Open source · Free tier

See everything your
AI agents ... do

Your agents send emails, create tickets, charge credit cards, and call APIs. AgentLedger logs every action, tracks every cost, and kills agents when things go wrong.

agent.ts
import { AgentLedger } from 'agentledger';

const ledger = new AgentLedger({
  apiKey: process.env.AGENTLEDGER_KEY
});

// Wrap any agent action
const result = await ledger.track({
  agent: 'support-bot',
  service: 'slack',
  action: 'send_message',
}, async () => {
  return await slack.chat.postMessage({
    channel: '#support',
    text: 'Issue resolved!'
  });
});

Works with LangChain · CrewAI · OpenAI Agents · Anthropic Claude · AutoGPT · MCP Servers · Any agent framework

Live Preview

Watch agents in real-time

This is what your dashboard looks like when agents are running. Every action logged, every cost tracked.

Live Agent Feed
0 events

Features

Everything you need to trust your agents

LLM observability tools track token usage. AgentLedger tracks what agents actually do.

📡

Real-Time Action Feed

Every API call, email, ticket — logged with timing, cost, and metadata. Live dashboard updates.

💰

Cost Tracking & Budgets

Know what your agents spend. Set daily/weekly/monthly budgets per agent with automatic enforcement.

🚨

Anomaly Detection

Automatic alerts when agents spike in activity, hit new services, or approach budget limits.

⏹️

Kill Switches

Pause or permanently kill any agent instantly from the dashboard or API.

🔌

2-Line Integration

Wrap any async function with ledger.track(). Works with LangChain, CrewAI, OpenAI, Anthropic, or plain code.

🛡️

Fail-Open by Default

If AgentLedger is down, your agents keep running. Never blocks production unless configured.

Get Started

Three steps. Five minutes.

No infrastructure. No config files. Just wrap and go.

1

Install the SDK

npm install agentledger
2

Wrap your agent actions

await ledger.track({ agent: 'my-bot', service: 'gmail', action: 'send_email', }, sendEmailFn)
3

Watch the dashboard

→ agentledger.co/dashboard

Comparison

Not another LLM tracer

Helicone and Langfuse track LLM calls. We track what happens after.

FeatureAgentLedgerLLM Tracers
LLM call tracing
Real-world action logging
Cross-service cost tracking
Agent kill switches
Budget controls & enforcement
Anomaly detection
Pre-flight action checks

Pricing

Simple pricing

Start free, scale when you need to.

Free

$0forever
  • 1,000 actions/mo
  • 2 agents
  • 24h data retention
  • Basic alerts
  • Community support
Get Started
Popular

Pro

$29/month
  • 50,000 actions/mo
  • Unlimited agents
  • 90-day data retention
  • Anomaly detection
  • Budget controls
  • Webhooks
  • Email support
Coming Soon

Team

$99/month
  • 500,000 actions/mo
  • Unlimited agents
  • 1-year data retention
  • SSO (coming soon)
  • Webhooks & API
  • Email support
Coming Soon

Free tier includes 1,000 actions/month with 24-hour data retention. Usage beyond plan limits is rate-limited. We reserve the right to enforce fair use policies to maintain service quality for all users.

Stop flying blind with your agents

Know exactly what your agents are doing, what they cost, and how to stop them when things go sideways.

Get Started Free