FlowDown - Open & Fast AI

About this app

<p>FlowDown is a fast, minimal AI chat app that makes working with large language models feel smooth, focused, and under your control.</p>
<p>For guides, tips, and advanced setup help, visit flowdown.ai.</p>
<p>Why FlowDown</p>
<p>Lightweight and efficient<br />
Focus on your conversation, not the app. FlowDown launches quickly, stays out of your way, and keeps long chats responsive, even on busy machines.</p>
<p>Rich formatting with Markdown<br />
Get clear, readable answers. FlowDown renders Markdown beautifully, so code blocks, bullet lists, tables, and headings in AI responses are easy to scan and use.</p>
<p>Works with the tools you already have<br />
Connect to any OpenAI-compatible API, from major cloud providers to services running in your own home lab. If it speaks the OpenAI API, FlowDown can talk to it.</p>
<p>Talk with text, images, and audio<br />
Show, not just tell. Paste screenshots, drop in images, or record your voice to ask questions. Use it to:<br />
- Transcribe meetings or lectures<br />
- Summarize voice notes<br />
- Ask about the content inside a photo</p>
<p>Smooth, instant-feeling conversations<br />
Blazing-fast text rendering makes responses stream in fluidly, so you can start reading and refining your prompt without waiting for the model to finish.</p>
<p>Automatic chat titles<br />
Stop hunting for the right thread. FlowDown names your conversations automatically based on their content, so you can quickly find that "API bug fix" or "Trip planning" chat later.</p>
<p>Shortcut integrations<br />
Use FlowDown inside your workflows. With Shortcuts support, you can:<br />
- Send selected text from another app to your model<br />
- Generate drafts, summaries, or replies with one tap<br />
- Build custom automations that call your favourite model</p>
<p>Privacy by design<br />
Your data is yours. FlowDown does not collect your chats. For maximum confidentiality, you can run models locally on your own machine with no external server involved.</p>
<p>Open source and transparent<br />
Every line of code is available on GitHub. Inspect it, audit it, or adapt it for your own setups. You can see exactly how your AI client works.</p>
<p>Free trial and open code</p>
<p>FlowDown is fully open source, and we provide a free trial so you can confirm it fits your workflow before buying.</p>
<p>Source code and trial builds are available at:<br />
https://github.com/Lakr233/FlowDown<br />
To try it, open the Releases section and download the latest trial version.</p>
<p>Local models</p>
<p>For offline, private usage, FlowDown can run models locally on Apple Silicon devices with sufficient memory.</p>
<p>Supported model families include:<br />
Cohere, Gemma, Gemma2, Gemma3, InternLM2, Llama / Mistral, OpenELM, Phi, Phi3, PhiMoE, Qwen2, Qwen3, Starcoder2, MiMo, and GLM4.</p>
<p>This gives you:<br />
- Full control over your data<br />
- No dependency on external servers<br />
- The ability to experiment with different open models</p>
<p>Remote models</p>
<p>A complimentary remote model is included so you can start chatting immediately. This starter service is best-effort, with rate limits and no uptime guarantee.</p>
<p>For consistent, reliable use, we recommend:<br />
- Bringing your own API, or<br />
- Hosting your own inference server on local or home-lab hardware</p>
<p>FlowDown supports all OpenAI-compatible endpoints, making it ideal for connecting to tools like Ollama and LM Studio running on your own machine for maximum privacy.</p>
<p>Some setups require technical knowledge. If you are new to self-hosted AI or custom endpoints, please read our documentation carefully; the app can be challenging without it.</p>
<p>We strongly recommend using the free trial before purchasing, as refunds may not be available. For advanced or enterprise use, configuration examples and best practices are documented on our website.</p>
<p>Important note</p>
<p>AI-generated content can be inaccurate or misleading. Always verify critical information and use FlowDown responsibly; you are responsible for how you use the output.</p>
<p>© 2025 FlowDown Team. All rights reserved.</p>