rat_rad

Lindroids (Does not require root access, only a terminal app and our package and web apks that we build and you can easy open and install for export) allows you to launch and export as web apk application from a container linux android application, tested on terminux, there are tons of these. Web apk does not rely on the browser, we assemble it ourselves in a decision to not rely on corporation apk signing for web apk, only accessible to chrome based browsers and samsung browser with the samsung store. The bridge is over web, and the terminal app can stay closed and run in the background when you open the application directly, which is really just a web view shell that connects to a bridge. The entire app is mapped, wether x11 or wayland, and events from the client such as touch, typing, scrolling etc. There is native android feature integration as well, older/file selectin you can choose from an injected dialogue to acess the container files and folders of the android system, camera, audio, and speakers. It is still under beta phase, and we would love developers to help us and the community to try it and hop on our discord. But the concept works and is simple and one of a kind, wich matters. No root access, no native lindroids native app, just a terminal app, our package, available via remote pacman, apk, dnf and apt, see the github page for install details and self assembled on demand web apk or exported apps not relying on browsers or corporate signing of applications via google or samsung.

AgentVoice is a bridge from your voice portal to your desired coding agent (claude code, cursor, codex) via an custom, global mcp server and more granular cli commands specific to the provider, such as new agent. For wake word detection, it uses a browser loaded, very lightweight vosk model, or a VAD model (silero VAD) instead of outsourcing the entire stream to speech to text provider. It does not actually use speech to speech models, this is a design choice, I intentionally wanted the coding agent provider to handle both user communication and actual implementation for quality responses and context, it works decently well in practice. This bridge can be run locally for testing, but also hosted, for remote accessibility from the device itself, I used tailscale for this, but other methods, such as headscale are also supported and encourage, as to reduce reliance on closed tailscale servers and have more control and privacy over your data. Interestingly, for text to speech, it was found that nearly every single modern web browser offers this for free, had to be taken advantage of. For speech to text however, I will note that just temporarily only Amazon Bedrock was supported for transcription, as this was a hobby project and it was the only provider accessible to me, but I am working on expanding support to other providers as well, such as OpenAI whisper, or Groq, and even completely self hosted for a professional setup and if you have premium hardware accessible. My dad and I both use this on a regular basis, especially where typing on tiny keyboards and interacting with the screen is not efficient, dangerous, and a regular PC is not available (e.g. driving to work and back). This is just a brief summary, for details check out the project, from experience, worth trying out, please consider contributing as well!