Jarvis AI Assistant

Hold one key. Speak. Text appears — perfectly.

100% open-source • 100% local-capable • 100% free forever

https://github.com/user-attachments/assets/763ea6aa-87d5-4e0a-9f05-a2bdaa82f40f

--- ## The (short) story Wispr Flow raised **$81 million** to build a voice dictation app. I got annoyed, spent 3 months of late nights building my own version, and open-sourced it. That's it. No funding. No team. Just one stubborn developer who hates subscriptions. This is what open source is supposed to be. --- ## Why people actually use it - Hold **Fn** → speak → release → clean, punctuated text appears **anywhere** - Removes "um", "like", all fillers automatically - Fixes grammar, can rephrase, bullet-point, or even generate text - Tiny actions already work ("open YouTube", "set 5-min timer") - **Full Prompt Engineering:** Every behavior is customizable. Tweak how Jarvis formats mail, cleans dictation, or behaves as an assistant. - **Fully offline** with local **Whisper** or **NVIDIA Parakeet** (via Sherpa-ONNX) - **100% Private, Blazingly Fast** support for local LLMs via [Ollama](https://ollama.com) - Or use cloud speed with Deepgram + Gemini (1M tokens/day free) — Deepgram requests default to `mip_opt_out=true` **Zero tracking. Zero telemetry. Zero bullshit.** --- ## Download | Platform | Link | |----------|------| | 🍎 **Mac** (Apple Silicon) | [Download DMG (M1/M2/M3/M4)](https://github.com/akshayaggarwal99/jarvis-ai-assistant/releases/latest) | | 💻 **Mac** (Intel) | [Download DMG (x64)](https://github.com/akshayaggarwal99/jarvis-ai-assistant/releases/latest) | | 📱 **iOS** (iPhone/iPad) | [TestFlight](./ios/README.md) *(NEW!)* | ✅ Signed & notarized by Apple → no scary warnings. --- ## Jarvis vs $700M startups | | **Jarvis** | The $700M one | |---|:---:|:---:| | 💰 Price | **Free forever** | $10–24/month | | 🔇 Offline / Local | **Yes (Whisper + Parakeet)** | No | | 🔓 Open Source | **Yes (MIT)** | No | | 📡 Telemetry | **None** | ??? | | 👨‍💻 Built by | **1 guy at 2am** | VC money | --- ## Quick setup (30 seconds) 1. Download & open the app 2. **Go Local (Recommended for privacy):** - Settings → Transcription → Enable **Local Model** - Choose **Whisper** (tiny/base/small) or **Parakeet** (NVIDIA's 600M param model) - Settings → AI Models → Enable **Ollama** (requires [Ollama](https://ollama.com) installed) 3. **Or Go Cloud (Recommended for speed/accuracy):** - Paste free Deepgram + Gemini keys 4. Hold Fn and talk That's literally it. --- ## 🦙 Ollama (Local LLM) Support Jarvis now supports running any LLM locally via Ollama. It's fast, private, and free. 1. **Install Ollama:** [Download here](https://ollama.com) 2. **Pull a model:** ```bash # LFM2 (optimized for speed) ollama pull sam860/LFM2:1.2b # Llama 3 (standard) ollama pull llama3 ``` 3. **Enable in Jarvis:** - Settings → AI Models → Enable **Use Ollama** - Select your model from the dropdown (Jarvis auto-detects them!) ### ⚡ Performance Note Running models locally depends heavily on your hardware. - **Enabled AI Post-Processing:** Adds ~1-3s latency on typical M1/M2 chips. - **Disabled AI Post-Processing:** Instant transcription. - **High-End Hardware:** M1/M2/M3 Max/Ultra chips are nearly instant. **For Lightning Fast Performance:** If speed is critical, use **Deepgram + Gemini** (Cloud) or **Local Whisper + Gemini Flash**, which are significantly faster than local LLMs on standard hardware. --- ## Keyboard shortcuts | Shortcut | What it does | |----------|--------------| | `Fn` (hold) | Start/stop recording | | `Fn` (double-tap) | Toggle hands-free mode | | `Escape` | Cancel recording | --- ## Build from source ```bash git clone https://github.com/akshayaggarwal99/jarvis-ai-assistant.git cd jarvis-ai-assistant npm install && npm run build && npm run dev ``` Requires Node.js 18+, macOS 10.13+, Xcode CLI tools. --- ## Roadmap (help me choose!) - [x] Proper "local-only" onboarding (no fake keys needed) - [x] AWS Bedrock support - [x] Ollama support - [x] Custom voice commands & prompts - [x] iOS (TestFlight available!) - [x] NVIDIA Parakeet support (via Sherpa-ONNX) — blazing fast local transcription - [ ] Windows version - [ ] Clipboard magic & multi-step actions - [ ] Streaming transcription (real-time words as you speak) Open issues, vote, or drop crazy ideas → [github.com/.../issues](https://github.com/akshayaggarwal99/jarvis-ai-assistant/issues) --- ## Wanna contribute? Jarvis is a community project. If you're a developer and want to help build the future of local-first AI, check out our [Contributing Guidelines](CONTRIBUTING.md). ## Wanna help? Every star pushes this higher so more people discover they don't need another subscription.

Or just use it and tell one friend. That's enough. --- ## ⭐ Star History

---

Built with caffeine and spite by Akshay

Open source isn't about beating giants.
It's about making sure no one ever has to pay them.

_{MIT License — do whatever you want with it.}