Flight recorder + spend governor for AI agents

Your agents are flying blind.
Record every move. Halt the spend.

Teams running AI agents have no audit trail — the invoice is the first sign something went wrong. Flightbox runs your agent pipelines through a managed runway: deterministic Python owns the loop, so it can record everything and actually stop agents, not just watch them.

Get the OSS core → See pricing
Trace waterfall of an agent run A session-replay waterfall with four agent lanes showing tool-call bars over time, ending in a red BUDGET HALT marker where the run was stopped at the cost cap. run 0142 · feature/checkout-refactor · $4.71 / cap $5.00 ● HALTED 0:301:00 1:302:002:30 planner builder reviewer shipper plan · $0.62 edit ×14 · $1.88 review · $0.94 ship · $1.27 BUDGET HALT $5.00 crossed nothing runs past here

The problem

“The invoice is your incident report.

An agent loops on a failing test at 2 a.m., burns through calls nobody sees, and the first artifact of the failure is a line item on next month's bill. No trace of which agent did what, which phase spent what, or where a human could have said no. Observability SDKs will tell you afterwards. Flightbox owns the loop — so it can stop it.

How it works

Stamp. Run. Replay & govern.

Flightbox is a managed runway, not a sidecar. Deterministic Python owns the loop; your agents are bounded nodes inside it.

STEP 01

Stamp the factory

Install the OSS core into your repo. Define your pipeline — phases, agents, budgets, approval points — in plain config. Run it with just.

STEP 02

Run through the runway

Every tool call, prompt, and decision streams live into a SQLite trace. Budget and approval gates sit in the loop itself — when a cap is crossed or an approval times out, the run halts. Hard stop, not a warning.

STEP 03

Replay & govern

Open the session-replay UI: a waterfall per run, per-phase tool-call detail, per-agent dollar attribution. Grant pending approvals from any terminal. Get cost estimates before the next run buys a single token.

Features

Everything recorded. Nothing unbounded.

Record

Flight recorder

Every tool call, prompt, and decision streams live into a SQLite trace. Session-replay UI with a waterfall per run and per-phase tool-call detail — scrub through exactly what your agents did.

Attribute

Cost attribution

Per-call token and dollar breakdown, rolled up per agent, per phase, per run. Know that the reviewer costs 3× the builder before it matters.

Halt

Budget gates

max_run_cost and per-agent max_cost HALT the run when crossed. The crossing call is billed and recorded — then nothing further runs. Not an alert. A stop.

Approve

Approval gates

A chain parks on a pending approval until a human grants it — from any terminal. Silence past the timeout is a denial. Your agents never assume a yes.

Forecast

Pre-run cost estimates

Median, p90, and worst-case cost from your own run history — before the first token is bought. A warning fires when p90 clears your cap.

$ just sessions

  RUN    PIPELINE            PHASES  COST     STATUS
  0139   feat/search-index   4/4     $2.13    ✔ complete
  0140   fix/rate-limiter    3/4     $3.87    ⏸ awaiting approval (deploy)
  0141   feat/checkout       4/4     $1.94    ✔ complete
  0142   feat/checkout-v2    3/4     $4.71    ■ HALTED — max_run_cost $5.00

$ just estimate feat/checkout-v3
  estimate from 12 prior runs:
  median $2.04   p90 $5.62   worst $7.90
  ⚠ WARNING: p90 ($5.62) clears max_run_cost ($5.00)
$ 

Pricing

Start free. Pay when the whole team flies.

Free

$0

OSS core · forever

  • Stamp the factory into any repo
  • Local SQLite trace
  • Engineer visualizer
Clone it

Recorder

$99

per month · $990/yr annual

  • Hosted replay across repos & teammates
  • Plain-language timelines
  • Spend roll-ups
  • Trace retention
Start 14-day free trial

Enterprise

Custom

talk to us

  • Everything in Governance
  • SSO
  • SOC 2 posture
  • Finance exports
Contact us

FAQ

Straight answers.

Is this an observability SDK?

No. SDKs observe from the sidelines — they can tell you what happened, not stop it. Flightbox is a managed runway: you run your agent pipelines through it. Deterministic Python owns the loop and agents are bounded nodes inside it, which is why a budget gate can actually halt a run mid-flight instead of just logging that it went over.

What happens exactly when a budget is crossed?

The call that crosses the cap is billed and recorded — you can't un-buy tokens already in flight. Then nothing further runs. The halt, the crossing call, and the full trace up to that point are all in the recording.

How do approvals work if I'm away from my desk?

The chain parks on the pending approval and waits. You can grant it from any terminal. If the timeout passes in silence, that's a denial — the run does not proceed on an assumed yes.

Where does my trace data live?

On the free OSS core, everything is local: a SQLite trace in your repo, viewed with the local visualizer. Paid tiers add hosted replay so teammates can share timelines across repos — that's the part you pay for, not the recording itself.