complyee/agent-guard-python

A customer-run companion that puts an Agent Control Room grant check in front of
any Python agent tool — LangGraph, CrewAI, LangChain or plain functions. It does
the repeatable work (fingerprinting, asking, waiting for a person, claiming,
verifying the grant token, reporting the outcome); you supply the action name and
the context facts your rules need.
Status: 0.1 (beta). Python 3.9 or later; depends only on httpx and cryptography.
bash
pip install complyee-agent-guard
Agent Control Room is the decision point; this package is
the enforcement point that runs inside your agent process. See
agent-cr.com/plugins and
agent-cr.com/enforcement-point.
## Use
python
import os
from complyeeagentguard import createguard, ApprovalPending, ActionRefused, VerifiedGrant
guard = createguard(
workspaceurl="https://acme.agent-cr.com", # your workspace address (also the JWT audience)
apikey=os.environ["ACRAPIKEY"], # scopes: policy.decide, policy.read
agent="finance-assistant",
approvals={"mode": "poll", "polltimeouts": 30, "pollintervals": 2}, # the defaults
@guard.tool(action="refund.issue", context=lambda a: {"amount": a["amount"]})
async def issuerefund(paymentid: str, amount: float, acrgrant: VerifiedGrant = None):
# Runs only after a verified grant for exactly these arguments.
return await payments.refund(paymentid, amount, idempotencykey=acrgrant.decisionid)
A plain def tool works the same way, synchronously. Add a parameter named
acrgrant to receive the verified grant; it is never part of the fingerprint.
Decorator options: name (tool name, default the function name), action
(default the tool name), context, resourceref, actiondescription,
parentdecisionid (each a function of the arguments), and approvals to
override the guard's approval settings for one tool.
## When a person must approve
"poll" (default): waits up to polltimeouts, then claims the grant with the
identical request. If nobody answers in time it raises ApprovalPending.
"raise": raises ApprovalPending at once — useful when a LangGraph workflow
should checkpoint and resume later.
python
try:
result = await issuerefund("pay1", amount=40)
except ApprovalPending as held:
store.save(held.tocheckpoint()) # JSON-safe; arguments stay in your store
...
result = await issuerefund.resume(store.load()) # same request, same idempotency key
## Fail closed
The tool body never runs when any of these is raised:
| Exception | Meaning |
| ActionRefused | policy or a person refused, or the arguments cannot be fingerprinted |
| ApprovalPending | a person has not approved yet |