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.
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
This is what your dashboard looks like when agents are running. Every action logged, every cost tracked.
Features
LLM observability tools track token usage. AgentLedger tracks what agents actually do.
Every API call, email, ticket — logged with timing, cost, and metadata. Live dashboard updates.
Know what your agents spend. Set daily/weekly/monthly budgets per agent with automatic enforcement.
Automatic alerts when agents spike in activity, hit new services, or approach budget limits.
Pause or permanently kill any agent instantly from the dashboard or API.
Wrap any async function with ledger.track(). Works with LangChain, CrewAI, OpenAI, Anthropic, or plain code.
If AgentLedger is down, your agents keep running. Never blocks production unless configured.
Get Started
No infrastructure. No config files. Just wrap and go.
npm install agentledgerawait ledger.track({
agent: 'my-bot',
service: 'gmail',
action: 'send_email',
}, sendEmailFn)→ agentledger.co/dashboardComparison
Helicone and Langfuse track LLM calls. We track what happens after.
| Feature | AgentLedger | LLM 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
Start free, scale when you need to.
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.
Know exactly what your agents are doing, what they cost, and how to stop them when things go sideways.
Get Started Free →