cogwheel0/conduit

Native iOS and Android client for Open WebUI, direct OpenAI-compatible, Ollama, and Hermes agents.

What it solves

Conduit is a native mobile client designed to bridge the gap between desktop-centric AI interfaces and mobile usage. It solves common mobile issues such as authentication failures behind reverse proxies, streaming responses that drop when an app backgrounds, and the lack of-native mobile integration (like home screen widgets and share-sheet ingestion).

How it works

Built with Flutter, Conduit acts as a frontend that connects to various AI backends. It supports several connection methods:

  • Open WebUI: Connects to self-hosted servers for full feature access (chats, folders, tools, etc.).
  • Direct: Connects directly to OpenAI-compatible endpoints, Ollama, or OpenRouter without needing a separate account.
  • Apple Intelligence: Integrates with Apple's local SystemLanguageModel (iOS 26+) and Private Cloud Compute (iOS 27+).
  • Hermes Agent: Connects to self-hosted Hermes servers for agentic workflows and scheduled tasks.

Who it’s for

Users who self-host their own AI models or use various API providers and want a high-performance, native mobile experience with strong privacy controls and support for complex authentication paths.

Highlights

  • Native Mobile Experience: Uses Flutter for smooth rendering of LaTeX, Mermaid diagrams, and syntax-highlighted code blocks.
  • Robust Authentication: Supports LDAP, SSO, OAuth, and various reverse proxies like Authelia and Cloudflare Tunnel.
  • Privacy-First: No developer-operated backend; data flows directly from the device to the configured server.
  • Mobile Integration: Includes home screen widgets, voice-call mode, and share-sheet ingestion for both iOS and Android.
  • Multimodal Support: Handles image and audio attachments, as well as multimodal prompts.

Related

  • Project
    open-webui/open-webui

    Open WebUI is an open‑source, self‑hosted web interface for LLMs that works with any OpenAI‑compatible API and with local Ollama models. It provides a rich UI (chat, notes, channels, calendar, voice/video, image generation), extensible plugin system, RBAC, multi‑model support, built‑in RAG (vector DBs, web search), an “Open Terminal” for agents to run code, and enterprise features like LDAP/SSO, SCIM provisioning, and observability. Install via pip, Docker (CPU/GPU, bundled Ollama), or Kubernetes. The ecosystem includes a desktop app, a mobile‑first coding agent, and tools for syncing external knowledge bases.

  • Project
    Amm1rr/WebAI-to-API

    WebAI‑to‑API is a self‑hosted bridge that runs Google Gemini (via web API or a Playwright‑driven browser) and exposes it through OpenAI‑compatible endpoints, with a local dashboard and Docker support.

  • Project
    uzairansaruzi/hermex

    Hermex is a free native iOS app that lets you control a self‑hosted Hermes‑webui AI agent from your iPhone. It provides real‑time chat, session history, model switching, task and skill management, and file‑system browsing, all while keeping the backend (model inference, data, tools) on your own hardware.

  • Project
    Eynzof/Hermes-CN-Desktop

    A native Windows and macOS desktop client for Hermes Agent, providing a streamlined interface and bundled runtime for managing AI agents.

  • Project
    icebear0828/codex-proxy

    Codex Proxy is a local service that converts Codex Desktop’s API into standard OpenAI/Anthropic/Gemini/Ollama endpoints, letting any AI‑coding client use Codex models. It offers multi‑account management, smart routing, TLS fingerprinting, Docker/desktop/npm installers, and supports image generation.