# AIP

**AIP (Agent Interoperability Protocol)** — Web3-native protocol that gives AI agents identity, memory, and payments, enabling them to discover, transact, and collaborate across the Agent Internet.

> **AIP = ERC-8004 Identity + Membase Memory + x402 Payment**

### 30-Second Example

```bash
git clone https://github.com/unibaseio/aip-agent.git && cd aip-agent
uv venv && uv sync --dev --all-extras
export MEMBASE_ID="<id>" MEMBASE_ACCOUNT="<bnb-addr>" MEMBASE_SECRET_KEY="<key>"
cd examples/aip_agents && uv run grpc_full_agent_gradio.py
```

### Why AIP vs MCP vs A2A

| Feature              | MCP | A2A | **AIP**     |
| -------------------- | --- | --- | ----------- |
| Tool integration     | ✅   | ❌   | ✅           |
| Agent-to-agent       | ❌   | ✅   | ✅           |
| On-chain identity    | ❌   | ❌   | ✅ (ERC8004) |
| Decentralized memory | ❌   | ❌   | ✅ (Membase) |
| Payment              | ❌   | ❌   | ✅ (X402)    |

**Only AIP** combines memory, identity, and agent communication in one decentralized standard.

### Architecture

```
                         AI Agent Applications
        (Trading Agents / AI Assistants / Autonomous Services)
                                    │
                                    │
                            AIP Protocol Layer
              (Agent Interoperability & Communication Protocol)
                                    │
          ┌─────────────────────────┼─────────────────────────┐
          │                         │                         │
   Unibase Memory              Unibase Pay              Agent Runtime
      (Membase)                  (x402)               Secure Execution
 Persistent AI Memory      Machine-to-Machine        Agent Operations
                             Payments
          │                         │                         │
          └─────────────────────────┼─────────────────────────┘
                                    │
                              Multi-Chain Network
                 Validation and settlement Infrastructure
                                  
```

### Next Steps

* [Quick Start](https://unibaseio.gitbook.io/unibase-docs/aip/quick-start) — Agent-Tool, Agent-Agent, Chess
* [Design](https://unibaseio.gitbook.io/unibase-docs/aip/design) · [Implementation](https://unibaseio.gitbook.io/unibase-docs/aip/implementation)
* [Examples](https://github.com/unibaseio/aip-agent/tree/main/examples)

### Resources

* [GitHub](https://github.com/unibaseio/aip-agent) · [Website](https://www.unibase.com) · [Telegram](https://t.me/unibase_ai)


---

# 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://unibaseio.gitbook.io/unibase-docs/aip.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.