Governance before agents act.
Evidence when they don't obey.
Trust when they coordinate.
A deterministic, auditable pre-execution governance layer for autonomous agents. Keeps agents inside the rules. Leaves a tamper-evident trail when they go off-script.
from canopy import authorize_action
result = authorize_action(
agent_ctx={"public_key": "pk-001"},
action_type="execute_shell",
action_payload={"command": "rm -rf /"},
)
# → DENY
Constitution — 3 immutable laws
Civil Code — 10 configurable titles
Firewall — pattern matching
Policy YAML — your rules
Audit trail — hash-chained + AVID
| Art. 0 | No catastrophic risk — immutable, no override |
| Art. 1 | Protect human life and dignity |
| Art. 7 | Sovereign kill switch |
Every decision records an authorization_id, avid, trace_id, and policy_snapshot. Reconstruct any incident — or prove it never happened.
canopy-incident --trace <id> audit.log
LangChain · LangGraph · CrewAI
AutoGen · OpenAI Agents SDK · OpenClaw
canopy-quickstart canopy-console
canopy-inspect canopy-policy-pack
canopy-incident canopy-verify
canopy-report canopy-lint-policy