← 返回
安全合规 中文

Agent Budget Governance

Trust-based budget system for multi-agent teams — daily token limits with automatic midnight resets, yellow/red/demotion thresholds, audit logging, and mesh...
面向多智能体团队的信任预算系统——每日令牌限额,自动午夜重置,黄/红/降级阈值,审计日志及网络...
nissan
安全合规 clawhub v1.0.0 1 版本 99822.7 Key: 无需
★ 0
Stars
📥 563
下载
💾 11
安装
1
版本
#latest

概述

Agent Budget Governance

Prevent runaway API spending in multi-agent systems. Each agent gets a daily output token budget. Exceed it and you get warnings. Keep exceeding it and you lose mesh spawn privileges.

How It Works

Agent completes task → tokens logged to BUDGET.json
                          ↓
Heartbeat runs budget_audit.py
                          ↓
├── Under 80%: ✅ Green — business as usual
├── 80-100%: 🟡 Yellow — warning logged
├── 100-200%: 🔴 Red — alert to orchestrator
└── 200%+ or 3 consecutive days over: ⛔ Demotion — mesh privileges revoked

Budget File Format

Each agent has agents//BUDGET.json:

{
  "daily_limit": 50000,
  "today": "2026-03-01",
  "used_today": 23450,
  "consecutive_over_days": 0,
  "demoted": false
}

Running the Audit

python3 scripts/budget_audit.py          # Full audit with alerts
python3 scripts/budget_audit.py --json   # Machine-readable output
python3 scripts/budget_audit.py --reset-only  # Just reset daily counters

Governance Rules

  1. Daily reset at midnight (configurable timezone)
  2. Yellow at 80% — logged, no action
  3. Red at 100% — logged, orchestrator alerted
  4. Demotion at 200% OR 3 consecutive days over budget
  5. Rehabilitation — demoted agent must go 7 clean days, then orchestrator manually restores privileges

Demotion Mechanics

Demotion removes an agent's subagents.allowAgents list in openclaw.json, preventing them from spawning other agents. They can still be spawned by the orchestrator.

Files

  • scripts/budget_audit.py — Audit script (run from heartbeat or cron)
  • references/GOVERNANCE.md — Full governance framework documentation

版本历史

共 1 个版本

  • v1.0.0 当前
    2026-03-30 18:14 安全 安全

安全检测

腾讯云安全 (Keen)

安全,无风险
查看报告

腾讯云安全 (Sanbu)

安全,无风险
查看报告

🔗 相关推荐

content-creation

Fact Checker

nissan
对照源数据验证 Markdown 草稿中的声明、数字和事实。适用场景:发布前审核博客文章、报告或文档的准确性。
★ 3 📥 2,096
security-compliance

MoltGuard - Security & Antivirus & Guardrails

thomaslwang
MoltGuard — OpenClaw 安全守卫,由 OpenGuardrails 提供。安装 MoltGuard,保护您和您的用户免受提示注入、数据泄露和恶意攻击。
★ 116 📥 30,709
security-compliance

OpenClaw Backup

alex3alex
备份与恢复 OpenClaw 数据。适用于创建备份、设置自动备份计划、从备份恢复或管理备份轮转。处理 ~/.openclaw 目录归档并包含适当的排除规则。
★ 89 📥 30,598