diff --git a/README.md b/README.md
index 8dda9c59..0a03a770 100644
--- a/README.md
+++ b/README.md
@@ -4,7 +4,7 @@
- 
+
@@ -12,141 +12,91 @@
-
+
-
- 
-
-# RowboatX - Claude Code for Everyday Automations
+# Rowboat
+**An open-source, local-first AI coworker with memory for everyday work**
+
-RowboatX is a local-first CLI for creating background AI agents with full shell access.
+Rowboat connects your email and meeting notes, builds long-lived knowledge from them, and uses that knowledge to help get work done on your machine.
-**Example agents you can create:**
-- Research every person before your meetings (Exa search MCP + Google Calendar MCP)
-- Daily podcast summarizing your saved articles (ElevenLabs MCP + ffmpeg)
-- Auto-triage Slack DMs and draft responses while you sleep (Slack MCP)
-
-## Quick start
-```bash
-npx @rowboatlabs/rowboatx@latest
-```
+---
## Demo
-[](https://www.youtube.com/watch?v=cyPBinQzicY&t)
-## Examples
-### Add and Manage MCP servers
-`$ rowboatx`
-- Add MCP: 'Add this MCP server config: \ '
-- Explore tools: 'What tools are there in \ '
+[](https://www.youtube.com/watch?v=T2Bmiy05FrI)
-### Create background agents
-`$ rowboatx`
-- 'Create agent to do X.'
-- '... Attach the correct tools from \ to the agent'
-- '... Allow the agent to run shell commands including ffmpeg'
+---
-### Schedule and monitor agents
-`$ rowboatx`
-- 'Make agent \ run every day at 10 AM'
-- 'What agents do I have scheduled to run and at what times'
-- 'When was \ last run'
-- 'Are any agents waiting for my input or confirmation'
+## Quick start
-### Run background agents manually
-``` bash
-rowboatx --agent= --input="xyz" --no-interactive=true
-```
-```bash
-rowboatx --agent= --run_id= # resume from a previous run
-```
-## Models support
-You can configure your models using:
-```bash
-rowboatx model-config
-```
+**Download for Mac:**
-Alternatively, you can directly edit `~/.rowboat/config/models.json`
-```json
-{
- "providers": {
- "openai": {
- "flavor": "openai"
- },
- "lm-studio": {
- "flavor": "openai-compatible",
- "baseURL": "http://localhost:2000/...",
- "apiKey": "...",
- "headers": {
- "foo": "bar"
- }
- },
- "anthropic": {
- "flavor": "anthropic"
- },
- "google": {
- "flavor": "google"
- },
- "ollama": {
- "flavor": "ollama"
- }
- },
- "defaults": {
- "provider": "lm-studio",
- "model": "gpt-5"
- }
-}
-```
-## Contributing
+https://github.com/rowboatlabs/rowboat/releases/latest
-We want help with:
-- **Agent templates** - Pre-built agents others can use (podcast generator, meeting prep, etc.)
-- **MCP server integrations** - Add support for new tools
-- **Platform support** - Windows improvements, Linux edge cases
+Or build from source:
```bash
-git clone git@github.com:rowboatlabs/rowboat.git
-cd rowboat
-npm install
-npm run build
-npm link
-rowboatx
+[build instructions]
```
-Ping us on [Discord](https://discord.com/invite/rxB8pzHxaS) if you want to discuss before building.
+## What it does
----
-## Prefer a Web UI: Rowboat Studio
+Rowboat ingests your:
+- **Email** (Gmail)
+- **Meeting notes** (Granola, Fireflies)
-*Cursor for Multi-agent Workflows*
+and organizes them into a local, Obsidian-compatible vault of plain Markdown files with backlinks.
-โก Build AI agents instantly with natural language | ๐ Connect tools with one-click integrations | ๐ Power with knowledge by adding documents for RAG | ๐ Automate workflows by setting up triggers and actions | ๐ Deploy anywhere via API or SDK
+This vault is not just for browsing or search. It becomes a working memory that Rowboatโs AI uses to take actions on your behalf.
-### Quick start
-1. Set your OpenAI key
- ```bash
- export OPENAI_API_KEY=your-openai-api-key
- ```
-
-2. Clone the repository and start Rowboat (requires Docker)
- ```bash
- ./start.sh
- ```
+As new emails and meetings come in, the relevant notes update automatically, building persistent context across people, projects, organizations, and topics.
-3. Access the app at [http://localhost:3000](http://localhost:3000).
+---
+
+## How itโs different
+
+Most AI tools reconstruct context on demand by searching transcripts or documents.
+
+Rowboat maintains **long-lived knowledge** instead:
+- context accumulates over time
+- relationships are explicit and inspectable
+- notes are editable by you, not hidden inside a model
+- everything lives on your machine as plain Markdown
+
+The result is memory that compounds, rather than retrieval that starts cold every time.
+
+---
+
+## What you can do with it
+
+Rowboat uses this knowledge to help with everyday work, including:
+
+- Drafting emails using accumulated context
+- Preparing for meetings from prior decisions and discussions
+- Organizing files and project artifacts as work evolves
+- Running shell commands or scripts as agent actions
+- Extending capabilities via external tools and MCP servers
+
+Actions are explicit and grounded in the current state of your knowledge.
+
+---
+
+## Local-first by design
+
+- All data is stored locally as plain Markdown
+- No proprietary formats or hosted lock-in
+- Works with local models via Ollama or LM Studio, or hosted models if you prefer
+- You can inspect, edit, back up, or delete everything at any time
-#### Create a multi-agent assistant with MCP tools by chatting with Rowboat
-[](https://youtu.be/KZTP4xZM2DY)
-See [Docs](https://docs.rowboatlabs.com/) for more details.
-
---