diff --git a/.gitignore b/.gitignore
new file mode 100644
index 0000000..fb45e40
--- /dev/null
+++ b/.gitignore
@@ -0,0 +1,13 @@
+
+# AI assistant symlinks (local only)
+CLAUDE.md
+AGENTS.md
+GEMINI.md
+QWEN.md
+
+# Model files
+*.safetensors
+*.bin
+*.gguf
+*.pt
+*.pth
diff --git a/LLM.md b/LLM.md
new file mode 100644
index 0000000..4235a86
--- /dev/null
+++ b/LLM.md
@@ -0,0 +1,36 @@
+# zen-pro — AI Knowledge Base
+
+**Project**: zen-pro
+**Organization**: zenlm
+**Repository**: https://github.com/zenlm/zen-pro
+**HuggingFace**: https://huggingface.co/zenlm/zen-pro
+**Last Updated**: 2026-02-27
+
+## Overview
+
+zen-pro is the 8B professional-grade model from Zen LM. Abliterated variant of Qwen3-8B.
+Built for professional workloads requiring complex reasoning without content restrictions.
+
+## Architecture
+
+- Parameters: 8B
+- Architecture: Qwen3ForCausalLM
+- Context: 32K tokens
+- Base: Qwen3-8B abliterated
+- License: Apache 2.0
+
+## Rules for AI Assistants
+
+1. **ALWAYS** update LLM.md with significant discoveries
+2. **NEVER** commit model weights (*.safetensors, *.bin, *.gguf, *.pt)
+3. **NEVER** commit symlinked files (CLAUDE.md, AGENTS.md, GEMINI.md, QWEN.md)
+4. **NEVER** create random summary files — update THIS file only
+5. Zen models are based on **Qwen3** (not Qwen2!)
+
+## Context
+
+This file (`LLM.md`) is symlinked as CLAUDE.md, AGENTS.md, GEMINI.md, QWEN.md.
+
+---
+
+*Part of the Zen AI family — Clarity Through Intelligence*