Self-Evolving Deterministic Agent Control Protocol

A governance gateway for AI agents — making every action bounded, auditable, reversible, and explainable.

Works transparently with Cursor, Claude Code, Codex, and any MCP-compatible agent. Also supports shell command governance and a language-agnostic HTTP API.

🛡️ Governance in Action

  <b>1. Set Up Governance Rule</b>
  
  Enable the governance rule in Cursor's settings to protect your workspace.
</td>

  <b>2. Block Secrets Exfiltration</b>
  
  Agent attempts to read <code>.env</code> and write secrets — blocked instantly.
</td>
<td align="center" width="50%">
  
  
  <b>3. Block Credential Scanning</b>
  
  Agent tries to search for credentials and secrets files — denied by policy.
</td>

https://github.com/user-attachments/assets/ec7a9524-1527-4e51-b837-7e05a24b189d

Table of Contents

• How It Works
• Core Principles
• Quick Start
• Agent Integrations
• Built-in Policies
• Integration Modes
• Policy Self-Evolution
• Architecture
• Policy DSL Reference
• Built-in Tool Adapters
• Custom Tool Adapters
• Development
• Contributing
• License

How It Works

Agents never execute tools directly. Every action flows through the control plane for evaluation, enforcement, and audit:

flowchart LR
    A["Agent"] -->|"action request"| CP["Control Protocol"]
    CP -->|"evaluate against policy"| D{"Decision"}
    D -->|"allow"| E["Agent Executes Action"]
    D -->|"deny"| F["Blocked + Reason Logged"]
    D -->|"gate"| G["Human Approval Required"]
    E -->|"record result"| L["Evidence Ledger"]
    G -->|"approved"| E

The protocol does not execute actions itself. It evaluates them against a policy, enforces session-level budgets, requires human approval for risky operations, and records everything in a tamper-evident audit ledger.

Core Principles

Quick Start

Install

npm i @det-acp/core

Set Up Governance (One Command)

npx det-acp init cursor        # Cursor
npx det-acp init codex         # Codex CLI
npx det-acp init claude-code   # Claude Code

This generates all required files (policy, MCP config, governance rules) with sensible defaults. Edit policy.yaml to customize — everything else is handled automatically.