Sandboxing only
Contains runtime damage, but still allows risky actions to start. CordClaw decides before execution.
CordClaw
Pre-dispatch governance for OpenClaw.
Stop dangerous actions before they run. CordClaw enforces deterministic policy decisions at the execution boundary, not in-prompt.
Request Path
OpenClaw
Gateway Plugin Hook
CordClaw
Local Go Daemon
Cordum
Safety Kernel
Decision returned before execution: ALLOW, DENY, THROTTLE, REQUIRE_HUMAN, CONSTRAIN.
Why CordClaw
Three common approaches miss the execution boundary.
CordClaw is built for deterministic pre-dispatch control, not post-hoc visibility.
Monitoring only
Tells you what happened after the fact. CordClaw blocks or gates actions up front.
In-context prompts
Policy text can be bypassed by prompt injection. CordClaw evaluates structured metadata outside context.
Decision Model
Five deterministic outcomes.
Every action request maps to a typed decision and reason before execution.
ALLOW
Low-risk action executes immediately.
exec: npm test
DENY
Dangerous action is blocked before execution.
exec: rm -rf /
THROTTLE
Action is rate-limited to reduce blast radius.
exec: npm install (burst)
REQUIRE_HUMAN
Execution pauses until a reviewer approves.
message-send: external notice
CONSTRAIN
Action runs with enforced limits (sandbox, timeout, paths).
exec: go test ./... with 30s timeout
Comparison
CordClaw vs alternatives.
A practical view of where pre-dispatch policy enforcement fits.
| Capability | CordClaw | NemoClaw | SecureClaw | Native OpenClaw |
|---|---|---|---|---|
| Enforcement point | Pre-dispatch | Runtime sandbox | In-context | Config allow/deny |
| Decision types | 5 | 2 | 2 | 2 |
| Prompt-injection resistance | Yes (structured) | Yes | No | No |
| Human approval flow | Native | No | No | Limited |
| Audit trail depth | Full decision trail | Partial | Minimal | Minimal |
Quickstart
Install and validate in minutes.
Start with local setup, run your first simulation, then connect CordClaw to the full Cordum stack.
getting-started
bash
cd setup OPENCLAW_SKIP=true ./install.sh # first decision openclaw cordclaw simulate --tool exec --command "echo hello" # destructive command (expected DENY) openclaw cordclaw simulate --tool exec --command "rm -rf /" # inspect audit trail openclaw cordclaw audit --limit 20
90-Day Metrics
Adoption and usage dashboard (placeholder).
These values are placeholders until live metrics wiring is finalized.
GitHub stars
12.4k
placeholder
npm installs / month
38.1k
placeholder
blocked high-risk actions
4,982
placeholder
Enterprise
Put governance in front of every agent action.
Bring pre-dispatch controls, approval gates, and auditable decision trails to production AI agent workflows.