Antihero Documentation v0.2.0

The policy engine for AI agents. Declarative policy enforcement, cryptographic audit trails, and fail-closed security for every AI agent, every tool call, every model.

Five Formal Guarantees

These are not marketing claims. They are mathematically enforced and verified by property-based tests.

Architecture

Every AI action passes through three layers: declare policy, enforce at the boundary, record the receipt.

┌─────────────────────────────────────────────────┐
│                    Policy Layer                  │
│        YAML rules, tiered composition,          │
│     deny-dominates, fail-closed, glob match     │
└────────────────────┬────────────────────────────┘
                     │
┌────────────┐  ┌────▼──────────────┐  ┌──────────────┐
│    TCE     │─>│      Guard        │─>│     AEE      │
│  (input)   │  │ policy evaluate   │  │ (audit log)  │
│            │  │ requirement gate  │  │ hash-chained │
│            │  │ fail-closed       │  │ append-only  │
└────────────┘  └────┬──────────────┘  └──────┬───────┘
                     │                        │
                ┌────▼──────┐          ┌──────▼───────┐
                │   PDE     │          │  Hash Chain   │
                │ (verdict) │          │  SHA-256      │
                └───────────┘          │  RFC 8785     │
                                       │  Ed25519 sig  │
                                       └──────────────┘

Install

pip install antihero

# Optional extras
pip install antihero[mcp]         # MCP server for Claude Code
pip install antihero[signing]     # Ed25519 audit signing
pip install antihero[all]         # Everything

60-Second Quickstart

# 1. Initialize (choose a persona: consumer, developer, enterprise)
antihero init --persona developer

# 2. Gate a dangerous command
antihero run -- rm -rf /
# -> DENIED. Logged to tamper-evident hash chain.

# 3. Gate a safe command
antihero run -- echo "hello"
# -> ALLOWED. Executed and logged.

# 4. Verify nothing was tampered with
antihero audit verify
# -> Chain integrity verified.

Policy Format

YAML rules compose across four tiers: baseline → org → app → user. Deny always dominates.

version: "1.0"
tier: app
name: my-policy

rules:
  - id: deny-dangerous
    effect: deny
    priority: 100
    actions: ["shell.execute"]
    resources: ["rm -rf*", "format*", "mkfs*"]
    risk_score: 1.0

  - id: gate-writes
    effect: allow_with_requirements
    priority: 50
    actions: ["file.write"]
    resources: ["*"]
    requirements:
      - kind: confirm
        params: { message: "Allow file write?" }
    risk_score: 0.5

Python SDK

from antihero import wrap

# Two lines. Every tool call is now policy-checked and audit-logged.
protected_agent = wrap(my_agent)
result = protected_agent.run("Deploy the update")

Guard (fine-grained control)

from antihero import Guard
from antihero.policy.engine import PolicyEngine
from antihero.policy.loader import load_policies
from antihero.evidence.chain import HashChain
from antihero.evidence.store import AuditStore

guard = Guard(
    engine=PolicyEngine(load_policies(".antihero")),
    chain=HashChain(),
    store=AuditStore(".antihero/audit.jsonl"),
)

guard.execute(
    my_tool_function,
    action="file.write",
    resource="/etc/passwd",
    parameters={"content": "..."},
)

TypeScript / JavaScript SDK

npm install @antihero/sdk

import { AntiheroClient } from "@antihero/sdk";

const client = new AntiheroClient({
  baseUrl: "https://api.antiheroes.dev",
  apiKey: "ah_live_...",
});

const stats = await client.getDashboardStats();
const events = await client.listEvents({ limit: 50 });

MCP Server

Works with any MCP-compatible client (Claude Code, OpenCode, Cursor). Every tool call is policy-gated and audit-logged.

Claude Code / Cursor

{
  "mcpServers": {
    "antihero": {
      "command": "antihero",
      "args": ["serve"]
    }
  }
}

OpenCode

{
  "mcp": {
    "antihero": {
      "type": "local",
      "command": ["antihero", "serve"],
      "enabled": true
    }
  }
}

Exposed Tools

Compliance

# SOC 2 Type II export
antihero audit export --format soc2 --org-name "Acme Corp" -o report.json

# HIPAA Security Rule export
antihero audit export --format hipaa --org-name "Acme Health" -o hipaa.json

Maps to Trust Services Criteria (CC6.1, CC6.3, CC7.2, CC8.1) and HIPAA Security Rule (164.312 b/c/d/e).

Three Markets, One Engine

CLI Reference