DashClaw

Govern AI agents before they act.

DashClaw is the governance layer for AI agents that touch real systems. It sits between agents and the world, evaluates policy on every risky action, routes human approval where it is required, records verifiable evidence, and tracks terminal outcomes so a retried agent never silently double-executes.

_{Plugs into the agents you already run: Claude Code, Codex, Hermes Agent, OpenClaw, Claude Desktop, and Claude Managed Agents. Framework integrations for LangChain, CrewAI, AutoGen, LangGraph, and OpenAI Agents SDK. Any other runtime over MCP, the Node/Python SDK, or direct REST.}

What DashClaw does

Intercept	Risky agent actions are evaluated before they execute. Block, warn, or hold for approval, by policy.
Enforce	Declarative policies (risk thresholds, deploy gates, capability access rules, semantic checks) run on every action.
Approve	Pending approvals route to a dashboard queue, the CLI inbox, a mobile PWA, Telegram, or Discord, with one-tap allow or deny.
Record	Every action becomes a replayable decision record: declared goal, reasoning, risk score, matched policies, assumptions, evidence.
Finalize	Terminal outcomes are one-shot and durable. Lost confirmations are swept and surfaced, so retries do not double-execute.
Govern external systems	The capability registry wraps real HTTP APIs with per-agent access rules, rate limits, and audit. Workflows compose these into multi-step governed runs.
Improve	Code Sessions ingests Claude Code transcripts (Stop-hook live or JSONL backfill), prices the spend, surfaces optimizer signals (stuck loops, cache crater, context gaps), and distills sessions into an Optimal Files bundle — root CLAUDE.md, path-scoped rules, hooks, and skill packs — applied locally via dashclaw code apply.

---

Choose your integration path

DashClaw meets agents where they already are. Every path lands on the same governance primitives, audit ledger, and approval queue — pick the one closest to how your agent already runs.

Coverage at a glance

If your agent is…	Use this path	Install
Claude Code	Plugin + hooks	npm run hooks:install
Codex	Plugin	dashclaw install codex --project <path>
Hermes Agent	Plugin (8 lifecycle hooks)	bash scripts/install-hermes-plugin.sh
OpenClaw	OpenClaw plugin	npm install @dashclaw/openclaw-plugin
Claude Desktop, any MCP host	MCP server (stdio)	npx @dashclaw/mcp-server
Claude Managed Agents	MCP server (Streamable HTTP)	Point at /api/mcp
LangChain	Python SDK callback handler	pip install dashclaw
CrewAI	Python SDK task callback / agent wrapper	pip install dashclaw
AutoGen	Python SDK instrumentation	pip install dashclaw
LangGraph, OpenAI Agents SDK	Node or Python SDK	npm install dashclaw
Custom / framework-less	Node or Python SDK	npm install dashclaw
Anything HTTP	REST API + webhooks	OpenAPI spec

Working end-to-end examples for each runtime live in examples/ — anthropic-governed-agent, autogen-governed, claude-code-review-agent, codex-review-agent, crewai-governed, langgraph-governed, managed-agent-governed, managed-agent-mcp, openai-agents-governed, and more.

1. Coding-agent plugins (Claude Code, Codex, Hermes Agent)

One plugin source, three ecosystems. Distributed via plugins/dashclaw/. Each manifest ships the MCP server config, the dashclaw-governance protocol skill, the dashclaw-platform-intelligence reference skill, and a distinct agent_id so Mission Control separates sessions per host.

# Claude Code — installer for hooks + plugin
npm run hooks:install
ln -s "$(pwd)/plugins/dashclaw" ~/.claude/plugins/dashclaw

# Codex — installer wires manifest, hooks, and AGENTS.md governance protocol
node cli/bin/dashclaw.js install codex --project /path/to/your/project

# Hermes Agent — 8 lifecycle hooks (pre/post tool, pre/post LLM, on-session
# start/end, secret redaction, subagent_stop ROI tracking)
bash scripts/install-hermes-plugin.sh        # macOS / Linux
powershell -File scripts/install-hermes-plugin.ps1   # Windows

For Claude Code specifically, the hook installer alone (without the plugin) governs 40+ tool types (Bash, Edit, Write, MultiEdit, …) with semantic classification, risk scoring, and per-turn token capture — no SDK calls in your agent code. Set DASHCLAW_BASE_URL, DASHCLAW_API_KEY, and optionally DASHCLAW_HOOK_MODE=enforce. Full details in hooks/README.md.

2. MCP server (zero code, any MCP host)

@dashclaw/mcp-server exposes 23 governance MCP tools across 7 groups — core governance, optimal files, session continuity, credential hygiene, skill safety, open loops, learning + retrospection — plus 4 read-only resources (dashclaw://policies, dashclaw://capabilities, dashclaw://agent/{agent_id}/history, dashclaw://status).

Stdio (Claude Code, Claude Desktop, any stdio MCP client):

{
  "mcpServers": {
    "dashclaw": {
      "command": "npx",
      "args": ["@dashclaw/mcp-server"],
      "env": {
        "DASHCLAW_URL": "https://your-dashclaw.vercel.app",
        "DASHCLAW_API_KEY": "oc_live_xxx"
      }
    }
  }
}

Streamable HTTP (Claude Managed Agents, any remote MCP client): every DashClaw instance serves MCP at /api/mcp — no npm package, no client install.

agent = client.beta.agents.create(
    name="Governed Agent",
    model="claude-sonnet-4-6",
    tools=[{"type": "agent_toolset_20260401"}],
    mcp_servers=[{
        "type": "url",
        "url": "https://your-dashclaw.vercel.app/api/mcp",
        "headers": {"x-api-key": "oc_live_xxx"},
        "name": "dashclaw"
    }],
)

3. Node and Python SDKs — including framework integrations

For custom agents, frameworks, and anywhere you want explicit control over what gets governed.

npm install dashclaw     # Node 18+
pip install dashclaw     # Python 3.7+

87-method canonical Node surface: core governance, durable execution finality, scoring profiles, learning analytics, messaging, handoffs, security scanning, threads, sessions, and the execution-studio domains (workflow templates, model strategies, knowledge collections, capability runtime). The Python SDK exposes 235 methods including ready-made framework integrations:

# LangChain — auto-log LLM calls, tool use, and costs
from dashclaw.integrations.langchain import DashClawCallbackHandler
agent.run("Hello world", callbacks=[DashClawCallbackHandler(claw)])

# CrewAI — per-task callback or agent-level instrumentation
from dashclaw.integrations.crewai import DashClawCrewIntegration
integration = DashClawCrewIntegration(claw)
analyst = integration.instrument_agent(analyst)

# AutoGen — multi-agent conversation monitoring
from dashclaw.integrations.autogen import DashClawAutoGenIntegration
DashClawAutoGenIntegration(claw).instrument_agent(assistant)

Full method catalogues: sdk/README.md (Node, camelCase), sdk-python/README.md (Python, snake_case). The 4-step governance loop is in the Quick start below.

4. OpenClaw plugin

For agents built on OpenClaw, @dashclaw/openclaw-plugin wires governance into the lifecycle directly.

npm install @dashclaw/openclaw-plugin

It intercepts every tool-use call (before_tool_call, llm_output, after_tool_call, agent_end), calls guard / record / waitForApproval automatically, and ships a HOOK.md the openclaw CLI installs. Tool-classification vocabulary aligns with DashClaw guard action types so policies behave consistently across plugin, hook, and SDK paths.

5. Direct REST API and webhooks

Every governance primitive is reachable as HTTP. The stable contract is pinned in docs/openapi/critical-stable.openapi.json; the full inventory (259 routes: 46 stable, 23 beta, 190 experimental) is at docs/api-inventory.md. Webhook events include signal.detected, decision.created, action.created, lost_confirmation, and the rest of the catalog — configurable per org.

6. Skills — governance protocol + live platform reference

Two drop-in skills, both available as zip bundles or source directories in public/downloads/ and auto-bundled into the coding-agent plugins:

• dashclaw-governance — governance protocol skill. Teaches agents the decision tree (allow / warn / block / require_approval), action recording, approval-wait protocol, session lifecycle, plus six new sections for handoffs, secret hygiene, skill safety, action-scoped open loops, learning, and in-session retrospection.
• dashclaw-platform-intelligence — live API reference, env var contract, and troubleshooting playbook with progressive disclosure. Regenerated from the codebase on every release so it never drifts from the running runtime.

cp -r public/downloads/dashclaw-governance .claude/skills/
cp -r public/downloads/dashclaw-platform-intelligence .claude/skills/

Or grab the zips from dashclaw.io/downloads. The platform-intelligence skill is also published on ClawHub.

---

Quick start

10-second demo

npx dashclaw-demo

Spins up a local demo runtime, fires a simulated high-risk deployment, lets DashClaw block it, and opens Decision Replay in your browser. No setup, no accounts.

Real agent in 8 minutes (SDK path)

npm install dashclaw   # or: pip install dashclaw

import { DashClaw, GuardBlockedError, ApprovalDeniedError } from 'dashclaw';

const claw = new DashClaw({
  baseUrl: process.env.DASHCLAW_BASE_URL,
  apiKey: process.env.DASHCLAW_API_KEY,
  agentId: 'my-agent',
});

// 1. Guard
const decision = await claw.guard({ action_type: 'deploy', risk_score: 80 });

// 2. Record
const action = await claw.createAction({
  action_type: 'deploy',
  declared_goal: 'Ship release 2.13.4 to production',
});

// 3. Verify reasoning basis
await claw.recordAssumption({
  action_id: action.action_id,
  assumption: 'Tests passed on the candidate commit',
});

// 4. Outcome (durable, retry-safe)
try {
  // ...do the real work...
  await claw.reportActionSuccess(action.action_id, 'Deployed 2.13.4');
} catch (err) {
  await claw.reportActionFailure(action.action_id, err.message);
}

Python uses the same shape with snake_case. Full reference: sdk/README.md. Step-by-step walkthrough: QUICK-START.md.

---

Deploy

$0 to deploy. Vercel free tier plus Neon free tier. Click the button, add the Neon integration when prompted, fill in the env vars listed in .env.example. The schema migration runs as part of the build, so there is no manual migration step.

After deploy

1. Open the app at https://your-app.vercel.app and sign in.
2. Copy the integration snippet from Mission Control. It pre-fills your base URL and gives you a one-click API key.
3. Run it. node --env-file=.env demo.js from any client environment and watch the governed action land in your decisions ledger.

Optional

• Live decision stream. Add Upstash Redis credentials (UPSTASH_REDIS_REST_URL, UPSTASH_REDIS_REST_TOKEN) to get cross-instance event replay. Without it, Mission Control uses in-memory events, which is fine for getting started but does not persist across serverless invocations.
• Hosted trial mode. If you want DashClaw itself to mint trial workspaces (operator deployments only), follow docs/hosted-deployment-runbook.md. That path needs Turnstile, cleanup secrets, and an operator-managed cron.
• Self-host without Vercel. A Dockerfile and standalone next start path are available; see Dockerfile. The schema migration in scripts/auto-migrate.mjs is idempotent and safe to re-run.

---

Durable execution finality (v2.13.3)

Approved actions now carry a terminal outcome separate from their lifecycle status. Five states, one-shot transitions, repository-level enforcement:

State	Meaning
pending	Approved, no outcome reported yet.
completed	Finished successfully. Set by the agent.
partial	Started but did not finish. Set by the agent with a progress payload.
failed	Attempted and errored. Set by the agent with an error message.
lost_confirmation	Timeout exceeded without a report. Set by the cron sweep.

// Retry-safe poll before re-trying any approved action
const outcome = await claw.getActionOutcome(actionId);
switch (outcome.status) {
  case 'pending':           /* still in flight, wait */ break;
  case 'completed':         /* already executed, skip */ break;
  case 'failed':            /* safe to retry */ break;
  case 'lost_confirmation': /* sweep gave up, safe to retry */ break;
  case 'partial':           /* clean up then retry */ break;
}

// Make the create itself retry-safe
const key = claw.deriveIdempotencyKey({
  agent_id: 'deploy-bot', action_type: 'deploy', scope: 'prod-us-east', request_id,
});
await claw.createAction({ /* ... */, idempotency_key: key });

POST /api/actions/[actionId]/outcome is one-shot: the first call wins, every subsequent POST returns 409 with current_status. A daily Vercel cron (hourly externally on Pro or via GitHub Actions) marks stale pending rows as lost_confirmation and emits a signal.detected event so subscribed webhooks know to investigate. Full spec: docs/architecture/durable-execution-finality.md.

---

Safety and governance model

DashClaw is not observability. It is control before execution. The model:

1. Every agent action is evaluated against active policies before the action runs. Policies are declarative; the policy builder ships with eight pre-built safety switches (Deploy Gate, Risk Threshold, Rate Limiter, and others), an AI generator, and YAML import.
2. Sensitive actions require human approval. Approvals route to the dashboard, the CLI (@dashclaw/cli), the mobile PWA at /approve, Telegram, or Discord. Same action, any surface.
3. Every decision is recorded. The decisions ledger is replayable: declared goal, reasoning, matched policies, assumptions, signals, and the final outcome.
4. Outcomes are durable. The five-state finality machine guarantees no silent double-execute on retry, and the sweep catches lost confirmations.
5. Evidence is exportable. Compliance evidence bundles (signed manifests, JSON exports) are produced from real action records, not synthetic fixtures.
6. Prompt injection scanning is on by default. Declared goals are scanned for injection patterns. Hits are blocked at guard time.

The full architecture map lives in PROJECT_DETAILS.md. The runtime API contract is in docs/architecture/runtime-api.md.

---

Approvals beyond the dashboard

Surface	Purpose	Setup
Dashboard (/approvals)	Primary inbox for operators in front of a browser.	None.
CLI (@dashclaw/cli)	Terminal-first inbox. dashclaw approvals, dashclaw approve <id>.	npm install -g @dashclaw/cli
Mobile PWA (/approve)	Phone-first allow/deny with risk score and policy. Add to home screen.	None.
Telegram	Inline Approve/Reject buttons in an admin chat.	Optional. See docs/telegram-setup.md.
Discord	Inline Approve/Deny on DM embeds.	Optional. See .env.example (Discord section).

waitForApproval() unblocks within roughly one second regardless of which surface resolves the action. All surfaces hit the same /api/approvals/[actionId] endpoint.

---

Beyond the basics

Feature	Description	Docs
Drift detection	Statistical reasoning and metric drift across sessions.	SDK: Learning Loop
Capability registry	Wrap real HTTP APIs with per-agent access rules and health monitoring.	Capability Runtime
Workflow engine	Compose governance into multi-step runs with variables, continue_on_failure, and resume from checkpoint.	DEMO.md
Scoring profiles	Multi-dimensional evaluation with weighted composites and auto-calibration.	SDK: Scoring
Recovery recipes	Six built-in recipes mapping signals to remediations.	SDK: Learning
Agent profiles	Per-agent governance dashboard at /agents/[agentId].	PROJECT_DETAILS.md
Analytics	Cost trends, action volume, agent and type breakdowns, policy enforcement stats, and token efficiency at /analytics.	PROJECT_DETAILS.md
Doctor	npm run doctor (local) or dashclaw doctor (remote). Auto-fixes missing migrations, default policy, CORS, and more.	SDK README

---

Documentation

• Quick start: eight-minute walkthrough from clone to first governed action.
• Node SDK reference: canonical reference for the dashclaw npm package.
• Python SDK reference: same surface, snake_case.
• SDK parity matrix: Node v2 vs Python coverage.
• Runtime API contract: minimal core governance endpoints.
• API inventory: full route list with maturity tier.
• Durable execution finality spec: five-state machine, sweep, idempotency.
• Architecture map: system boundaries and SDK surface inventory.
• Changelog: release history.
• Security guide: operator-facing security model, controls, and coordinated disclosure.

---

License

MIT

_{Built by Practical Systems}