Search Results for "device" - Page 2
Sort By:
Showing 107 open source projects for "device"
View related business solutions-
Build Agents and Models on One PlatformGemini Enterprise Agent Platform is Google Cloud's comprehensive platform for developers to build, scale, govern, and optimize agents and models. Choose from Google's most advanced models and third-party models like Anthropic's Claude Model Family.
-
$300 Free Credits to Build on Google CloudStart your next project with $300 in free Google Cloud credit. Spin up VMs, run containers, query petabytes in BigQuery, or build agents with Gemini Enterprise Agent Platform. Once your credits are used, keep building with 20+ always-free tier products including Compute Engine, Cloud Storage, GKE, and Cloud Run functions. No commitment required—just sign up and start building.
-
1
Codex Mobile
Run Codex Mobile Anywhere: Linux, Windows, or Termux on Android
...It is designed to let users run a Codex-style UI on Linux, Windows, or Termux-powered Android setups. The project starts a local web server with one command, then lets the user open the interface from the same machine, a LAN device, or another reachable connection. It can also create a Cloudflare tunnel by default, making remote access easier when the local setup allows it. Codex Mobile is useful for developers who want to control coding-agent sessions from a phone, tablet, remote browser, or nonstandard environment. Its main value is making Codex app workflows more portable, accessible, and usable beyond a traditional desktop terminal. -
2
Spacedrive
Spacedrive is an open source cross-platform file explorer
Spacedrive is an open‑source cross‑platform file manager powered by a virtual distributed filesystem (VDFS) written in Rust, allowing users to organize files across multiple devices—cloud services, offline drives—into a unified personal distributed cloud. It emphasizes security, interoperability, and ownership of personal data. Organize files across many devices in one place. From cloud services to offline hard drives, Spacedrive combines the storage capacity and processing power of your... -
3
Gemma Chat
Local AI chat + coding agent for Apple Silicon, powered by Gemma 4
Gemma Chat is a local-first AI chat and coding assistant designed to run fully on-device, particularly optimized for Apple Silicon machines. It leverages Google’s Gemma family of lightweight language models, which are built on the same underlying technology as Gemini and designed for efficient local inference and reasoning tasks. The project enables users to interact with AI through a chat interface while also supporting code generation and editing workflows. -
4
ChatLab
Local-first AI chat analysis tool for insights from conversation data
...By combining a flexible SQL engine with AI agents, the tool allows users to query, summarize, and explore conversation patterns in a more interactive and intelligent way. ChatLab emphasizes a local-first approach, meaning all chat data is processed and stored on the user’s device rather than being uploaded to external servers. It supports large-scale datasets through streaming parsing and multi-worker processing, allowing it to handle millions of messages efficiently. ChatLab also includes visualization features that present trends, activity patterns, and interaction metrics in a clear and accessible format. -
MongoDB Atlas runs apps anywhereMongoDB Atlas gives you the freedom to build and run modern applications anywhere—across AWS, Azure, and Google Cloud. With global availability in over 115 regions, Atlas lets you deploy close to your users, meet compliance needs, and scale with confidence across any geography.
-
5
Materialize
Materialize, a web framework based on Material Design
...Components should be useable by mobile devices and easily accessible by keyboard too. Try it out. User-centric approach with established design principles mainly from Google's Material guidelines. Our Components should work on nearly every device with a monitor. User-centric approach with many members all around the world, which helps bring Materialize forward and improve usability for everyone on the web. You can be a part too. -
6
CallMe
Minimal plugin that lets Claude Code call you on the phone
CallMe is a minimalist plugin for Claude Code that bridges computational tasks with real-world alerts by letting the AI call your phone, smartwatch, or even a landline when an operation finishes, gets stuck, or needs a user decision. It is designed to let users start a long-running task, leave their device, and then be notified in a natural way with a phone call instead of second-guessing progress in the console. The plugin uses a local MCP server alongside a webhook tunnel (typically via ngrok) to connect with voice providers like Telnyx or Twilio for outbound calls, with prompts and responses flowing between Claude Code and the user’s voice device. -
7
Notifee Notifications
A feature rich notifications library for React Native
Notifee enables developers to rapidly build rich notifications with a simple API interface, whilst taking care of complex problems such as scheduling, background tasks, device API compatibility & more. Manage the applications channels (Android) and categories (iOS), allowing you to customize how notifications behave when they are displayed on the device. Present & handle quick actions alongside your notification content. Actions can be handled in the background or foreground with JavaScript code! Notifee supports many notification styles such as Big Text, Big Picture, Inbox & Messaging on Android and attachments & custom summary text on iOS. ... -
8
Happy Coder
Mobile and Web client for Codex and Claude Code, with realtime voice
Happy is an open-source, cross-platform mobile and web client designed to bring powerful AI coding agents such as Claude Code and Codex to your fingertips no matter where you are. At its core, Happy wraps existing AI coding tools with a unified interface, providing real-time voice interactions, encrypted communication, and seamless device switching between desktop and mobile. You can start a coding session locally through the Happy CLI or connect from a phone or browser, allowing developers to inspect, interact with, and guide the AI as it generates, tests, or explains code. The project includes components like a dedicated backend server for encrypted sync, a rich front-end experience across web and native apps, and support for push notifications when your coding agent encounters permission requests or errors. ... -
9
QMD
mini cli search engine for your docs, knowledge bases, etc.
QMD is a powerful and lightweight command-line tool that acts as an on-device search engine for your personal knowledge base, allowing you to index and search files like Markdown notes, meeting transcripts, technical documentation, and other text collections without depending on cloud services. Designed to keep all search activity local, it combines classic full-text search techniques with modern semantic features such as vector similarity and hybrid ranking so that queries return not just literal matches but conceptually relevant results. ... -
Error to trace to log to deploy. One click. No SSH.AppSignal links every error to the trace, the trace to the log, the log to the deploy that shipped it.
-
10
FingerprintJS
Browser fingerprinting library
...For example, when 2 different users send requests using identical (i.e. same version, same vendor, same platform), browsers, FingerprintJS will not be able to tell these two browsers apart, primarily because the attribitutes from these browsers will be identical. Fingerprint Identification is a closed-source, commercial device identification product designed for fraud detection, device identification, marketing attribution, and analytics. -
11
react-native-iap
react-native native module for In App Purchase.
react-native-iap will help you access the In-App purchases capabilities of your device on iOS, and Android (Play Store and Amazon). In order to initialize the native modules, call initConnection() early in the lifecycle of your application. This should be done at a top-level component as the library caches the native connection. Initializing just before you needed is discouraged as it incurs on a performance hit. Calling this method multiple times without ending the previous connection will result in an error. ... -
12
Chatbox
The Ultimate AI Copilot on Your Desktop
Chatbox is a cross-platform desktop AI client designed to give you a fast, polished, and private way to work with modern language models. It runs locally on Windows, macOS, and Linux, keeping your conversations and data stored on your own device. Chatbox acts as a unified interface for popular LLMs like ChatGPT, Claude, Gemini, and local models via Ollama, making it easy to switch providers without changing tools. Built with an ergonomic UI, it’s optimized for long sessions, prompt experimentation, and everyday productivity. The app supports rich formatting, streaming responses, and advanced prompting to help you get clearer, more useful outputs. ... -
13
Operit AI
Powerful Android AI agent with tools, automation, and Linux shell
...It integrates deep system-level capabilities with a wide range of tools, allowing the AI to perform real tasks such as file management, automation, and system control directly on the device. A standout aspect of the project is its built-in Ubuntu 24 environment, which enables users to run Linux commands, scripts, and development tools in a mobile context. Operit supports both local and remote AI models, including offline execution through frameworks like llama.cpp and MNN, helping preserve user privacy while maintaining flexibility. ... -
14
dataline
AI data analysis and visualization on CSV, Postgres, MySQL, Snowflake
...Once connected, users can generate tables, charts, and reports automatically based on queries produced by the AI engine. The platform is designed with a privacy-first architecture that stores data locally on the user’s device rather than sending it to external cloud services by default. It can also hide sensitive data from language models during processing, ensuring that only necessary metadata is used for query generation. -
15
Popcorn Time
Your favorite platforms, your shows, your movies-ready when you are
Popcorn Time is an open-source, cross-platform application designed to bring movies, TV shows, and media content into a single, unified viewing experience. Built with modern technologies like Tauri, Rust, and React, it offers a fast and lightweight interface across desktop, mobile, and TV devices. The project is a complete rebuild with a focus on transparency, community-driven development, and improved safety. Unlike traditional streaming directories, Popcorn Time aims to provide a more... -
16
WechatOnCloud
Cloud Micro WOC, Cloud WeChat, Free Connection
...It allows multiple independent WeChat instances to be managed from one web panel. Each instance works as a separate WeChat session that authorized users can access through a browser. The project is designed for cross-device message access, multi-user sharing, and centralized session management without modifying the official WeChat client. It is especially useful for teams, families, or technical users who want browser-based access to WeChat from a private server environment. Its main value is turning WeChat into a locally hosted, multi-instance service that can be managed and shared more flexibly. -
17
Dyad
Free, local, open-source AI app builder
...Deep Supabase integration means you can create UI and backend logic in one cohesive environment, while the model-agnostic architecture lets you connect to any AI, whether cloud-based (Gemini 2.5 Pro, GPT-4.1, Claude Sonnet 4) or local via Ollama, so you’re never locked in. All source code remains on your device and integrates seamlessly with your preferred IDE. A natural-language API enables powerful data queries and updates, automating tasks without leaving the chat interface. By running entirely locally, Dyad delivers maximum privacy, minimal latency, and smooth developer experiences free from cloud-based inconsistencies. -
18
PixiJS
The HTML5 Creation Engine
...PixiJS works across all devices and is incredibly fast. If you want to create exceptional experiences without having to deal with dense, low level code, browser inconsistencies, WebGL API or device compatibility, PixiJS is for you! See some great examples and creations made with PixiJS in the official website: https://www.pixijs.com/ -
19
Basic Memory
Persistent AI memory using local Markdown knowledge graphs
...With a local-first design, your data stays private and portable, while optional cloud sync enables cross-device access. It combines simplicity with powerful indexing and search, giving you a flexible way to build long-term memory for projects, research, and workflows. -
20
T3 Code
Minimal web GUI for coding agents
...Users need to install and authenticate at least one supported provider before using it, which keeps the actual agent accounts under the user’s control. The repository includes guidance for exposing a T3 Code server to another device, such as a phone, tablet, or separate desktop app. Overall, it is an early-stage developer tool for managing AI coding agents through a lightweight, session-oriented web interface. -
21
Frigate NVR
NVR with realtime local object detection for IP cameras
Frigate is a local network video recorder designed for real-time object detection on IP camera streams using machine learning. It runs entirely on local hardware and integrates closely with Home Assistant to provide smart surveillance without relying on cloud processing. The system uses OpenCV and TensorFlow to analyze video feeds and detect objects such as people, vehicles, and animals in real time. Frigate is optimized for efficiency and supports hardware acceleration across a wide range... -
22
react-native-fast-tflite
High-performance TensorFlow Lite library for React Native
...It can load and swap TensorFlow Lite models at runtime, making it useful for apps that run multiple machine learning tasks. The project supports GPU-accelerated delegates such as CoreML, Metal, and OpenGL. It is especially useful for mobile computer vision, on-device inference, and VisionCamera-based workflows that need fast local model execution. -
23
Ollama Server
No need for Termux, you can start the Ollama service
...The application includes basic model lifecycle management such as downloading official models, uploading custom GGUF files, and controlling running instances. It also enables offline inference, allowing users to run language models entirely on-device without requiring a network connection or external infrastructure. -
24
Ito
Ito, smart dictation in every application
ito is an open‑source JavaScript library for serverless, browser‑to‑browser communication designed for use on devices with or without user input interfaces, such as IoT devices, mobile devices, tablets, and desktops, enabling peer messaging and data sharing via short passcodes and cloud‑backed pairing without an application server. -
25
Porcupine
On-device wake word detection powered by deep learning
Build always-listening yet private voice applications. Porcupine is a highly-accurate and lightweight wake word engine. It enables building always-listening voice-enabled applications. It is using deep neural networks trained in real-world environments. Compact and computationally-efficient. It is perfect for IoT. Cross-platform. Arm Cortex-M, STM32, PSoC, Arduino, and i.MX RT. Raspberry Pi, NVIDIA Jetson Nano, and BeagleBone. Android and iOS. Chrome, Safari, Firefox, and Edge. Linux...
