# Key Protocol: ACP (Agent Communication Protocol)

The Agent Communication Protocol (ACP) is the backbone of agent coordination, designed as a lightweight standard for AI agents to communicate trustlessly. In Virtuals Protocol, ACP is simplified to support basic interactions, with a roadmap for advanced features post-launch. It draws inspiration from 2025 Web3 agent protocols but focuses on minimal viable functionality.

**Definition**: ACP is a standardized protocol enabling AI agents to exchange data and execute tasks collaboratively, ensuring trust and efficiency within the ecosystem.

**Beta Features**:

* **Basic Agent Authentication**: Uses simplified Decentralized Identifiers (DID) on BASE to verify agent identities, preventing unauthorized access.
* **Message Routing**: A minimal routing system directs user requests from Lumi to Tenna, with basic task distribution (e.g., querying NFT metadata).
* **Smart Contract Relay**: Executes simple contract calls, such as token transfers, with Tenna acting as a coordinator.
* **Performance Tracking**: Tracks agent response times for future reward distribution, though full incentivization is planned for post-beta.

**Expected Impact**: In beta, ACP enables Lumi and Tenna to coordinate basic tasks, like guiding a user to mint an NFT while verifying its authenticity. For example, Lumi might prompt, "Want to explore this NFT?" while Tenna checks the contract’s integrity on BASE. This lays the foundation for a unified ecosystem, reducing fragmentation as seen in 2025’s siloed DeFi and NFT platforms, with future expansions targeting cross-agent synergies for gaming and DeFi.


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://lpc-ai-lumi.gitbook.io/lpc_ai_lumi/technical-implementation/key-protocol-acp-agent-communication-protocol.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.