OPEN SOURCE · SELF-HOSTABLE · FREE

Know what every agent costs before your invoice does

One API call per action. One dashboard for every provider. Cost-per-agent, cost-per-task, cost-per-dollar — in real time.

Try the live demoRead the docs
localhost:3000/dashboard

Today

$12.84+18%

This week

$67.41-4%

Active agents

7+2

Events (24h)

1,847+312
Cost over timeLast 14 days

research-agent

anthropic · 142K tokens

$4.21

code-reviewer

openai · 98K tokens

$3.08

data-pipeline

google · 67K tokens

$2.17

Works with every provider in your stack

OpenAIAnthropicGoogleMistralCohereE2BComposioBrowserbaseMem0Stripe

How it works

Three lines to cost visibility

track_costs.py
import requests

# After every LLM call, send one event
requests.post("/api/ingest", json={
    "agentId": "research-agent",
    "provider": "anthropic",
    "model": "claude-sonnet-4-20250514",
    "costUsd": 0.08,
    "inputTokens": 2400,
    "outputTokens": 800
})

Python · Node.js · curl · any language with HTTP

01

Ingest cost events

One POST per LLM call, tool use, or compute action. Batch up to 1,000 events. Authenticated with an API key.

02

Costs aggregate automatically

Grouped by agent, provider, model, and operation. Time-series data updates in real time. No configuration needed.

03

Set budget guardrails

Daily, weekly, or monthly limits per agent or globally. Webhook alerts to Slack or Discord before you overspend.

Capabilities

Built for teams that ship agents

Real-time dashboard

Today’s spend, weekly trends, per-provider breakdowns. No refresh needed.

Per-agent accounting

Register agents, tag by project. See exactly which agent burns budget and why.

Budget alerts

Threshold-based alerts per agent or globally. Webhook delivery to Slack, Discord, email.

Cost explorer

Filter by date range, provider, agent, model. Export time-series data.

Multi-provider

OpenAI, Anthropic, Google, Mistral, Cohere, E2B, Composio — or any custom provider.

Self-hostable

Next.js + SQLite. Deploy to Vercel, Fly, Docker, or your own VPS. Swap to Postgres for production.

Open-core pricing

Free to start. Pay when you scale.

The core is MIT-licensed. Self-host forever or let us run it for you.

Community

For solo builders and experimentation

Freeforever
Get started
  • 5 agents
  • 50K events / month
  • 30-day data retention
  • Real-time dashboard
  • 3 budget alerts
  • Self-host (MIT core)
  • —Webhook alerts
  • —Batch ingestion
  • —Team members
Most popular

Pro

For teams shipping agents to production

$39/ month
Start free trial
  • Unlimited agents
  • 1M events / month
  • 90-day data retention
  • Real-time dashboard
  • Unlimited budget alerts
  • Self-host (license key)
  • Slack, Discord, email webhooks
  • Batch ingestion (1K/req)
  • 5 team members

Enterprise

For orgs that need governance at scale

Custom
Talk to us
  • Unlimited everything
  • Unlimited events
  • Unlimited retention
  • SSO / SAML + RBAC
  • 99.9% SLA
  • On-prem deployment option
  • + PagerDuty, custom hooks
  • Snowflake & BigQuery export
  • Unlimited members + 4h support

Built for real agent workloads

One dashboard for every dollar your agents spend

5 min

To first dashboard

Clone, configure, deploy. See costs immediately.

100%

Open source core

MIT-licensed. Self-host forever. No vendor lock-in.

Any provider

LLMs, compute, tools

OpenAI, Anthropic, E2B, Browserbase — one view.

Start tracking agent costs in 5 minutes

MIT-licensed core. No credit card. No vendor lock-in. Self-host forever or let us run it for you.

Try the live demoView API docs