TL;DR: jev-chat sits on top of your messaging apps by leveraging accessibility services on Android, on-device OCR on desktop, and custom keyboards on iOS to intercept and read chat windows. Instead of generating immediate responses, it runs a judgment model to evaluate the sender's intent and conversation risk.
Best for: Developers and power users seeking an open-source assistant to manage heavy chat loads across multiple devices.
Repository snapshot: ⭐ 8 373 stars · 🍴 1 335 forks · Kotlin · MIT
Daily picks: Follow GitHub Open Source on Telegram
What it is
Jev Chat Jarvis is an open-source chat decision assistant written in Kotlin. It integrates across Android, Windows, macOS, and iOS to read incoming messages, judge intent, and draft ranked reply options directly into your text input box while keeping you in full control of the final send action.
How it works
The project sits on top of your messaging apps using platform-specific mechanisms. On Android, it leverages accessibility services; on desktop, it uses on-device optical character recognition; and on iOS, it relies on custom keyboards. Rather than sending immediate automated replies, it routes data through lightweight local or configured models to evaluate sender intent and conversation risk before populating ranked options.
Key features
- Evaluate message intent and risk levels before drafting responses
- Rank and check generated replies against initial conversation judgments
- Native overlays and integrations across Android, Windows, macOS, and iOS
- Direct API requests to your own configured model provider
- Operation via accessibility services or local desktop OCR without server logging
Getting started
To run and build the project locally, clone the repository from GitHub and open it in your preferred Kotlin-compatible development environment like Android Studio or IntelliJ IDEA. Ensure you have your own API keys configured for your desired model provider before building for your target platform.
When not to use it
Skip this project if you are concerned about platform terms of service violations related to accessibility services, screen reading, or UI automation on mobile and desktop operating systems.
Discuss
Which chat app would you want this assistant running on first?
Curated from the repository README and metadata. No hands-on test is claimed; evaluate it in a sandbox before production use.
Top comments (0)