diff --git a/docs/index.md b/docs/index.md
new file mode 100644
index 0000000..f674c55
--- /dev/null
+++ b/docs/index.md
@@ -0,0 +1,44 @@
+# Pagepiper
+
+Self-hosted document search with BM25 full-text indexing and (with local Ollama) hybrid vector search and LLM-powered chat.
+
+## Demo
+
+Try it: [pagepiper.circuitforge.tech](https://pagepiper.circuitforge.tech)
+
+## Screenshots
+
+### Library
+
+![Library view](screenshots/01-library.png)
+
+Scan your PDF directory to index documents. Each document shows page count and ingest status.
+
+### Chat
+
+![Chat view](screenshots/02-chat.png)
+
+Ask questions across your indexed documents. Results cite the source document and page number.
+
+## Quick Start (Docker)
+
+```bash
+git clone https://git.opensourcesolarpunk.com/Circuit-Forge/pagepiper
+cd pagepiper
+cp .env.example .env          # set PAGEPIPER_DATA_DIR and PAGEPIPER_BOOKS_DIR
+docker compose up -d --build
+# open http://localhost:8521
+```
+
+Place PDFs in your `PAGEPIPER_BOOKS_DIR` directory, then click "Scan for PDFs" in the Library view.
+
+## Tiers
+
+| Feature | Free | Paid (BYOK) |
+|---------|------|-------------|
+| BM25 full-text search | Yes | Yes |
+| Unlimited local ingestion | Yes | Yes |
+| Hybrid vector search | No | Yes (local Ollama) |
+| LLM chat over documents | No | Yes (local Ollama) |
+
+Set `PAGEPIPER_OLLAMA_URL` in your `.env` to unlock the Paid tier with your own Ollama instance.
diff --git a/docs/screenshots/01-library.png b/docs/screenshots/01-library.png
new file mode 100644
index 0000000..f637c90
Binary files /dev/null and b/docs/screenshots/01-library.png differ
diff --git a/docs/screenshots/02-chat.png b/docs/screenshots/02-chat.png
new file mode 100644
index 0000000..fe62bb5
Binary files /dev/null and b/docs/screenshots/02-chat.png differ