CA: launching soon
001 — The control layer for AI agents

Agents move fast.
You decide how far.

Every action your AI agents take passes through Checkpoint before it runs. Allowed, stopped, or escalated to a human — and every decision recorded in a tamper-evident log.

ALLOW
It runs.
Within policy. No friction, no delay.
STOP
It's blocked.
Crosses a hard limit. Halted before it happens.
ESCALATE
A human decides.
Needs judgment. Paused and routed for approval.
002 — Integration

One line between your agent and the irreversible.

Wrap any action. Define rules in plain language. Checkpoint returns the verdict before anything executes — watch it run, then drop in the one line.
checkpoint-sdk · allow · escalate · stop · sealed
agent.pypython
import checkpoint as cp
 
# evaluate before the action runs
verdict = cp.check("transfer_funds", {
    "amount": 80000,
})
 
# rule: amount > 5000 requires review
# → STOP · routed to a human
003 — How it works
i
Wrap the action
Your agent proposes what it intends to do. A single call, before execution.
ii
Check the policy
The action is evaluated against your rules — spend limits, data thresholds, environments, identity.
iii
Return a verdict
Allow, stop, or escalate, decided instantly and written to a tamper-evident audit log.
004 — Built for any agent

One policy layer. Every kind of agent.

Finance, developers, internal ops, on-chain agents, DevOps, trading. Checkpoint sits in front of any action an agent can take, with the rules you set. See each scenario play out, with the policy behind it.
Explore use cases, with policy rules →