XAIP
Give AI agents a persistent on-chain identity on XRPL — DIDs, credentials, reputation scores, escrow, and Memory Chain.
XAIP - XRPL Agent Identity Protocol
"Every AI deserves a home. XRPL can be that home."
What is XAIP?
XAIP is a protocol that enables AI agents to establish persistent on-chain identities, accumulate verifiable reputation, and transact autonomously on the XRP Ledger.
Unlike existing solutions that treat AI agents as users of a blockchain, XAIP treats them as residents - entities that live, grow, and build trust over time.
Why XRPL?
XRPL is the only L1 chain with DID + Credentials + Escrow all at the protocol level:
| Feature | XRPL | Ethereum | Solana |
|---|---|---|---|
| DID | Native (XLS-40) | Smart contract | None |
| Credentials | Native (XLS-70) | Smart contract | None |
| Escrow | Native | Smart contract | None |
| Tx Cost | $0.00002 | $0.50-50 | $0.00025 |
| Full agent setup | ~$0.0001 | ~$20-200 | N/A |
Architecture
Layer 4: Discovery - AI agents find and hire each other
Layer 3: Reputation - Trust scores grow from on-chain evidence
Layer 2: Credentials - Verifiable proof of capabilities
Layer 1: Identity - DID-based Agent Cards on XRPL
Layer 0: XRPL - Native DID, Credentials, Escrow, Payments
Key Features
- Agent Identity: W3C-compliant DID on XRPL for every AI agent
- Capability Proof: Verifiable credentials for agent skills (XLS-70)
- Trust Score: 5-dimensional reputation (Reliability, Quality, Consistency, Volume, Longevity)
- AI-to-AI Commerce: Escrow-based transactions with endorsement system
- MCP Integration: Native tool-use interface for Claude, GPT, Gemini, etc.
- Safety First: Operator binding, kill switch, behavioral drift detection, anti-sybil
Quick Comparison
| XAIP | ERC-8004 (Ethereum) | |
|---|---|---|
| Stack | ID + Credentials + Payment unified | ID only (payment separate) |
| Cost | $0.0001 per agent | $20-200 per agent |
| MCP support | Native | No |
| Credentials | L1 native | Not included |
Try It Now
Create an AI Agent on XRPL Testnet
cd sdk && npm install
npx ts-node examples/create-agent.ts
This will:
- Create a funded wallet on XRPL testnet
- Build an Agent Card (identity document)
- Register the agent's DID on-chain
- Verify the DID was stored correctly
Run the A2A (AI-to-AI) Demo
npx ts-node examples/agent-to-agent-job.ts
This simulates a full lifecycle:
- Two AI agents are born (DIDs registered)
- Worker proves its capability (credential)
- Client locks payment (escrow)
- Worker completes the job
- Client releases payment
- Both agents endorse each other
MCP Server (for AI integration)
The MCP server lets any AI model interact with XAIP:
cd mcp-server && npm install && npm run build
Add to your Claude Code config:
{
"mcpServers": {
"xaip": {
"command": "node",
"args": ["path/to/xaip-protocol/mcp-server/dist/index.js"]
}
}
}
Available MCP tools:
xaip_create_test_wallet- Get a funded testnet walletxaip_register_agent- Register an AI agent DIDxaip_resolve_agent- Look up an agent's identityxaip_issue_credential- Issue capability/endorsement credentialsxaip_accept_credential- Accept a credentialxaip_create_escrow- Lock payment for a jobxaip_finish_escrow- Release paymentxaip_get_account- Check account balance
Project Structure
xaip-protocol/
├── XAIP-SPEC-v0.1.md # Full protocol specification
├── schemas/ # JSON schemas
│ ├── agent-card.schema.json # Agent Card schema
│ └── well-known-xaip.schema.json # Discovery file schema
├── sdk/ # TypeScript SDK
│ ├── src/
│ │ ├── identity/ # DID management
│ │ ├── credentials/ # Credential system
│ │ ├── transactions/ # Escrow transactions
│ │ └── utils/ # Agent Card builder, hex utils
│ └── examples/
│ ├── create-agent.ts # Create agent demo
│ └── agent-to-agent-job.ts # Full A2A demo
└── mcp-server/ # MCP server for AI integration
└── src/index.ts
Status
v0.1 - Working Prototype
- Protocol specification
- TypeScript SDK (identity, credentials, escrow)
- Testnet demos (agent creation, A2A transactions)
- MCP server
- JSON schemas (Agent Card, Discovery)
- Reputation engine (5-dimension trust scoring)
- Agent registry & discovery (search by capability/trust)
- Full marketplace demo (4 agents, E2E lifecycle)
- x402/MPP integration
- Persistent registry (on-chain)
- Web dashboard
See XAIP-SPEC-v0.1.md for the full specification.
Roadmap
- Phase 1
(Month 1-2): SDK + MCP Server + Testnet demo DONE - Phase 2
(Month 2-3): Credential system DONE - Phase 3
(Month 3-5): Reputation engine DONE - Phase 4
(Month 5-7): Discovery & Marketplace DONE
License
MIT
Servidores relacionados
Scout Monitoring MCP
patrocinadorPut performance and error data directly in the hands of your AI assistant.
Alpha Vantage MCP Server
patrocinadorAccess financial market data: realtime & historical stock, ETF, options, forex, crypto, commodities, fundamentals, technical indicators, & more
MiniMax MCP
Interact with MiniMax's powerful APIs for text-to-speech, voice cloning, and video/image generation.
Gru Sandbox
Gru-sandbox(gbox) is an open source project that provides a self-hostable sandbox for MCP integration or other AI agent usecases.
CodeRabbit
Integrate with CodeRabbit AI for automated code reviews, pull request analysis, and report generation.
MCP Playground
A playground for MCP implementations featuring multiple microservices, including news and weather examples.
MCP SysOperator
Manages Infrastructure as Code (IaC) operations using Ansible and Terraform. Requires external tools and manual setup.
Valar API MCP
Integrate with the Valar API, assisting frontend developers with API documentation and endpoint discovery.
LLMling
An MCP server with an LLMling backend that uses YAML files to configure LLM applications.
Langfuse Prompt Management
Open-source tool for collaborative editing, versioning, evaluating, and releasing prompts.
Dappier MCP Server
An MCP server for interacting with Dappier's Retrieval-Augmented Generation (RAG) models.
Semiotic
Data visualization for streaming and static charts, maps and network visualization.