@vaultfire/langchain

v1.0.1

Published

3 days ago

LangChain/LangGraph integration for Vaultfire Protocol — on-chain identity, trust verification, and partnership bonds for AI agents. 3-line setup.

Downloads

276

⚠️ Alpha Software — Vaultfire Protocol is in active development. Smart contracts are deployed on mainnet but have not been formally audited by a third-party security firm. Read-only tools are safe for any agent. Write tools interact with live contracts and transactions are irreversible. Use at your own risk. See LICENSE for warranty disclaimers.

@vaultfire/langchain

LangChain/LangGraph integration for Vaultfire Protocol

On-chain identity, trust verification, and partnership bonds for AI agents. Deployed on Base · Avalanche · Arbitrum · Polygon.

Why Vaultfire?

Every AI agent needs three things before a partner will trust it:

Identity — Who is this agent? (ERC-8004 on-chain identity registry)
Reputation — Has it performed well? (Verified feedback with Street Cred scoring)
Skin in the game — What happens if it fails? (AI Partnership Bonds with economic stakes)

Vaultfire Protocol makes all three verifiable on-chain. This package gives your LangChain agent direct access.

Quick Start

Install

npm install @vaultfire/langchain

3-Line Setup

import { createVaultfireTools } from '@vaultfire/langchain';

const tools = createVaultfireTools({ chain: 'base' });
// Pass `tools` to your LangChain agent — done.

With a LangGraph Agent

import { createVaultfireTools } from '@vaultfire/langchain';
import { ChatOpenAI } from '@langchain/openai';
import { createReactAgent } from '@langchain/langgraph/prebuilt';

const tools = createVaultfireTools({ chain: 'base' });
const model = new ChatOpenAI({ model: 'gpt-4o' });

const agent = createReactAgent({ llm: model, tools });

// Agent can now verify trust, check Street Cred, read bonds, etc.
const result = await agent.invoke({
  messages: [{ role: 'user', content: 'Is agent 0xA054...b84F trustworthy?' }],
});

Available Tools

Read-Only (7 tools — safe for any agent)

| Tool | Description | |------|-------------| | vaultfire_verify_agent | Full trust verification — identity, bonds, Street Cred, reputation, bridge status | | vaultfire_get_street_cred | Get Street Cred score (0–95) and tier: Unranked, Bronze, Silver, Gold, Platinum | | vaultfire_get_agent | Get on-chain identity data (URI, type, registration date, active status) | | vaultfire_get_bonds | Get all partnership bonds for an address (stake, type, status) | | vaultfire_get_reputation | Get reputation data (average rating, feedback count, verified %) | | vaultfire_discover_agents | Find agents by capability tags in the on-chain registry | | vaultfire_protocol_stats | Protocol stats: total agents, bonds, bonded value, bridge sync count |

Write Tools (2 additional — requires signer)

| Tool | Description | |------|-------------| | vaultfire_register_agent | Register a new AI agent on-chain via ERC-8004 Identity Registry | | vaultfire_create_bond | Create a partnership bond with economic stake |

Usage Examples

Read-Only — Verify Trust Before Interacting

import { createVaultfireReadTools } from '@vaultfire/langchain';

// Safe to give any agent — no signer, no write operations
const tools = createVaultfireReadTools({ chain: 'base' });

// Use with any LangChain-compatible agent

Write Operations — Register Agent & Create Bond

import { createVaultfireTools } from '@vaultfire/langchain';

const tools = createVaultfireTools({
  chain: 'base',
  privateKey: process.env.AGENT_PRIVATE_KEY,  // NEVER hardcode keys
});

// Agent now has 9 tools — including register and create_bond

Multi-Chain — Check Trust Across All 4 Chains

import { VaultfireClient } from '@vaultfire/langchain';

const trust = await VaultfireClient.verifyTrustMultiChain(
  '0xA054f831B562e729F8D268291EBde1B2EDcFb84F'
);

// trust.base, trust.avalanche, trust.arbitrum, trust.polygon
for (const [chain, result] of Object.entries(trust)) {
  console.log(`${chain}: Score ${result.streetCred.score}/95 (${result.streetCred.tier})`);
}

Direct Client — Without LangChain

import { VaultfireClient } from '@vaultfire/langchain';

const client = new VaultfireClient({ chain: 'base' });

// Check if an agent is trustworthy
const cred = await client.getStreetCred('0x...');
console.log(`Street Cred: ${cred.score}/95 (${cred.tier})`);

// Full trust verification
const trust = await client.verifyTrust('0x...');
if (trust.trusted) {
  console.log('Agent is verified and trusted');
}

Street Cred Scoring

Street Cred is Vaultfire's composite trust score (0–95 points):

| Component | Points | Description | |-----------|--------|-------------| | Identity Registered | 30 | Agent has ERC-8004 on-chain identity | | Has Bond | 25 | At least one partnership bond exists | | Bond Active | 15 | Bond is currently active | | Bond Tier | 5–20 | Based on stake amount (Bronze → Platinum) | | Multiple Bonds | 5 | More than one bond on record |

Tiers

| Tier | Score | Meaning | |------|-------|---------| | Unranked | 0–19 | No on-chain presence | | Bronze | 20–39 | Basic identity registered | | Silver | 40–59 | Identity + bond established | | Gold | 60–79 | Active bonds with meaningful stake | | Platinum | 80–95 | Full trust profile — identity, active bonds, high stake |

Bond Tier Thresholds

| Stake Amount | Tier Points | |-------------|-------------| | ≥ 0.01 ETH | 5 (Bronze) | | ≥ 0.05 ETH | 10 (Silver) | | ≥ 0.1 ETH | 15 (Gold) | | ≥ 0.5 ETH | 20 (Platinum) |

Supported Chains

| Chain | ID | Hub | Explorer | |-------|----|-----|----------| | Base | 8453 | ✅ Primary | basescan.org | | Avalanche | 43114 | Spoke | snowtrace.io | | Arbitrum | 42161 | Spoke | arbiscan.io | | Polygon | 137 | Spoke | polygonscan.com |

Deployed Contracts

API Reference

`createVaultfireTools(config?)`

Creates all Vaultfire tools for a LangChain agent. If a signer or private key is provided, includes write tools (register, bond).

createVaultfireTools({
  chain?: 'base' | 'avalanche' | 'arbitrum' | 'polygon',  // default: 'base'
  rpcUrl?: string,        // custom RPC (overrides default)
  signer?: ethers.Signer, // for write operations
  privateKey?: string,    // alternative to signer — use env vars, NEVER hardcode
}): VaultfireTool[]

`createVaultfireReadTools(config?)`

Creates read-only Vaultfire tools. Safe to give to any agent — cannot modify on-chain state.

createVaultfireReadTools({
  chain?: 'base' | 'avalanche' | 'arbitrum' | 'polygon',
  rpcUrl?: string,
}): VaultfireTool[]

`VaultfireClient`

Direct access to all protocol operations without the LangChain tool wrapper.

const client = new VaultfireClient({ chain: 'base' });

// Read operations (no signer needed)
await client.getAgent(address)
await client.isAgentActive(address)
await client.getTotalAgents()
await client.getStreetCred(address)
await client.getReputation(address)
await client.verifyTrust(address, minScore?)
await client.getBond(bondId)
await client.getBondsByParticipant(address)
await client.discoverAgents(capabilities)

// Write operations (requires signer)
await client.registerAgent(uri, type, capabilities)
await client.createBond(agentAddress, partnershipType, stakeEther?)

// Multi-chain (static)
await VaultfireClient.verifyTrustMultiChain(address, minScore?)

Chain Utilities

import { CHAIN_CONFIG, getChainConfig, getSupportedChains } from '@vaultfire/langchain';

getSupportedChains();           // ['base', 'avalanche', 'arbitrum', 'polygon']
getChainConfig('base');         // { name, chainId, rpcUrl, explorer, contracts }
getChainConfig(42161);          // look up by chain ID

Vaultfire Ecosystem

| Package | Description | |---|---| | @vaultfire/agent-sdk | Core SDK — register agents, create bonds, query reputation | | @vaultfire/langchain | This package — LangChain / LangGraph integration | | @vaultfire/a2a | Agent-to-Agent (A2A) protocol bridge | | @vaultfire/enterprise | Enterprise IAM bridge (Okta, Azure AD, OIDC) | | @vaultfire/mcp-server | MCP server for Claude, Copilot, Cursor | | @vaultfire/openai-agents | OpenAI Agents SDK integration | | @vaultfire/vercel-ai | Vercel AI SDK middleware and tools | | @vaultfire/xmtp | XMTP messaging with trust verification | | @vaultfire/x402 | X402 payment protocol with trust gates | | @vaultfire/vns | Vaultfire Name Service — human-readable agent IDs | | vaultfire-crewai | CrewAI integration (Python) | | vaultfire-agents | 3 reference agents with live on-chain trust | | vaultfire-a2a-trust-extension | A2A Trust Extension spec — on-chain trust for Agent Cards | | vaultfire-showcase | Why Vaultfire Bonds beat trust scores — live proof | | vaultfire-whitepaper | Trust Framework whitepaper — economic accountability for AI | | vaultfire-docs | Developer portal — quickstart, playground, framework picker |

Security

Never hardcode private keys. Always use environment variables.
Read-only tools are safe for any agent — they cannot modify on-chain state.
Write tools require a signer and should only be given to trusted agent pipelines.
All contract addresses are verified on mainnet explorers.

Requirements

Node.js ≥ 18
@langchain/core ≥ 0.3.0 (peer dependency, optional)

License

MIT — Ghostkey316

Published

Vulnerabilities

Links

Maintainers

Keywords

Readme

@vaultfire/langchain

Why Vaultfire?

Quick Start

Install

3-Line Setup

With a LangGraph Agent

Available Tools

Read-Only (7 tools — safe for any agent)

Write Tools (2 additional — requires signer)

Usage Examples

Read-Only — Verify Trust Before Interacting

Write Operations — Register Agent & Create Bond

Multi-Chain — Check Trust Across All 4 Chains

Direct Client — Without LangChain

Street Cred Scoring

Tiers

Bond Tier Thresholds

Supported Chains

Deployed Contracts

Base (Chain 8453) — Hub Chain

Avalanche (Chain 43114)

Arbitrum (Chain 42161)

Polygon (Chain 137)

API Reference

createVaultfireTools(config?)

createVaultfireReadTools(config?)

VaultfireClient

Chain Utilities

Vaultfire Ecosystem

Security

Requirements

License

`createVaultfireTools(config?)`

`createVaultfireReadTools(config?)`

`VaultfireClient`