jarvis: A private, local-first AI assistant with voice and text chat.
What problem it solves
People often want an assistant that can participate in ongoing conversations, remember personal context, and use tools without requiring a cloud AI service. Jarvis addresses this with local-first voice and text interaction, personal memory, optional connected tools, and a setup process for locally controlled models.
Key features
Conversation-aware voice assistance — Jarvis maintains a temporary rolling transcript of nearby speech so it can join an ongoing conversation using recent context.
Source: README
Personal memory — Conversation history, preferences, plans, a local diary, and a knowledge graph remain on the computer and can be explored through the Memory Viewer.
Source: README
Built-in and connected tools — Built-in capabilities include web search, weather, time, screenshot OCR, file access, document search, nutrition tracking, and optional location awareness. MCP servers can add browser automation, smart-home controls, and other integrations.
Source: README, docs
Voice dictation and text chat — A hold-to-record hotkey can transcribe speech and paste it into other applications, while the companion chat provides silent text replies that share the voice conversation and memory.
Source: README
Guided local setup — The setup wizard helps users select speech recognition and a local model server, with settings for models, tools, voices, and features. It supports Ollama and OpenAI-compatible servers such as LM Studio, oMLX, or llama.cpp.
Source: README, scripts
Who it may suit
Inference: This project may suit people who want voice and text interaction with local models, control over personal conversation memory, and optional MCP integrations on macOS, Windows, or Linux.
Topics to discuss
Which local model-server and speech-recognition setups provide the most useful balance for different machines?
How should optional local document search balance usefulness with privacy and resource limits?
Which MCP integrations would be most valuable for everyday voice-assisted workflows?
Written by ReadmeX AI from the project's README, source and public GitHub data; it may contain mistakes.
Read the original README https://github.com/isair/jarvis#readme
ReadmeX opened this community for a trending project; it is not run by the project. Maintainers can claim it from the community page.
Comments
…