System context

Eigin at the system level. For platform specifics, see iOS.

The pieces

flowchart LR
    User["<b>User</b>"]

    subgraph Device["User device"]
        Chat["<b>Chat</b><br/>messages, input,<br/>interaction modes"]
        Agent["<b>Agent</b><br/>identity, knowledge,<br/>chats, skills, intents"]
        Gatekeeper["<b>Gatekeeper</b><br/>per-turn context<br/>+ pre/post-processing"]
        Storage["<b>Storage</b><br/>chats, knowledge,<br/>intents, settings"]
        Voice["<b>Voice</b><br/>dictation, TTS,<br/>live call"]
        OS["<b>OS APIs</b><br/>calendar, reminders,<br/>location, microphone"]
        ToolsMCP["<b>Tools & MCP</b><br/>built-in tools<br/>+ MCP clients"]
        LocalModel["<b>Local model</b><br/>on-device,<br/>hardware accelerated"]
    end

    CloudModel["<b>Cloud models</b><br/>Eigin Relay, OpenAI, Anthropic, Google, Mistral, etc."]
    Relay["<b>Eigin Relay</b><br/>(optional)"]
    MCPServers["<b>MCP servers</b><br/>third-party"]

    User --- Chat
    Chat --- Voice
    Chat --- Agent
    Chat --- Storage
    Voice -.- OS -.- ToolsMCP
    Storage --- Agent
    Agent --- ToolsMCP
    Agent --- Gatekeeper
    Gatekeeper --- LocalModel
    Gatekeeper --- CloudModel
    ToolsMCP --- Relay
    ToolsMCP --- MCPServers

    classDef eigin min-width:160px
    class Chat,Agent,Gatekeeper,Storage,Voice,ToolsMCP,LocalModel eigin

Chat

Where the user meets the agent: a persistent sequence of messages, typed or dictated. Chats live in storage and can be grouped into spaces. See Conversation.

Agent

A persistent AI personality with its own identity, knowledge, history, and goals. One agent runs per device. See The Agent.

Sits between the agent and the provider. Hydrates each turn with dynamic context (skills, intents, interaction mode, space, hints) and is the seam for future input/output safety work. See The gatekeeper.

Storage

Chats, knowledge, intents, settings, and provider config live on the device.

Voice

On-device speech recognition, text-to-speech, and a half-duplex live call mode. See Voice.

Tools and MCP

How the agent acts: built-in tools that integrate with the OS and internet, plus MCP clients for external servers. Both flow through the same permission model. See Tools and MCP servers.

Inference providers

The agent calls one of two provider kinds:

Cloud: remote inference through Eigin Relay or any OpenAI-compatible API.
Local: a hardware-accelerated on-device model. No network required.

See Inference providers.

Eigin Relay

Eigin's optional connectivity service and AI inference proxy, for features that need server-side keys the app can't ship. See Eigin Relay.

Eigin Docs