DashClaw
🛡️ The approval and policy layer for AI agents. Intercept risky actions before they run, block them, or approve them remotely.
Source#
- Repository: ucsandman/DashClaw
- Last source update: 2026-08-15
- Last verified: 2026-08-16
Tags#
Integration notes#
Repository is focused on tool/server interoperability; wrap in bounded worker contracts for production use.
worker.md example#
Starter worker.md contract mapped from this registry entry. Copy this file and adapt schemas, constraints, and statuses for your task.
---
id: dashclaw-repo-derived-worker
name: DashClaw Repo-Derived Worker
version: 1.0.0
source_registry_url: https://worker.md/registry/dashclaw/
source_repository: https://github.com/ucsandman/DashClaw
repository_default_branch: main
repository_language: TypeScript
repository_license: MIT
repository_updated_at: 2026-08-15
worker_mode: agent-orchestration-worker
derivation_method: github_repository_metadata_plus_raw_readme
derivation_confidence: 0.95
derived_on: 2026-08-16
tags:
- agent-framework
- agent-governance
- agent-runtime
- ai-agents
- ai-governance
- ai-infrastructure
---
# DashClaw Repo-Derived Worker
## Repo-derived summary
- Registry summary: 🛡️ The approval and policy layer for AI agents. Intercept risky actions before they run, block them, or approve them remotely.
- Repository description: 🛡️ The approval and policy layer for AI agents. Intercept risky actions before they run, block them, or approve them remotely.
- Stars (snapshot): 293
- Primary language: TypeScript
- Worker mode classification: agent-orchestration-worker
## Extracted from
- https://github.com/ucsandman/DashClaw
- https://github.com/ucsandman/DashClaw/blob/main/README.md
- https://www.dashclaw.io/llms.txt
- https://hosted.dashclaw.io/connect
- https://www.dashclaw.io/guides/openclaw
## Evidence notes (from repository text)
- README summary paragraph: When your AI coding agent tries something destructive, DashClaw catches it before it runs and asks you first, even when you are not at the keyboard.
- When your AI coding agent tries something destructive, DashClaw catches it before it runs and asks you first, even when you are not at the keyboard.
- Run agents unattended without giving them unconditional authority.
- An agent tries a destructive tool call. DashClaw freezes it before it runs, routes it to the Approvals inbox, and writes a replayable decision record when you resolve it.
- - **Fail-closed intercept.** A blocked tool call never runs. The hook cancels it before execution (exit 2 at the seam).
- - **Multi-runtime.** Claude Code, Codex, Hermes, OpenClaw, MCP, Node and Python SDKs, plain REST.
## Installation hints found in README
- `pip install dashclaw` (Python 3.7+). The **39-method canonical Node surface** covers guard, record, assumptions, approvals, durable-execution finality, security scanning, sessions and the action graph, pairing, risk signals, policy simulation, plan authorization, delegation constraints, containment verdicts, and team tasks. The **Python SDK exposes 59 methods**, plus CrewAI and AutoGen integrations.`
- `npm install dashclaw` (Node 18+) or `pip install dashclaw` (Python 3.7+). The **39-method canonical Node surface** covers guard, record, assumptions, approvals, durable-execution finality, security scanning, sessions and the action graph, pairing, risk signals, policy simulation, plan authorization, delegation constraints, containment verdicts, and team tasks. The **Python SDK exposes 59 methods**, plus CrewAI and AutoGen integrations.`
## worker.md contract (derived starter)
Purpose: Execute one orchestrated agent task as a bounded worker step.
### Input schema
```json
{
"type": "object",
"additionalProperties": false,
"required": [
"run_id",
"task",
"context"
],
"properties": {
"run_id": {
"type": "string"
},
"task": {
"type": "string"
},
"context": {
"type": "object"
}
}
}
```
### Output schema
```json
{
"type": "object",
"additionalProperties": false,
"required": [
"run_id",
"status",
"result"
],
"properties": {
"run_id": {
"type": "string"
},
"status": {
"type": "string",
"enum": [
"ok",
"retryable_error",
"invalid_request",
"invalid_output"
]
},
"result": {
"type": "object"
}
}
}
```
### Constraints
- timeout_seconds: 30
- max_attempts: 2
- idempotency_key: run_id
- status_enum: [ok, retryable_error, invalid_request, invalid_output]
- notes: adapt to concrete APIs/classes documented in this repository before production use
## How this should be used
1. Treat this file as a repo-derived starter profile, not a claim of an official repository API contract.
2. Replace schemas with exact interfaces from code/docs you adopt.
3. Keep execution bounded and auditable using worker protocol constraints.
How to use#
- Save this as a worker spec file (for example:
dashclaw-my-task.worker.md). - Replace the input/output schemas and purpose with your real bounded task.
- Enforce schema validation + timeout + retry policy in your runtime before production use.
Citation#
Reference URL: https://worker.md/registry/dashclaw/
Source URL: https://github.com/ucsandman/DashClaw