Agent Integration

Overview

The Cashmere Agent SDK (@cashmerelabs/cashmere-agent-sdk) turns cross-chain USDC transfers into a standard AI agent tool. Any framework that supports function calling or tool use can integrate Cashmere bridging in minutes. What agents can do:

Simulate a transfer to preview fees, duration, and route viability without executing
Execute a transfer across 16 chains (EVM, Solana, Aptos, Sui)
Query supported routes and CCTP versions programmatically

Destination minting is handled automatically by Cashmere relayers — the agent only needs to initiate the source-side burn.

Install

npm install @cashmerelabs/cashmere-agent-sdk

For LangChain integration, also install:

npm install @langchain/core

Quick Setup

import { CashmereCCTP } from '@cashmerelabs/cashmere-agent-sdk';

const cctp = new CashmereCCTP({
  evm: { privateKey: process.env.EVM_PRIVATE_KEY },
  solana: { privateKey: process.env.SOLANA_PRIVATE_KEY },
  aptos: { privateKey: process.env.APTOS_PRIVATE_KEY },
  sui: { privateKey: process.env.SUI_PRIVATE_KEY },
});

Only configure the chains your agent needs. Keys are read from environment variables and used only for in-memory transaction signing.

Simulate Before Execute

Use simulate() to let the agent preview costs before committing funds:

const sim = await cctp.simulate({
  from: 'ethereum',
  to: 'arbitrum',
  amount: '100',
});

// {
//   supported: true,
//   version: 'v2-fast',
//   estimatedDuration: '~15 seconds',
//   estimatedFee: { cashmere: '0.12 USDC', circleBurnBps: 1.3 }
// }

This calls the Gas API and Circle Iris to fetch real-time fee data without submitting any transaction.

Framework Integration

OpenAI Assistants
LangChain
crewAI
Custom Framework

Import the JSON tool schemas and pass them directly to the OpenAI API:

import { bridgeToolSchema, simulateToolSchema } from '@cashmerelabs/cashmere-agent-sdk';

const tools = [
  { type: "function", function: bridgeToolSchema },
  { type: "function", function: simulateToolSchema },
];

const response = await openai.chat.completions.create({
  model: "gpt-4",
  messages: [
    { role: "system", content: "You are a cross-chain treasury agent." },
    { role: "user", content: "Bridge 500 USDC from Ethereum to Solana" },
  ],
  tools,
});

// When the model calls cashmere_bridge or cashmere_simulate,
// parse the arguments and call cctp.transfer() or cctp.simulate()
const call = response.choices[0].message.tool_calls[0];
if (call.function.name === 'cashmere_simulate') {
  const result = await cctp.simulate(JSON.parse(call.function.arguments));
} else if (call.function.name === 'cashmere_bridge') {
  const result = await cctp.transfer(JSON.parse(call.function.arguments));
}

The schema defines two tools:

Tool	Description
`cashmere_simulate`	Preview fee, duration, route — no execution
`cashmere_bridge`	Execute a cross-chain USDC transfer

The SDK provides ready-made LangChain Tool classes:

import { CashmereCCTP } from '@cashmerelabs/cashmere-agent-sdk';
import {
  CashmereBridgeTool,
  CashmereSimulateTool,
} from '@cashmerelabs/cashmere-agent-sdk/tools/langchain';

const cctp = new CashmereCCTP({
  evm: { privateKey: process.env.EVM_PRIVATE_KEY },
});

const tools = [
  new CashmereBridgeTool(cctp),
  new CashmereSimulateTool(cctp),
];

// Use with any LangChain agent
import { createReactAgent } from '@langchain/langgraph/prebuilt';

const agent = createReactAgent({ llm: chatModel, tools });
const result = await agent.invoke({
  messages: [{ role: "user", content: "Send 200 USDC from Base to Polygon" }],
});

Both tools accept JSON string input and return JSON string output, compatible with all LangChain agent types.

crewAI uses LangChain tools natively. The same CashmereBridgeTool and CashmereSimulateTool classes work directly:

# crewAI uses LangChain tools under the hood
# In your Python crewAI setup, wrap the Node.js SDK via subprocess or HTTP

# Or use the JSON tool schemas for a Python-native approach:
cashmere_tool = {
    "name": "cashmere_bridge",
    "description": "Bridge USDC across chains via Cashmere CCTP...",
    "parameters": {
        "type": "object",
        "properties": {
            "from": {"type": "string", "description": "Source chain"},
            "to": {"type": "string", "description": "Destination chain"},
            "amount": {"type": "string", "description": "USDC amount"},
            "recipient": {"type": "string", "description": "Destination address"},
        },
        "required": ["from", "to", "amount", "recipient"],
    },
}

For TypeScript crewAI setups, use the LangChain tools directly as shown in the LangChain tab.

For any framework that supports function calling, use the raw JSON schemas:

import { bridgeToolSchema, simulateToolSchema } from '@cashmerelabs/cashmere-agent-sdk';

// bridgeToolSchema and simulateToolSchema are plain objects:
// {
//   name: "cashmere_bridge",
//   description: "...",
//   parameters: { type: "object", properties: {...}, required: [...] }
// }

// Register as tools in your framework, then dispatch:
async function handleToolCall(name: string, args: any) {
  if (name === 'cashmere_bridge') {
    return await cctp.transfer(args);
  } else if (name === 'cashmere_simulate') {
    return await cctp.simulate(args);
  }
}

Tool Schemas Reference

`cashmere_bridge`

Executes a cross-chain USDC transfer.

Parameter	Type	Required	Description
`from`	string	Yes	Source chain (e.g. `ethereum`, `arbitrum`, `solana`)
`to`	string	Yes	Destination chain
`amount`	string	Yes	USDC amount, human-readable (e.g. `"100"`)
`recipient`	string	Yes	Destination wallet address
`version`	string	No	`v1`, `v2-fast`, or `v2-norm` (auto-resolved if omitted)
`feeMode`	string	No	`native` or `stable` (default: `native`)

Returns: { txHash, explorerUrl, version, from, to }

`cashmere_simulate`

Previews a transfer without executing.

Parameter	Type	Required	Description
`from`	string	Yes	Source chain
`to`	string	Yes	Destination chain
`amount`	string	Yes	USDC amount
`version`	string	No	CCTP version preference
`feeMode`	string	No	Fee payment mode

Returns: { supported, version, estimatedDuration, estimatedFee: { cashmere, circleBurnBps } }

Supported Chains

Chain	Domain	V1	V2 Fast	V2 Norm
Ethereum	0	Y	Y	Y
Avalanche	1	Y	N	Y
Optimism	2	Y	Y	Y
Arbitrum	3	Y	Y	Y
Solana	5	Y	N	Y
Base	6	Y	Y	Y
Polygon	7	Y	N	Y
Sui	8	Y	N	N
Aptos	9	Y	N	N
Unichain	10	Y	Y	Y
Linea	11	N	Y	Y
Sonic	13	N	N	Y
Worldchain	14	N	Y	Y
Monad	15	N	N	Y
Sei	16	N	N	Y
HyperEVM	19	N	N	Y

SKILL.md (Agent Context)

The SDK ships with a SKILL.md file that provides comprehensive context for AI agents. Load it to give your agent detailed knowledge about Cashmere CCTP:

import { readFileSync } from 'fs';

const skillContext = readFileSync(
  require.resolve('@cashmerelabs/cashmere-agent-sdk/SKILL.md'),
  'utf-8',
);

// Pass as system message to your LLM
const messages = [
  { role: "system", content: skillContext },
  { role: "user", content: "What's the fastest way to bridge 1000 USDC to Solana?" },
];

The SKILL.md covers:

All contract addresses and program IDs (public, on-chain data)
Fee calculation formulas and gas API integration
Per-chain transfer patterns and ABI details
CCTP version routing rules and estimated durations

Security

Private keys are never logged, stored on disk, or sent to any API other than the chain’s own RPC for transaction submission. The Gas API only receives domain IDs and fee parameters.

Keys are provided via environment variables and used only for in-memory signing
The SDK contains zero console.log statements
All contract addresses in the SDK are public on-chain data
The .env.example file ships with empty values — never commit .env

Next Steps

Smart Contracts — per-chain contract details and ABI reference
Backend APIs — Gas API and monitoring endpoints
Contract Addresses — deployed addresses for all 16 chains
GitHub — source code and issues

Welcome

Overview

Products

Developer Resources

API Reference

Overview

Install

Quick Setup

Simulate Before Execute

Framework Integration

Tool Schemas Reference

`cashmere_bridge`

`cashmere_simulate`

Supported Chains

SKILL.md (Agent Context)

Security

Next Steps

​Overview

​Install

​Quick Setup

​Simulate Before Execute

​Framework Integration

​Tool Schemas Reference

​cashmere_bridge

​cashmere_simulate

​Supported Chains

​SKILL.md (Agent Context)

​Security

​Next Steps

Overview

Install

Quick Setup

Simulate Before Execute

Framework Integration

Tool Schemas Reference

`cashmere_bridge`

`cashmere_simulate`

Supported Chains

SKILL.md (Agent Context)

Security

Next Steps