AgentLedgerby Neuralex

Know what every agent task costs you — and whether you can trust it in production.

AgentLedger records, per task, which model ran, what it cost vs. your subscription, and whether it was production-worthy. Self-hosted. Live in an afternoon.

No credit card required · open-source connector · 100% self-hostable

Every provider — API, Usage, or OAuth Verdict + audit trail — not just observability Priced below Langfuse/Datadog

The problem

Three things nobody can answer reliably today

The bill surprises you

Agentic AI burns 5–30× more tokens than chat, and retries + RAG push costs up 40–60% — invisible in your current dashboard.

Subscription or API?

Since "all-you-can-eat" pricing disappeared, nobody knows anymore which is cheaper per task. AgentLedger calculates it for you, task by task.

Pilots stay pilots

86% of agent pilots never reach production — usually due to missing audit trails and unclear evaluation criteria. We give you both.

How it works

Three steps, no rebuild

1

Plug in

One adapter on your gateway (LiteLLM/OpenTelemetry) or our SDK call. No rebuilding your stack.

2

Measure

Every task → an append-only ledger record: model, cost, savings, latency, retries.

3

Verdict

The verdict engine marks every task production-worthy / review / reject, with reasons — your audit trail for a board or client.

Proof

What you get

Cost per task, per model, per provider — including hidden retry costs.

Subscription-vs-API savings, calculated live.

Production-worthy verdict with configurable criteria.

Full audit trail per task — append-only, step by step.

Multi-provider: DeepSeek, Anthropic, OpenRouter and more — one line per new provider.

100% self-hostable. No prompt content stored unless you turn it on.

Competition

Everyone measures tokens. Nobody ties savings to a verdict.

ToolFocusGovernance verdictSub-vs-API
LangfuseObservability + costNoNo
HeliconeGateway + logging (maintenance mode)NoNo
PortkeyGateway + guardrailsPartialNo
Datadog LLM ObsEnterprise observabilityPartialNo
AgentLedgerCost + savings + verdict + auditYesYes

Pricing

Deliberately priced below Langfuse Pro and Datadog LLM

Free / OSS
€0
Indie, hobby
  • Connector + cost tab
  • 1 provider
  • Community support
Self-host now
Solo
€19/mo
Solo founder
  • Multi-provider
  • Savings benchmark
  • 100k tasks/mo
  • Email support
Start Solo
Team
€79/mo
Agency
  • Verdict engine
  • White-label PDF export
  • 3 seats
  • 500k tasks/mo
Start Team
Sovereign
€299/mo
Compliance-focused SMB
  • Fully self-hosted license
  • SSO
  • Audit export
  • Priority support
Get in touch

From "the model decided" to "here's exactly what it did, what it cost, and why it was allowed to."