Understand and control your agents down to each action they take.
See, control, and price every model and tool call — across every agent framework you run. Free to start. Flat price for teams — never per seat.
You shipped an agent. Now it's a black box.
The day an agent hits production is the day you find out you can't see — or stop — what it's doing. If any of these is you:
Same task, wildly different cost — and you find out from the invoice, not the run.
It reads your .env, pulls customer PII, pipes secrets straight into a prompt — and you can't see what left the building.
Every team ships in a different framework — and there's no one place to see or control them all.
See exactly where your agents are costing you.
Averages lie. The same coding agent here ran 0.9¢ at the median — and $501 in the tail, on the same kind of task. Cost tracks how much context the orchestration loop re-reads to decide its next move, and that scales with how far the run wanders. One number can't tell you whether an agent is cheap or a runaway waiting to happen.
- Every run as one dot — median, middle-80% band, and the expensive tail
- Failed runs called out — you pay for the ones that never finish, too
- Loop vs leaf: the orchestration loop re-reading context is usually most of the bill
- Budget caps that halt the run, deterministically — not just a warning
Understand every action it took.
When a run costs $50 or does something you didn't expect, you need to see what actually happened. ACP records every action in order — each model call and tool call with its latency, tokens, cost, and allow-or-deny decision, plus the real identity behind it. Click any event and see exactly what it did.
- The full timeline — loop, leaf, and tool calls, as they happened
- Per-event cost, latency, model, and the policy decision that gated it
- Real identity and scopes carried through every delegation hop
Your agent walked in holding 76 tools.
Every request a coding agent makes declares its full tool catalog — the model can't call what it can't see. A real Claude Code session declares 76 tools: the coding loop, yes — and tools that send messages, publish public web pages, schedule their own future runs, and drive your logged-in browser. Most were never invoked. All of them are standing open.
ACP captures the declared surface on the agent's first call — before anything runs — and turns it into a control table: every tool a click to allow, flag, or deny. When the surface drifts mid-session (we've watched one gain 21 tools in an afternoon), you hear about it.
- The full catalog, visible before first invocation
- One click per tool: allow · flag · deny · ask
- Drift detection — know when the surface grows
Your first audit row in thirty seconds.
A coding agent in your IDE, a CrewAI pipeline, a LangGraph service, the OpenAI SDK in a script — pick the method that fits your stack. One install, no code changes, and every tool call is controlled. Free to start. Flat price for teams — never per seat.
One install per stack — the same control plane behind all of them. See every integration →
Open core, hosted control plane. The enforcement modules are six MIT-licensed npm packages you can read and self-host — the hosted control plane is how you run them in production.
Free to start — 10,000 governed calls a month.
Every feature works on the free tier. You pay when you outgrow the limits — or when the whole team needs in. Never per seat.
- See, control & price every call
- 10,000 calls / month (tool + model)
- Unlimited agents & seats
- Full audit, cost & policy
- 30-day audit retention
- Everything in Free
- 100,000 calls / month · $0.20 per 1K after
- Per-user rate limits & budgets
- Custom PII patterns
- 90-day audit retention
- Everything in Pro
- 1,000,000 calls / month · $0.20 per 1K after
- Roles & org-wide cost rollup
- Unlimited seats — flat price
- 1-year audit retention
See full pricing details, FAQ, and examples at /pricing →
Go deeper: why agents make chains of calls · the delegation-chain spec · how our logs caught an agent quietly getting worse
Control every tool call your agents make.
Free to start — 10,000 governed calls a month, no credit card. See your first controlled tool call in about thirty seconds.
Rolling agents out across a team? See ACP for teams →
Or book 30 minutes — I’ll wire it into your agent with you, live.
— David Crowe, founder
