v-modal/vmodal_sdk_android

Video Search SDK for Android Kotlin. Integrate in any video app

What it solves

This SDK allows Android developers to integrate multimodal semantic search for videos and images into their applications. It solves the problem of making video libraries searchable by meaning (e.g., searching for "a red car entering the parking lot") rather than relying on simple tags or metadata.

How it works

The SDK provides a UI-free Kotlin client that handles the complex backend communication, including signed upload streams, request models, and response parsing. It integrates with Android's Storage Access Framework for secure file handling and uses Kotlin coroutines and Flow for asynchronous operations like uploads and search queries.

Who it’s for

Android developers using Kotlin, Jetpack Compose, or traditional Views who want to add visual memory and semantic search capabilities to their video-centric apps.

Highlights

  • Multimodal Search: Supports searching for specific moments in videos based on image-semantic meaning or imagery.
  • Native Android Integration: Built for Kotlin 1.9+ and Java 17, with support for CoroutineWorker and lifecycle-aware state collection.
  • UI-Free Client: The SDK handles the logic and data gateway, leaving the app developer to own the screens, themes, and design system.
  • Streaming Uploads: Supports streaming content:// URIs from the system photo picker with progress tracking and cancellation capabilities.

Related

  • Project
    v-modal/vmodal_sdk_flutter

    VModal for Flutter is a mobile‑focused SDK that adds multimodal video search and upload to Android/iOS apps built with Flutter. It provides typed Dart APIs for semantic, audio, text, and image‑based search, streaming uploads with progress and cancellation, and flexible authentication (runtime API key or short‑lived backend tokens). The SDK handles all networking and session management while leaving UI design to the developer.

  • Project
    v-modal/vmodal_sdk_smartglass

    An Android SDK that enables reliable, low-latency live video streaming from smart glasses to a cloud ingest service using a Rust-powered media core.

  • Project
    GetStream/gemini-android

    A demonstration project showing how to integrate Google's Gemini AI with the Stream Chat SDK to build an AI-powered chat application on Android.

  • Project
    livekit/python-sdks

    LiveKit’s Python SDK provides two packages (`livekit` for real‑time media participation and `livekit-api` for server‑side token and room management). It enables Python apps to join LiveKit video/audio rooms, publish/consume media, run RPC between participants, and integrate with LiveKit’s voice‑AI Agents (STT, LLM, TTS). Install via pip, generate a JWT token, connect to a room, and use the `MediaDevices` helper for microphone/speaker handling. The SDK is async, works with Python 3.9+, and is MIT‑licensed.

  • Project
    BeaconBay/ck

    ck is a Rust‑based CLI/TUI tool that builds local embeddings of source code and lets you search by meaning (semantic search) as well as by traditional regex. It supports incremental indexing, multiple embedding models, AI‑agent integration via an MCP server, and outputs results in JSON/JSONL for automation.