Jarvis

Your intelligence. Your hardware.

A private, local-first AI assistant with voice and text chat. Talk naturally, as if Jarvis were a third person in the room.

Voice-first · Local AI · Personal memory · No subscription

Download Jarvis →   ·   Website   ·   Get started   ·   Explore the app   ·   Support the project

---

An assistant that lives with you, not in the cloud

Jarvis is built to be part of the conversation. Talk through an idea, discuss plans with a friend, then ask “Jarvis, what do you think?” While listening, it keeps a short, temporary rolling transcript of nearby speech so it can join an ongoing conversation using what was just discussed.

Address Jarvis by name anywhere in a sentence and follow up naturally. Speech recognition, language models and speech synthesis run on hardware you control.

Your diary and knowledge graph stay on your computer. Speech and chat models run locally when you use a local model server. Sensitive information is redacted before reaching model context or the saved diary. Web search, weather and connected tools use the network for those requests.

A voice, a face, and a place in the conversation.

Quick Install

1. Download the app. Choose your platform from GitHub Releases.

Platform	Package	Open
macOS · Apple Silicon	Jarvis-macOS-arm64.zip	Extract, move to Applications, then right-click → Open
macOS · Intel	Jarvis-macOS-x64.zip	Extract, move to Applications, then right-click → Open
Windows · x64	Jarvis-Windows-x64.zip	Extract, then run Jarvis.exe
Linux · x64	Jarvis-Linux-x64.tar.gz	Extract, then run ./Jarvis/Jarvis

2. Choose your local models. The setup wizard guides you through speech recognition and a model server. Use Ollama, or connect an OpenAI-compatible server you already run, such as LM Studio, oMLX or llama.cpp.

3. Make it yours. Allow microphone access and let the first model downloads finish. When Jarvis reports that it is listening, try:

“Jarvis, help me think through my day.”

Right-click the face or use the tray menu to open Chat. Text replies are silent.

Hardware and model choices

Memory needs depend on model size, quantisation, context length and speech recognition. Both Ollama and OpenAI-compatible setup show a memory budget; you can edit estimates for models served through an OpenAI-compatible endpoint. Smaller models trade capability for lower resource use.

Starting point	Chat model
Smaller hardware	qwen3.5:0.8b
Constrained memory	gemma4:e2b
Default	gemma4:e4b
Larger local setup	qwen3.8:27b

Budget memory for Whisper and, when different from chat, the fast model used for voice intent and tool routing. Apple Silicon uses unified memory; other GPUs use dedicated VRAM. Setup budgets chat and fast together alongside the selected Whisper model, using E2B for fast tasks when it fits or sharing E4B across both roles to save memory. Apple Silicon estimates reserve memory for macOS. Saved model choices are preserved, and insufficient memory shows CPU fallback guidance.