isair /jarvis
A 100% private and local AI assistant for your desktop. Always present, able to jump into conversations. Supports unlimited MCP tools and unlimited memory with self-learning. Free WisprFlow alternative with its dictation support. Runs on macOS, Windows and Linux.
★ 2,336⑂ 553👁 26⑃ 655● 531▤ 58
2,336
stars
553
forks
26
watchers
655
prs
531
issues
58
releases
README
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
Top issues
#21Revamp the memory system4 comments · 2025-08-26#715No answers or file launching; startup log incomplete (Windows)2 comments · 2026-09-22#701No default microphone found; chat model ID unclear (Windows)2 comments · 2026-09-20#340DirectML/AMD GPU acceleration support (Windows, v1.33.0)2 comments · 2026-05-03#172Dictation support on macOS 26+ (Tahoe)2 comments · 2026-04-10#91Evaluate Moonshine as alternative STT backend2 comments · 2026-03-22#1225failed1 comments · 2026-11-16#1220❌ Failed to load Whisper model: mkl_malloc: failed to allocate memory1 comments · 2026-11-14
Discussions
#987Accessibility error1 comments · 2026-10-11#650the requirments menu is gone and the next and back buttons on the first page1 comments · 2026-09-06#620stuck in this interface1 comments · 2026-08-19#609serious0 comments · 2026-08-15#604virus detected1 comments · 2026-08-14#519i know it sounds noob but i am not able to run on my laptop0 comments · 2026-07-19#329Русификатор1 comments · 2026-05-03#315Jarvis4 comments · 2026-05-01
Latest release
v2.9.0 v2.9.0 2026-11-122.9.0 (2026-11-12) ✨ Features add bounded local document search (672) (8379677) make background tasks opt-in (1179) (990dc34) 🐛 Bug Fixes bound memory used by local file previews (1176) (4c49b9c) close MCP logs when connection setup fails (1173) (00e977d) complete native tool-call batches within the reply budget (1177) (94f77b9) honour configured MCP server paths (1172) (318d915) keep background tasks queued until conversation admission (1178) (977ffd5) keep setup independent of macOS system artwork (1174) (deb19e8) pin direct search page connections to validated addresses (12