Runvouch

com.runvouch由 runvouch.com 发布官方发布者v0.3.4更新于 Nov 2, 2026

Watchdog for unattended AI agents: alerts, evidence checks and a verifiable proof per run.

已验证Streamable HTTP可网页运行开发者工具安全与监控AI 与机器学习

概览

AI 生成的概览

RunVouch 是无人值守 AI 智能体的看门狗：助手可查看智能体健康状态、读取并确认告警，以及上报和校验运行记录。

可以做什么
  • 查看所有被监控智能体的健康状态，包括状态、上次运行、24 小时花费和未处理告警
  • 列出未处理告警（漏跑、失败、无证据、预算超限、重试风暴、漂移、停滞），并按 id 确认告警
  • 查看单个智能体最近的运行记录
  • 上报运行开始与结束，附带状态和证据条目，并获得运行 id
  • 获取已完成运行的防篡改证明，包含哈希记录、Merkle 路径、当日根、链哈希和时间戳状态
适用场景
适用于定时或无头智能体在无人监督下运行，希望助手能发现失败、缺少证据、预算超支或循环，并为每次运行留下可验证证明的场景。
运行要求
通过 streamable HTTP 连接 api.runvouch.com 远程端点。需要 RunVouch API 密钥，放在 X-API-Key 请求头中，可在 runvouch.com 免费创建。使用托管端点无需本地安装包。
安装前请注意
API 密钥属于凭据，应妥善保密。确认告警会改变账户中的状态。上报运行会把运行状态和证据信息（包括 URL）发送给 RunVouch。免费额度为三个智能体，之后有付费方案。

安装

在 SourceWeft 中

  1. 打开 控制台中的 Runvouch，将其添加到工作区。
  2. 连接 X-API-Key 凭据。它们会被私密存储，绝不会在公开页面上展示。
  3. 为需要使用其工具的对话启用该服务。

Web executable，通过 Streamable HTTP。 远程服务在工作区中配置后即可从网页运行时运行。

交给智能体安装

把这段提示词粘贴到 Claude Code、Codex、Cursor 等智能体，或 SourceWeft 对话中。智能体会读取该服务器的安装指南，先向你展示发布者、端点和登录方式，经你同意后再把它添加到你的客户端。密钥不会写进任何命令。

阅读 https://sourceweft.com/mcp/com.runvouch%2Frunvouch/install.md，并按其中说明把这个 MCP 服务器接入我的客户端。修改任何配置之前，先告诉我它的发布者、端点和登录方式，等我确认。不要把 API 密钥写进命令或我会提交的文件；问我密钥应从哪里获取。

查看智能体所依据的安装指南

其他 MCP 客户端

把它添加到你客户端的 mcpServers 配置中。

{
  "mcpServers": {
    "runvouch": {
      "type": "http",
      "url": "https://api.runvouch.com/mcp",
      "headers": {
        "X-API-Key": "<YOUR_API_KEY>"
      }
    }
  }
}

README

[RunVouch]

RunVouch

The watchdog for unattended AI agents: proof they did the job, and an alert the moment they don't (or start spending), with a tamper-evident proof per run.
Claude Code Routines · headless claude -p · OpenClaw · n8n · cron

Website · Docs · Verify a run · Field notes · MCP Registry · Product Hunt

[PyPI] [npm] [GitHub Action] [MCP Registry] [Smithery] [License: MIT]

A green run means the scheduler worked, not that the task got done. RunVouch alerts within minutes when a scheduled agent is missing, failed, looping, over budget, drifting, or reported success without evidence.

pip install runvouch     # or: npm install -g runvouch  (zero-dependency client + rv CLI)rv agent nightly-report --cadence 24h --cap-run-cost 2 --evidencerv run nightly-report --evidence-file out/report.html -- claude -p "build tonight's report"

No client, no header: every agent also has a ping URL, so anything that can call a URL can report.

0 3 * * * /usr/local/bin/nightly.sh; curl -fsS -m 10 https://api.runvouch.com/ping/<token>/$?

Nothing for success, /start to open a run, /fail, or the exit code. rv agent NAME prints the URL.

Verifiable runs

Every finished run gets a sha256 record, every UTC day a Merkle root chained to the previous day and stamped in Bitcoin with OpenTimestamps. The day files are public at https://api.runvouch.com/proof/ and templates/verify_proof.py (stdlib only) checks a proof without our code. On every plan, Free included.

rv proof RUN_ID --verify     # recomputes leaf + Merkle path against the public day file, exit 0 or 1

Check it yourself, no account: https://runvouch.com/verify hands you one real sealed run from our own fleet, recomputes every hash in your browser, and has a button that edits a field so you can watch it break.

Mechanism and limits: https://runvouch.com/docs/proof · who needs it: https://runvouch.com/verifiable-agent-runs

Detectors

AlertMeaning
MISSEDexpected run never started (dead scheduler, expired auth, crash before first line)
FAILEDrun ended non-zero / status=fail
NO_EVIDENCErun said ok but required proof (file written, URL 200, assertion) is missing, green ≠ done
RETRY_STORMsame tool + identical input ≥ N times in one run (the invisible loop that costs $437)
BUDGET_RUN / BUDGET_DAYcost or tokens over the cap you set. On Solo and Team the agent is paused and its next run is refused until rv agent NAME --resume
DRIFTduration / output size off its 7-run baseline (robust MAD), silently doing something else
STALLEDstarted, no end and no heartbeat past max runtime

Alerts go to e-mail, Telegram, Slack, any JSON webhook, PagerDuty (Team) and the dashboard.

Layout

runvouch/server.py            FastAPI + SQLite, all detectors, dashboard at /runvouch/cli.py               `rv`, stdlib-only client: rv agent / rv run -- CMD / rv status / rv alerts / rv proofintegrations/claude-code-plugin Claude Code plugin: SessionStart/PostToolUse/Stop hooks → RunVouchintegrations/mcp                MCP server (stdio): runvouch_status/alerts/ack/runs/run_start/run_endsite/build.py                   generates the site into site/public/ (served by the same server)tests/                          123 tests (pytest, no network)docs/SELF_HOSTING.md            run it yourself: Docker or venv, what differs from hosted

Self-hosting

One process, one SQLite file, Docker or a venv. Full guide in docs/SELF_HOSTING.md (ten minutes, what differs from the hosted service, how to move later).

cp .env.example .env && docker compose up -d          # or: pip install -r requirements.txt && ./run.shcurl -X POST "localhost:8787/admin/accounts?name=me&plan=team" -H "X-Admin-Token: $RUNVOUCH_ADMIN_TOKEN"   # -> api_key

Use

export RUNVOUCH_KEY=rv_... RUNVOUCH_URL=http://localhost:8787rv agent nightly-report --cadence 24h --cap-run-cost 2 --evidencerv run nightly-report --evidence-file out/report.html -- claude -p "build tonight's report"rv status ; rv alerts

Claude Code plugin: see integrations/claude-code-plugin/README.md. MCP: claude mcp add runvouch -e RUNVOUCH_KEY=... -- python3 integrations/mcp/runvouch_mcp.py

Test and contribute

.venv/bin/pip install -r requirements-dev.txt && .venv/bin/python -m pytest -q tests

See CONTRIBUTING.md.

Hosted vs self-host

Hosted at runvouch.com: free for 3 agents, $19 Solo, $99 Team, alerts, dashboard, a nightly database backup on the server, EU hosting. Self-host: this repo, MIT. Same code.

Compare

vs Healthchecks.io · vs Cronitor · vs Langfuse

License

MIT.

来源：README.md，提交 b1d9dbc

工具

7

runvouch_status

Health of all watched agents: state (ok/alert/failed/unproven/running/waiting), last run, 24h cost, open alerts.

无需输入参数。

runvouch_alerts

Open (un-acknowledged) alerts: MISSED, FAILED, NO_EVIDENCE, BUDGET_RUN, BUDGET_DAY, RETRY_STORM, DRIFT, STALLED.

无需输入参数。

runvouch_ack

Acknowledge an alert by id.

输入参数alert_id必填

runvouch_runs

Recent runs of one agent.

输入参数agent必填limit

runvouch_run_start

Report that a run of `agent` started. Returns run_id.

输入参数agent必填source

runvouch_run_end

Report that a run ended, with status and evidence dict (name -> bool or {type:'url',url}). Green run without evidence alerts.

输入参数costrun_id必填statustokensevidence

runvouch_run_proof

Tamper-evident proof of a finished run: hashed record, Merkle path, day root, chain hash and OpenTimestamps status. Verify offline with templates/verify_proof.py.

输入参数run_id必填

版本历史

1
  1. v0.3.4最新Sep 16, 2026

评分

已满足适用检查项的 100%

该评分衡量此收录条目的完整程度，依据注册中心条目、端点与公开来源计算得出。它不是对服务器本身的评价，也不表示服务器安全或当前可用：可连通性是带日期的检查结果，评分也不包含安装量或用户评价。

  • 近 30 天内可连通必需25 分
  • 已声明认证方式必需10 分
  • 已列出工具必需15 分
  • 描述必需15 分
  • 图标10 分
  • 文档15 分
  • 许可证10 分