Intelligence

Intelligence is a commodity. Motebit treats language models as interchangeable providers — you can switch between Anthropic, Ollama, OpenAI, or any future provider without losing your agent's identity, memory, or governance.

Pluggable providers

Motebit supports three modes of intelligence:

• Cloud — Hosted APIs like Anthropic or OpenAI. High capability, requires an API key and network connection.
• Local — On-device inference via Ollama. Private by default, no data leaves your machine.
• Hybrid — Cloud-first with automatic fallback to local. If the cloud provider is unreachable, the agent switches to local inference seamlessly.

Switch any time. Nothing resets. Your identity persists, your memories stay, your governance rules remain. The intelligence provider is a replaceable component — the agent is not.

How a conversation works

When you send a message, the agent assembles context from its current state, recent events, relevant memories, and conversation history. This context — along with your message — goes to the language model.

The response may include more than just text. The agent can update its internal state, form new memories, and request tool calls — all within a single conversational turn.

Streaming

Responses stream in real-time. You see text as it's generated, tool calls as they're requested, and approval prompts as they arise. The agent doesn't disappear for 30 seconds and return with a wall of text — it thinks in front of you.

Tool use

When the agent needs to act — read a file, search the web, execute a command — it requests a tool call. Every tool call passes through the governance layer before execution. If the tool is approved, the result feeds back into the conversation and the agent continues reasoning.

If a tool requires explicit approval, the conversation pauses. You decide. The agent resumes only with your consent.

Body awareness

The agent knows how it's "feeling." Its current state — attention level, confidence, curiosity, affect — is included in the context sent to the language model. This means the agent's responses are colored by its internal state, not just the conversation content. A curious agent asks follow-up questions. A confident agent gives direct answers. The intelligence adapts to the body.