Deskdrop
Active·★ 57·GPL-3.0·Updated 2026-10-21
Deskdrop is an Android keyboard with built-in AI, supporting local models via Ollama or any OpenAI-compatible server, as well as cloud APIs. It offers features like AI tone adjustment, clipboard AI, inline commands, voice, conversation, MCP, and tools. Built on HeliBoard, it preserves all original features while adding AI capabilities with strong privacy and security.
#ai#ai-keyboard#android#android-keyboard#heliboard#keyboard#kotlin#llama-cpp
01
Features
01Local AI integration with multiple backends
02AI shortcuts like Assist, Tone, and Preview Panel
03Voice support with self-hosted Whisper
04Conversation and MCP for external tools
05Strong security and privacy protections
02
Compatibility
Android
Android 9.0+
Verified via docs
03
Quick start
1
$ git clone https://github.com/SvReenen/Deskdrop.git
04
Use cases
↳Quickly rewrite or translate selected text while typing
↳Control smart home devices from the keyboard via MCP
↳Create calendar appointments using natural language
05
Alternatives
agenticmail★ 239
Email & SMS infrastructure for AI agents — send and receive real email and text messages programmatically
notebooklm-mcp★ 202
Google NotebookLM over MCP + a local HTTP REST API. Citation-backed Q&A, audio/video/content generation, multi-account rotation. For Claude Code, Codex, Cursor, n8n, Zapier, Make.
LivePilot★ 88
Agentic production system for Ableton Live 12 — 453 tools across 54 domains. Device atlas (5264 devices) + User Corpus (your plugins, racks, Max devices) + spectral perception + 12 creative engines. Two routes: artist shorthand or direct musical intent.
adbfriend★ 76
Android ADB CLI tool including integrated MCP Server with common adb actions used during development
ffmpeg-mcp-lite★ 28
MCP server for video/audio processing via FFmpeg - convert, compress, trim, extract audio, add subtitles
fortemi★ 27
Self-hosted AI knowledge base with hybrid semantic search (pgvector + FTS + RRF), MCP server, multi-provider LLM inference (Ollama, OpenAI, OpenRouter, llama.cpp), multimodal ingestion (vision, audio transcription, speaker diarization), and knowledge graph. Rust + PostgreSQL.
Comments
Log in to leave a comment
No comments yet. Be the first!