Akshayykadam/PixelBoard

Unlock Google 11's Gemini "Rambler" Natural Voice Dictation & AI Writing Tools on ANY Android phone. No root required.

What it solves

PixelBoard provides an enhanced version of the Gboard keyboard that unlocks advanced AI features—such as natural voice dictation and AI-powered writing assistance—on a wider range of Android devices. It also removes promotional bloatware and allows users to run these features alongside their existing keyboard without requiring root access.

How it works

The project uses bytecode-level modifications and runtime flag management to enable hidden or restricted Google keyboard features. It hooks into Gboard's internal settings and service classes to force-enable capabilities like the "Rambler" voice model, inline spell-checker chips, and AI writing tools. By using a unique package ID (com.akshaykadam.pixelboard), it functions as a standalone application that coexists with the stock keyboard.

Who it’s for

This project is for Android users who want to access premium Pixel-exclusive keyboard features, such as advanced AI-driven voice typing and grammar correction, on non-Pixel devices or older hardware. It is also for power users who prefer a cleaner, bloat-free keyboard interface with granular control over AI inference backends.

Highlights

  • Rambler Voice Typing: Uses a state-of-the-art model that filters out filler words, fixes self-corrections, and handles auto-punctuation.
  • AI Writing Assistant: Provides one-tap proofreading and tone adjustment (Professional, Casual, Concise, Emotive) directly within the keyboard.
  • No Root Required: Installs as a side-by-side application, ensuring system stability and easy setup.
  • Advanced Customization: Offers toggles for Material 3 rounded keys, custom emoji drawer layouts, and selection of on-device AI inference backends (where supported).
  • Instant Activation: Features hot-reloading for settings, meaning changes take effect immediately without requiring app or device restarts.

Related

  • Project
    YOURSJEYO/claude-switcher

    Claude Switcher is a native macOS (and beta Windows/Linux) app that audits 14 network/system fingerprints before launching Claude AI. If any check fails, the app refuses to start, and a background kill‑switch instantly terminates Claude on tunnel loss. It includes a hand‑crafted STUN probe for WebRTC leaks, per‑account snapshot isolation, and self‑healing configuration.

  • Project
    voidful/hung-yi-lee-skill

    A structured knowledge system that distills Professor Hung-yi Lee's teaching style and AI expertise into a knowledge graph and linguistic framework for AI assistants.

  • Project
    apecloud/ApeRAG

    ApeRAG is an open‑source, production‑ready Retrieval‑Augmented Generation platform that combines vector, full‑text, graph, summary and vision search with AI agents. It provides Docker‑Compose quick‑start, full Kubernetes/Helm deployment, MCP integration, and optional advanced document parsing (MinerU). Ideal for building enterprise knowledge‑base assistants, multimodal document search, and AI‑driven support bots.

  • Project
    DrJonaC/Pensieve

    A local-first workspace for managing structured AI memory, allowing users to inspect, edit, and govern the data used by AI assistants to personalize responses.