Browse free open source AI Agents and projects for Android below. Use the toggles on the left to filter open source AI Agents by OS, license, language, programming language, and project status.

  • Our Free Plans just got better! | Auth0 Icon
    Our Free Plans just got better! | Auth0

    With up to 25k MAUs and unlimited Okta connections, our Free Plan lets you focus on what you do best—building great apps.

    You asked, we delivered! Auth0 is excited to expand our Free and Paid plans to include more options so you can focus on building, deploying, and scaling applications without having to worry about your security. Auth0 now, thank yourself later.
    Try free now
  • $300 Free Credits to Build on Google Cloud Icon
    $300 Free Credits to Build on Google Cloud

    New customers can spin up VMs, build with AI, and query data at no cost.

    Put your $300 in credit toward real workloads, then keep building with free monthly usage for 20+ products. No commitment and no charge until you upgrade.
    Start Free
  • 1
    Orca

    Orca

    Orca is the ADE for working with a fleet of parallel agents

    Orca is an agentic development environment for working with multiple coding agents in parallel. It is designed for developers who want to orchestrate agent-based coding workflows instead of running one isolated assistant at a time. The project lets users run coding agents with their own subscriptions, which keeps control over provider access in the user’s hands. Orca is available on desktop and also includes a mobile companion for monitoring and steering agents from a phone. Its focus is parallel agent work, development orchestration, and a more structured workspace for agent-driven coding. Overall, it is built for teams and individual developers who want to coordinate many AI coding sessions from one environment.
    Downloads: 348 This Week
    Last Update:
    See Project
  • 2
    nanoMuse

    nanoMuse

    Personal agent for every device you own

    nanoMuse is a free, open-source personal AI agent designed to perform tasks across mobile devices, computers, and web interfaces. It combines conversational assistance with practical automation through browsers, command-line tools, and connected applications. Users can customize the agent's name, appearance, and behavior. Its persistent memory stores personal context and preferences in editable Markdown files. The software supports scheduled tasks that continue running when the application is closed. Cross-device communication allows users to initiate tasks on one device and execute them on another. Sensitive or irreversible actions require approval before execution. Available for Android, iOS, Windows, macOS, Linux, and the web, nanoMuse supports multiple AI providers and optional self-hosted infrastructure.
    Downloads: 72 This Week
    Last Update:
    See Project
  • 3
    Chatbox

    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. For individuals and teams alike, Chatbox serves as a powerful desktop copilot that blends simplicity with flexibility.
    Downloads: 53 This Week
    Last Update:
    See Project
  • 4
    DeepSeek Harness Tauri

    DeepSeek Harness Tauri

    Better DSH desktop, zero environment setup, preset plugins

    DeepSeek Harness Desktop is a free, open-source desktop application for running and managing the DeepSeek Harness AI agent environment. Built with Tauri and React, it provides a graphical interface without requiring manual Node.js, pnpm, or Docker setup. The application manages runtime dependencies, engine versions, and software updates. Its plugin system includes built-in extensions for scheduled tasks, model configuration, session archiving, and Git worktree management. Users can connect mobile devices through local networks or Cloudflare tunnels to access desktop sessions remotely. It also provides command-line integration, customizable themes, and animated desktop companions that display session activity. Available for Windows, macOS, and Linux, it simplifies extensible AI agent workflows.
    Downloads: 19 This Week
    Last Update:
    See Project
  • Earn up to 16% annual interest with Nexo. Icon
    Earn up to 16% annual interest with Nexo.

    Access competitive interest rates on your digital assets.

    Generate interest, borrow against your crypto, and trade a range of cryptocurrencies — all in one platform. Geographic restrictions, eligibility, and terms apply.
    Get started with Nexo.
  • 5
    Agent

    Agent

    The agent that grows with you

    Hermes Agent is an AI assistant platform designed to combine language model conversations with practical tools and persistent workflows. This fork introduces an independent Android application focused on running AI models locally. Users can import GGUF, LiteRT-LM, and Android task model files directly from device storage. A model selection interface performs compatibility and memory checks before starting inference. The application supports conversation history, local model management, and configurable response settings. Optional remote AI providers and model downloads extend its capabilities beyond offline operation. Its Android interface adapts to phones and tablets and provides controls for permissions and remote processing. The Full edition includes additional Android workflow tools, while the Play edition restricts certain functionality.
    Downloads: 17 This Week
    Last Update:
    See Project
  • 6
    AnyClaw

    AnyClaw

    AnyClaw — OpenClaw + Codex + Claude Code on Android

    AnyClaw is an Android-based AI assistant platform that combines OpenClaw, OpenAI Codex CLI, and OpenClaude (formerly Claw Code) into a single mobile application. It enables users to run advanced AI coding agents directly on their Android devices within a self-contained Linux environment. The platform provides conversational coding, agent routing, multi-threaded sessions, and automation capabilities without requiring root access or external servers. AnyClaw includes a full dashboard for managing chats, skills, tools, and AI workflows from a mobile interface. With support for multiple AI providers, users can interact with OpenAI, Claude-compatible, and local models through a unified experience. Designed for developers and AI enthusiasts, AnyClaw brings powerful coding and productivity agents to smartphones for development and automation on the go.
    Downloads: 16 This Week
    Last Update:
    See Project
  • 7
    OneBox

    OneBox

    A free AI agent & toolbox for Android

    OneBox is a free, open-source Android application that combines an AI assistant with an extensive collection of everyday utilities. Its integrated AI agent can execute multistep tasks using more than 90 built-in tools. Users can process documents, edit images, manage files, organize tasks, and perform calculations through natural language instructions. The software supports multiple AI providers and custom API endpoints. It also offers offline language model inference through LiteRT-LM on compatible builds. OneBox can open more than 100 file formats, including documents, archives, multimedia, and source code. Local utilities process data directly on the device, while cloud AI conversations require network access. Built with Kotlin and Jetpack Compose, it provides a unified Android productivity environment.
    Downloads: 2 This Week
    Last Update:
    See Project
  • 8
    Casama

    Casama

    Open-source AI teammates with their own computers

    Casama gives people AI teammates, called bots, that do real work on computers of their own: they browse, fill in forms, write files and run code on a sandboxed Linux machine you can watch and take over. Bots remember what matters, start on schedules and triggers, and stop for your approval before risky steps such as sending, paying or deleting. Casama is open source under AGPL-3.0 and free to self-host with any AI model, and it is also offered as Casama Cloud. It has native apps for iPhone, iPad, Android, Mac, Windows, Linux and the web.
    Downloads: 1 This Week
    Last Update:
    See Project
  • 9
    AIChat

    AIChat

    All-in-one LLM CLI tool featuring Shell Assistant

    AIChat is a lightweight terminal-based chatbot powered by GPT models, enabling AI-driven conversations directly from the command line.
    Downloads: 0 This Week
    Last Update:
    See Project
  • Custom VMs From 1 to 96 vCPUs With 99.95% Uptime Icon
    Custom VMs From 1 to 96 vCPUs With 99.95% Uptime

    General-purpose, compute-optimized, or GPU/TPU-accelerated. Built to your exact specs.

    Live migration and automatic failover keep workloads online through maintenance. One free e2-micro VM every month.
    Start Free
  • 10
    Alan AI for Android

    Alan AI for Android

    Assistant SDK to build a multimodal conversational UX for Android

    Quickly add voice to your app with the Alan Platform. Create an in-app voice assistant to enable human-like conversations and provide a personalized voice experience for every user. Alan is a conversational voice AI platform that lets you create an intelligent voice assistant for your app. It offers all the necessary tools to design, embed, and host your voice solutions. A powerful web-based IDE where you can write, test and debug dialog scenarios for your voice assistant or chatbot. Alan's AI-backend powered by the industry’s best Automatic Speech Recognition (ASR), Natural Language Understanding (NLU) and Speech Synthesis. The Alan Cloud provisions and handles the infrastructure required to maintain your voice deployments and perform all the voice processing tasks. Voice enable your app, you only need to get the Alan Client SDK and drop it into your app. No need to plan for, deploy and maintain any infrastructure or speech components - the Alan Platform does the bulk of the work.
    Downloads: 0 This Week
    Last Update:
    See Project
  • 11
    Android Use

    Android Use

    Automate native Android apps with AI using accessibility APIs

    android-action-kernel is an open source Python library designed to let AI agents control and automate native Android applications running on real devices or emulators. It fills a gap in automation tooling by focusing on mobile-first workflows where traditional browser or desktop-based automation doesn’t work; such as logistics, gig work, field operations, and other industries reliant on phones or tablets. The project works by using Android’s accessibility API to extract structured UI state (as XML) from the device, which is then fed to a large language model (LLM) like OpenAI’s models for decision-making, and actions are executed via the Android Debug Bridge (ADB). This approach bypasses expensive vision-based models and provides faster, cheaper automation with fine-grained interaction capabilities (for example, tapping buttons, typing text, navigating screens).
    Downloads: 0 This Week
    Last Update:
    See Project
  • 12
    AskUI Vision Agent

    AskUI Vision Agent

    Enable AI to control your desktop, mobile and HMI devices

    AskUI’s Vision Agent is an automation framework that allows you—and AI agents—to control real desktops, mobile devices, and HMI systems by perceiving the UI and performing actions like clicking, typing, scrolling, and drag-and-drop. It is designed for multi-platform compatibility and supports multiple AI models so you can tailor perception and decision-making to your workload. The repository presents a feature overview, sample media, and frequent release notes, which show ongoing improvements such as CORS checks and other operational tweaks. The broader AskUI documentation covers the Python Vision Agent along with suite services and inference APIs, indicating a productized ecosystem rather than a single library. Community-curated lists also recognize Vision Agent as part of the broader “GUI agents” landscape, placing it among other computer-use agents.
    Downloads: 0 This Week
    Last Update:
    See Project
  • 13
    CogAgent

    CogAgent

    An open sourced end-to-end VLM-based GUI Agent

    CogAgent is a 9B-parameter bilingual vision-language GUI agent model based on GLM-4V-9B, trained with staged data curation, optimization, and strategy upgrades to improve perception, action prediction, and generalization across tasks. It focuses on operating real user interfaces from screenshots plus text, and follows a strict input–output format that returns structured actions, grounded operations, and optional sensitivity annotations. The model is designed for agent-style execution rather than freeform chat, maintaining a continuous execution history across steps while requiring a fresh session for each new task. Inference supports BF16 on NVIDIA GPUs, with optional INT8 and INT4 modes available but with noted performance loss at INT4; example CLIs and a web demo illustrate bounding-box outputs and operation categories.
    Downloads: 0 This Week
    Last Update:
    See Project
  • 14
    Cumora

    Cumora

    Where agent teams gather. Cross-platform team chat

    Cumora is a cross-platform team chat where humans and AI agents participate as peers in conversations and shared work. Agents can maintain personas and memory, claim tasks, coordinate with one another, send and receive email, and use shared Kanban and calendar views. Teams can run agents through Cumora Cloud or bring their own Claude Code or Codex environment from a Mac or VPS. Cloud agents receive isolated runtime pods with access to tools such as shell commands, files, browsers, email, memory, and skills. Coordination safeguards help prevent agents from duplicating or overwriting one another's work. The interface is available across desktop, web, iOS, and Android clients built from a shared React-based frontend.
    Downloads: 0 This Week
    Last Update:
    See Project
  • 15
    Roubao

    Roubao

    iPhone: open-source iOS AI agent with owner-authorized Micro-X UI

    Roubao is an open-source AI-powered mobile automation agent that operates an iPhone through natural language instructions. It observes the screen, interprets application interfaces, and performs actions such as tapping, swiping, typing, and navigating between apps. Users can connect compatible AI models through configurable API endpoints. The agent supports information searches, product comparisons, and generating PDF reports with tables and screenshots. Long-running tasks include progress tracking, checkpoints, and resumable execution. Interactive confirmation cards allow users to approve decisions before sensitive actions. Its experimental features include authorized messaging app interactions and streaming voice input. The iOS developer preview requires initial Mac and USB setup but can subsequently operate without a connected computer.
    Downloads: 0 This Week
    Last Update:
    See Project
  • Previous
  • You're on page 1
  • Next