agendex 0.2.0

Governance SDK for AI Agents - Runtime policy enforcement, activity capture, and approval workflows

Agendex SDK

Resource-Level Governance for AI Agents - Dynamic task-scoped access control, parameter inspection, and tamper-evident audit trails.

What Makes Agendex Different

Traditional IAM	Agendex
"Agent can use payment tool"	"Agent doing vendor_payment task can call payments API if amount < $1000"
Static permissions	Dynamic, task-scoped
No parameter inspection	Full body/query inspection
Tool-level control	Resource-level control

Installation

pip install agendex

Quick Start: Resource-Level Governance (~30 lines)

from agendex import AgendexClient, GovernedDBClient, GovernedS3Client, GovernedHTTPSession
from agendex.errors import DeniedError, PendingApprovalError

# 1. Create client (reads config from env vars)
client = AgendexClient()

# 2. Create governed resource clients
db = GovernedDBClient(client, task="monthly_report")
s3 = GovernedS3Client(client, task="monthly_report")
http = GovernedHTTPSession(client, task="monthly_report")

# 3. Use in your tools - governance happens automatically
def fetch_revenue(month: str) -> str:
    try:
        result = db.query("monthly_revenue", {"month": month})
        return json.dumps(result.get("rows", []))
    except DeniedError as e:
        return f"[DENIED] {e.reason}"
    except PendingApprovalError as e:
        return f"[APPROVAL REQUIRED] ID: {e.approval_id}"

def initiate_payment(amount: float, vendor: str) -> str:
    try:
        result = http.post(
            "https://payments.api/v1/pay",
            json={"amount": amount, "vendor": vendor}
        )
        return json.dumps(result)
    except DeniedError as e:
        return f"[DENIED] {e.reason}"  # e.g., "amount > 5000"

Environment Variables

Variable	Description	Default
AGENDEX_URL	Proxy URL	http://localhost:8000
AGENDEX_AGENT_ID	Agent identifier	required
AGENDEX_TOKEN	Bearer token	required

How It Works

┌─────────────────────────────────────────────────────────────────┐
│  Agent Process                                                  │
│                                                                 │
│  Tool: fetch_revenue("2025-01")                                 │
│         │                                                       │
│         ▼                                                       │
│  GovernedDBClient.query("monthly_revenue", {month: "2025-01"})  │
│         │                                                       │
└─────────┼───────────────────────────────────────────────────────┘
          │
          ▼
┌─────────────────────────────────────────────────────────────────┐
│  Agendex Proxy                                                  │
│                                                                 │
│  /evaluate: {                                                   │
│    action: "db.query.run",                                      │
│    params: {query_id: "monthly_revenue"},                       │
│    task: "monthly_report"                                       │
│  }                                                              │
│         │                                                       │
│         ▼                                                       │
│  Policy: Allow db.query.run IF query_id=monthly_revenue         │
│          AND task IN [monthly_report, demo]                     │
│         │                                                       │
│         ▼                                                       │
│  /invoke → DBQueryAdapter → SQLite → rows                       │
│                                                                 │
└─────────────────────────────────────────────────────────────────┘

Policy Examples

agents:
  finance_bot:
    allow:
      # DB: Only specific queries, scoped by task
      - action: "db.query.run"
        resources:
          - type: db_query
            query_id: "monthly_revenue"
        tasks: ["monthly_report", "demo"]
      
      # S3: Only specific buckets/prefixes
      - action: "s3.reports.fetch"
        resources:
          - type: s3
            bucket: "reports-bucket"
            key_prefix: "monthly/"
      
      # HTTP: Parameter-aware decisions
      - action: "http.service.call"
        condition: "body.amount < 1000"
      
      - action: "http.service.call"
        condition: "1000 <= body.amount <= 5000"
        require_approval: true
    
    deny:
      - action: "http.service.call"
        condition: "body.amount > 5000"

Resource Clients

Client	Action	What It Governs
GovernedDBClient	db.query.run	Query ID, parameters
GovernedS3Client	s3.reports.fetch	Bucket, key prefix
GovernedHTTPSession	http.service.call	Domain, path, method, body

Integration Overhead

~31 lines to add Agendex to an existing agent:

• 2 lines: imports
• 3 lines: config
• 3 lines: tool signatures
• 18 lines: error handling (6 per tool)
• 5 lines: initialization

Documentation

• Quickstart Guide - Step-by-step integration
• API Reference - Complete SDK docs

License

MIT