When your coding agent tries something destructive, DashClaw catches it before it runs.

It freezes the action and asks you first, with one click, from anywhere. A fail-closed approval layer for the long, unattended runs where your agent's native permission prompts cannot help, because they need you at the keyboard.

Install the runtime

Installs the runtime, provisions Postgres, mints your key, and wires your first hook. No account on the path to your first caught action.

Rather not deploy yet? The hosted trial lets you see the Approvals inbox in your browser, no install.

Enforced at the hook seam in Claude Code, Codex, and Hermes, and at the OpenClaw gateway. Honored cooperatively by the Node and Python SDKs, the MCP server, and REST.

MIT licensedSelf hostedNo account to your first blockYour data stays on your infrastructure
Governed actionexample
agent_id
deploy-bot
action_type
deploy
declared_goal
"Ship auth-service v2.1 to production"
risk_score
92 / 100
matched_policy
production_deploy_gate
  1. REQUIRE_APPROVALheld, routed to on-call+0.3s
  2. approved by wes via Discord+41s
  3. deploy executed, outcome success+47s
act_9f2c47b1 · dc_sig_v1_eyJpZCI6… signed
Intercepted, held, approved, executed, recorded. Run this call against a live instance

The whole loop, on film · 55 seconds

Sound on. An agent action intercepted, held for a one-click approval, and recorded in the ledger.

Live demo, real demo endpoints

Try a real governance decision

Pick an action, hit Evaluate, and watch DashClaw enforce policy in real time. Every call hits the same governance runtime that ships to your instance.

Pick an action to evaluate
SDK call
await claw.guard({
  agent_id: 'openai-deployer-1',
  action_type: 'deploy',
  risk_score: 85,
  declared_goal: 'Deploy auth-service v2.1 to production with new session token rotation.',
});
Governance result

Pick an action and click Evaluate. The result will appear here, including the matched policy, the risk score, and what a human approver would see.

Guard decisions are live against the demo deployment. Approval clicks resolve locally so visitors can explore the flow without an account; your own instance routes them to /api/actions/:id/approve.

Native permission prompts protect you at the keyboard. DashClaw protects the runs you walk away from.

Claude Code and Codex already ship permission prompts for the at-keyboard user, for free. DashClaw does not compete with those. It does the job those prompts structurally cannot, because they need you present: it freezes the dangerous call and lets you approve it minutes or hours later, from anywhere.

DimensionNative permission promptsDashClaw
Who it protectsYou, while you watch each promptThe run you walked away from
When you must be presentEvery prompt, in real timeNever; approve later, from a phone
Policy scopePer session, per machine allowlistOne policy across every runtime and session
Audit trailNone you can exportSigned, replayable ledger (Ed25519, JWKS)
Interruption rateFixed prompts, no tuningCalibrated to a target false-block bound

This is not observability either. LangSmith and Langfuse record what an agent did, after it did it. DashClaw decides what it is allowed to do, before it runs.

The whole product is one loop

Intercept, decide, approve, prove. The hook seam runs it for you in Claude Code, Codex, and Hermes; the SDK, MCP server, and REST run the same four calls when you want explicit control.

govern-forcepush.ts
const claw = new DashClaw();

// 1. guard: policy decides before anything runs
const g = await claw.guard({
  action_type: 'shell',
  act: { kind: 'shell', command: 'git push --force origin main' },
});

// 2. createAction: open the decision record
const action = await claw.createAction({
  action_type: 'shell',
  declared_goal: 'Force-push the rebased branch',
});

// 3. waitForApproval: freeze until a human resolves it
if (g.decision === 'require_approval') {
  await claw.waitForApproval(action.action_id);
}

// 4. close the record: one-shot, durable, retry-safe
try {
  await run();
  await claw.reportActionSuccess(action.action_id, 'Pushed');
} catch (err) {
  await claw.reportActionFailure(action.action_id, err.message);
}
  1. Intercept

    A PreToolUse hook in Claude Code, Codex, or Hermes (plus dashclaw_invoke and the OpenClaw gateway) catches a tool call before it executes.

  2. Decide

    The guard engine risk-scores the call against your policies into the lattice allow < warn < require_approval < block. The join is max, and a block is absolute.

  3. Approve

    require_approval freezes the action and pages a human, who approves or denies with one click, from the Approvals inbox or a phone. Grants are single-use and bound to the exact action.

  4. Prove

    Every decision writes a durable, replayable, signed audit row. A liveness probe keeps proving the governor is still enforcing.

Read the SDK and API docs

Two things make the checkpoint livable

A governor you disable is worse than none. These two keep it earning its interruptions, and prove it is still awake.

Calibrated interruptions

A distribution-free controller tunes the interruption threshold from your approve and deny stream, with a proven false-block bound. It runs in shadow first, and when active it only ever tightens; loosening always routes through a proposal a human ratifies. Governance earns its interruptions instead of nagging you into turning it off.

Enforcement liveness

Once, the governor stopped enforcing and nothing noticed, because the ledger kept looking healthy. Now a probe drives a synthetic held action through the real hook seam and verdicts by whether it executed, not by reading the ledger. Stale never renders green.

Definitions, theorems, and honest limits are in the governance core theory doc.

It meets your agent where it already runs

One command wires Claude Code, Codex, or Hermes. A plugin covers OpenClaw. The MCP server gives any MCP client the same loop through 15 tools and 3 resources, no SDK and no code changes. Everything else takes the Node or Python SDK.

Claude CodeOne-command install
# No clone required — the CLI downloads the hooks bundle
# from your instance, wires ~/.claude/settings.json, and
# defaults to observe mode.
npm i -g @dashclaw/cli
dashclaw install claude            # prompts for endpoint + API key
dashclaw install claude --trial    # hosted signup, paste the key

# Governs Bash, Edit, Write, MultiEdit, Agent/Task, mcp__* tools.
# Flip to enforce: set DASHCLAW_HOOK_MODE=enforce in
# ~/.dashclaw/claude-hooks/.env

Where the block is mechanical, and where it is honored

We do not claim universal enforcement. We publish the table.

Mechanical halt

Claude Code, Codex, and Hermes lifecycle hooks (fail-closed, exit-2 on block), the OpenClaw gateway, and dashclaw_invoke. The action is stopped in the seam before it runs. The agent cannot proceed past a block.

Honored and recorded

Bare SDK, MCP, and chat-based callers consult guard and honor the decision cooperatively. Every call is still recorded, a block is never downgraded in the ledger, and any gap between decision and behavior is visible evidence, not silence. SDK callers can attach the actual command or request, so the server classifies risk from evidence instead of trusting the declaration.

The full per-surface table lives in the enforcement boundary doc.

What developers use DashClaw for

Three patterns that come up in every production agent stack.

Stop runaway deployments

One approval before production, full audit trail after.

await claw.guard({
  agent_id: 'deploy-bot',
  action_type: 'deploy',
  risk_score: 92,
  declared_goal: 'Ship auth-service v2.1 to prod',
});
What DashClaw did

Matched the production_deploy policy, paused the action, routed to the on-call engineer, recorded the approval.

Every governed action also lands in the signed decision ledger, ready to audit and export without a separate pipeline.

Put an approval layer in front of your unattended runs.

For the developer who kicks off a long run and cannot watch every tool call.