AI Skill Hub 强烈推荐:AI决策协议 是一款优质的Agent工作流。AI 综合评分 8.5 分,在同类工具中表现稳健。如果你正在寻找可靠的Agent工作流解决方案,这是一个值得深入了解的选择。
AI决策协议 是一套完整的 AI Agent 自动化工作流方案。通过可视化的节点编排,将复杂的多步骤任务拆解为清晰的自动化流程,实现全程无人值守的智能处理。支持与数百种外部服务和 API 无缝集成,适合构建数据处理管线、业务自动化和 AI 辅助决策系统。
AI决策协议 是一套完整的 AI Agent 自动化工作流方案。通过可视化的节点编排,将复杂的多步骤任务拆解为清晰的自动化流程,实现全程无人值守的智能处理。支持与数百种外部服务和 API 无缝集成,适合构建数据处理管线、业务自动化和 AI 辅助决策系统。
# 方式一:npm 全局安装 npm install -g agent-decision-protocol # 方式二:npx 直接运行(无需安装) npx agent-decision-protocol --help # 方式三:项目依赖安装 npm install agent-decision-protocol # 方式四:从源码运行 git clone https://github.com/OpenAgentGovernance/agent-decision-protocol cd agent-decision-protocol npm install npm start
# 命令行使用
agent-decision-protocol --help
# 基本用法
agent-decision-protocol [options] <input>
# Node.js 代码中使用
const agent_decision_protocol = require('agent-decision-protocol');
const result = await agent_decision_protocol.run(options);
console.log(result);
# agent-decision-protocol 配置说明 # 查看配置选项 agent-decision-protocol --config-example > config.yml # 常见配置项 # output_dir: ./output # log_level: info # workers: 4 # 环境变量(覆盖配置文件) export AGENT_DECISION_PROTOCOL_CONFIG="/path/to/config.yml"
<p align="center"> <img src="assets/adp-logo.svg" alt="Agent Decision Protocol" width="200"/> </p>
<p align="center"> <strong>The open governance framework for autonomous AI agents.</strong><br/> Classify decisions. Enforce policies. Prove compliance. </p>
<p align="center"> <a href="LICENSE"><img src="https://img.shields.io/badge/license-Apache%202.0-blue.svg" alt="License"></a> <a href="#"><img src="https://img.shields.io/badge/version-0.3.0-orange.svg" alt="Version"></a> <a href="#"><img src="https://img.shields.io/badge/status-draft-yellow.svg" alt="Status"></a> <a href="#regulatory-compatibility"><img src="https://img.shields.io/badge/EU%20AI%20Act-compatible-green.svg" alt="EU AI Act"></a> <a href="#regulatory-compatibility"><img src="https://img.shields.io/badge/Loi%2025%20QC-compatible-green.svg" alt="Loi 25"></a> <a href="#regulatory-compatibility"><img src="https://img.shields.io/badge/NIST%20AI%20RMF-compatible-green.svg" alt="NIST"></a> <a href="#regulatory-compatibility"><img src="https://img.shields.io/badge/ISO%2042001-compatible-green.svg" alt="ISO 42001"></a> <a href="#regulatory-compatibility"><img src="https://img.shields.io/badge/Singapore%20MGF-compatible-green.svg" alt="Singapore MGF"></a> </p>
<p align="center"> <a href="../../stargazers"><img src="https://img.shields.io/github/stars/OpenAgentGovernance/agent-decision-protocol?style=social" alt="Stars"></a> <a href="../../network/members"><img src="https://img.shields.io/github/forks/OpenAgentGovernance/agent-decision-protocol?style=social" alt="Forks"></a> <a href="../../actions/workflows/validate-schemas.yml"><img src="https://img.shields.io/github/actions/workflow/status/OpenAgentGovernance/agent-decision-protocol/validate-schemas.yml?label=CI" alt="CI"></a> </p>
<p align="center"> <a href="#quick-start">Quick Start</a> • <a href="#why-this-exists">Why This Exists</a> • <a href="docs/">Documentation</a> • <a href="#contributing">Contributing</a> • <a href="https://gouvernance.ai">gouvernance.ai</a> </p>
---
npm install # requires Node.js 20+
Add to your claude_desktop_config.json:
{
"mcpServers": {
"adp-governance": {
"command": "npx",
"args": ["tsx", "src/mcp/index.ts"],
"cwd": "/path/to/agent-decision-protocol"
}
}
}
| ADP Component | Loi 25 | EU AI Act | NIST RMF | ISO 42001 |
|---|---|---|---|---|
| Agent Registry | — | Art. 49 | GOVERN | A.6 |
| Risk Classification | — | Art. 6-7 | MAP | A.5 |
| Decision Traceability | Art. 12.1 | Art. 12 | MEASURE | A.7 |
| Right to Explanation | Art. 12.1 | Art. 13 | GOVERN | A.8 |
| Human Oversight | Implicit | Art. 14 | MANAGE | A.9 |
| Risk Management | — | Art. 9 | MAP+MANAGE | A.5 |
| Post-deployment Monitoring | — | Art. 72 | MEASURE | A.10 |
ADP uniquely addresses self-modification governance — no existing regulation explicitly covers an agent's ability to modify its own behavior. ADP classifies all self-modification as D4 with mandatory human approval.
---
| Component | Description | Spec |
|---|---|---|
| **Autonomy Taxonomy** | 5 standardized levels of agent autonomy (A1–A5) | [View →](docs/specs/01-autonomy-taxonomy.md) |
| **Decision Classification** | 4 decision types × 4 risk levels × 3 reversibility classes | [View →](docs/specs/02-decision-classification.md) |
| **Trace Format** | Hash-chained event schema for immutable decision logging | [View →](docs/specs/03-trace-format.md) |
| **Authorization Matrix** | Rules determining when human approval is required | [View →](docs/specs/04-authorization-matrix.md) |
| **Policy Schema** | Pre-built governance rules mapped to regulations | [View →](docs/specs/05-policy-schema.md) |
| **Regulatory Mapping** | How ADP maps to EU AI Act, Loi 25, NIST, ISO, Singapore MGF | [View →](docs/specs/06-regulatory-mapping.md) |
| **Agent Registry** | Structured inventory of all AI agents in an organization | [View →](docs/specs/07-agent-registry.md) |
---
| ADP | Langfuse | LangSmith | Datadog LLM | Credo AI | |
|---|---|---|---|---|---|
| **Focus** | Governance & compliance | Observability | Observability | Monitoring | Model governance |
| **Agent autonomy levels** | ✅ A1–A5 taxonomy | ❌ | ❌ | ❌ | Partial |
| **Decision classification** | ✅ 4 types × 4 risks | ❌ | ❌ | ❌ | ❌ |
| **Authorization matrix** | ✅ With escalation | ❌ | ❌ | ❌ | ❌ |
| **Policy engine** | ✅ 6 templates | ❌ | ❌ | ❌ | Partial |
| **Self-modification detection** | ✅ D4 category | ❌ | ❌ | ❌ | ❌ |
| **Regulatory mapping** | ✅ 6 frameworks | ❌ | ❌ | ❌ | Partial |
| **Vendor-independent** | ✅ Open standard | ✅ | ❌ LangChain | ❌ Datadog | ❌ |
| **Open source** | ✅ Apache 2.0 | ✅ | ❌ | ❌ | ❌ |
ADP complements observability tools — it doesn't replace them. Use Langfuse/LangSmith for technical tracing. Use ADP for governance, compliance, and policy enforcement.
---
高质量的开源AI工作流,实现自治AI代理的决策分类和执行
AI Skill Hub 为第三方内容聚合平台,本页面信息基于公开数据整理,不对工具功能和质量作任何法律背书。
建议在沙箱或测试环境中充分验证后,再部署至生产环境,并做好必要的安全评估。
✅ Apache 2.0 — 宽松开源协议,可商用,需保留版权声明和 NOTICE 文件,含专利授权条款。
总体来看,AI决策协议 是一款质量优秀的Agent工作流,在同类工具中具备一定竞争力。AI Skill Hub 将持续追踪其更新动态,建议收藏备用,结合自身场景选择合适时机引入使用。
| 原始名称 | agent-decision-protocol |
| 原始描述 | 开源AI工作流:Open governance framework for autonomous AI agents. Classify decisions. Enforce 。⭐5 · TypeScript |
| Topics | ai-agentsai-governanceai-safetyautonomous-agents |
| GitHub | https://github.com/OpenAgentGovernance/agent-decision-protocol |
| License | Apache-2.0 |
| 语言 | TypeScript |
收录时间:2026-06-17 · 更新时间:2026-06-17 · License:Apache-2.0 · AI Skill Hub 不对第三方内容的准确性作法律背书。
选择 Agent 类型,复制安装指令后粘贴到对应客户端