JiangNanGenius/floe-agent

iPad-first, open-source iOS AI Agent optimized for iOS/iPadOS, with native iPhone support and Android alpha. On-device Linux, terminal, Python/Node.js, Git and web previews; BYOK AI, Notes, Office, Canvas, CAD/3D, voice, Skill Hub and supported local models on iOS. 开源设备端 AI 智能体工作台。

What it solves

Floe Agent provides a unified, mobile-first workspace that bridges the gap between AI assistance and practical productivity. It allows users to manage complex tasks, documents, and code directly on their mobile devices without needing a desktop computer.

How it works

The app functions as a self-contained environment that integrates AI with local file management and system tools. On iOS and iPadOS, it includes a persistent Linux environment where you can run shell commands, Python, and Node.js scripts. It supports both cloud-based AI (using your own API keys) and on-device local model inference. All your files, notes, and task history are stored locally, with credentials secured in the device keychain.

Who it’s for

It is designed for power users, developers, and creative professionals who want to perform technical tasks—such as coding, document editing, and data organization—on an iPad or iPhone. It is particularly useful for those who want to maintain privacy by using their own AI provider keys or running models entirely offline.

Highlights

  • Integrated Linux Environment: Run code, packages, and background services directly on your device.
  • Versatile Document Support: Create and edit Office documents (DOCX, XLSX, PPTX) and annotate PDFs or images.
  • Flexible AI Options: Use your own cloud API keys or run supported models locally on your device.
  • Creative & Technical Tools: Includes a canvas for media organization, engineering drawing inspection, and Git-based code management.
  • Privacy-Focused: Credentials are kept in the device keychain, and cloud requests go directly to your chosen provider.

Related

  • Project
    Deyweaver/DeyWeaver

    An AI-integrated productivity tool that auto-schedules your day, breaks down large tasks, and provides burnout prediction based on work patterns.

  • Project
    AnubhavChaturvedi-GitHub/jarvis-ai-assistant

    A modular, voice-activated AI desktop assistant that combines speech recognition, LLM reasoning, image generation, and system automation to control your computer hands-free.

  • Project
    ReflexioAI/reflexio

    Reflexio is an open‑source platform that records LLM‑agent conversations, extracts user‑specific facts (profiles) and reusable procedures (playbooks) from corrections and expert replies, and makes this knowledge searchable for future agent turns. It offers a CLI, Python SDK, FastAPI backend, hybrid vector‑text search, multi‑LLM support, and integrations (OpenClaw, mem0). Benchmarked on the GDPVal suite, it reduces planning steps by up to 81 % and token usage by 72 % on top of a self‑learning Hermes agent.

  • Project
    a-agmon/rs-graph-llm

    graph-flow is a type-safe, LangGraph-inspired framework for building stateful, resumable AI agent workflows in Rust. It provides graph-based task orchestration with conditional routing, human-in-the-loop pauses, session persistence (in-memory or PostgreSQL), and tight integration with the Rig LLM ecosystem.