From 9a84675ffa5054b7b9dbe3996b3fbf2d38db627b Mon Sep 17 00:00:00 2001
From: Geoff Seemueller <28698553+geoffsee@users.noreply.github.com>
Date: Thu, 5 Jun 2025 21:46:00 -0400
Subject: [PATCH] Update README.md

Signed-off-by: Geoff Seemueller <28698553+geoffsee@users.noreply.github.com>
---
 README.md | 27 ++++++---------------------
 1 file changed, 6 insertions(+), 21 deletions(-)

diff --git a/README.md b/README.md
index 836ce8e..4f03d79 100644
--- a/README.md
+++ b/README.md
@@ -1,27 +1,12 @@
 # open-web-agent-rs
 
-A Rust-based web agent with local inference capabilities.
+A Rust-based web agent with an embedded openai compatible inference server (supports gemma models only).
 
-## Components
-
-### Local Inference Engine
-
-The [Local Inference Engine](./local_inference_engine/README.md) provides a way to run large language models locally. It supports both CLI mode for direct text generation and server mode with an OpenAI-compatible API.
-
-Features:
-- Run Gemma models locally (1B, 2B, 7B, 9B variants)
-- CLI mode for direct text generation
-- Server mode with OpenAI-compatible API
-- Support for various model configurations (base, instruction-tuned)
-- Metal acceleration on macOS
-
-See the [Local Inference Engine README](./local_inference_engine/README.md) for detailed usage instructions.
-
-### Web Server
-
-Server is being converted to MCP. Things are probably broken.
-
-```text
+## Quickstart
+```bash
+cp .env.example .env
 bun i
+(cd local_inference_server && cargo run --release -- --server)
+docker compose up -d searxng
 bun dev
 ```