-08-17.