Trust Infrastructure for AI Agents

Every AI Action.
Authorized. Logged. Audited.

AgentAudit is the accountability layer for AI agents — real-time authorization, behavioral risk scoring, and compliance-ready audit trails in minutes.

agentaudit — authorize & execute
// 1. Authorize an action
POST https://api.agentpassport.in/authorize
{ "agentId": "agent_payment_bot", "action": "transfer_funds", "ttl": 300 }

// Response
{ "token": "auth_7x9k...", "expiresIn": 300, "status": "authorized" }

// 2. Execute with validation (7 security checks)
POST /execute✓ Allowed — risk score: 12/100

// 3. Behavioral anomaly detected next day
⚠ INCIDENT: agent made 847 calls in 2 min — rate limit exceeded
✓ Auto-suspended + incident logged to audit trail
20
API Endpoints
7
Security Checks
99.9%
Uptime SLA
<50ms
Avg Latency

Everything your AI agents
need to stay safe

One API for authorization, execution validation, behavioral analytics, and compliance audit trails.

🔐

Time-Limited Authorization

Every agent action requires an authorization token with configurable TTL. No token = no execution. Automatic expiry prevents replay attacks.

🛡️

7-Layer Execution Validation

Every /execute call runs policy checks, rate limits, suspension checks, token validation, and more — before your agent does anything.

📊

Real-Time Risk Scoring

Gemini AI analyzes behavior patterns and assigns a 0–100 risk score per agent. Catch anomalies before they become incidents.

📋

Compliance Audit Logs

Paginated, immutable audit trails for every agent action. Export for SOC 2, ISO 27001, or internal compliance reviews.

Behavioral Analytics

Daily trends, hourly heatmaps, denial reason breakdowns, and per-agent performance analytics — all via API.

🚨

Automatic Incident Detection

Rate spikes, policy violations, and suspicious patterns trigger instant incident creation. Auto-suspend on critical risk.

Live in 3 API calls

Register your agent, define policies, and start authorizing actions — all via REST API.

01

Register your AI agent

Give your agent a name and capabilities. Get back an agentId to use in all future calls.

POST /agents → { "agentId": "agent_abc123", "status": "active" }
02

Define policy rules

Set rate limits, allowed actions, blacklisted actions, and execution windows per agent.

POST /policies → { "rateLimit": 100, "allowedActions": ["read", "write"] }
03

Authorize → Execute → Audit

Every action needs an authorization token. Execute validates against 7 security checks. Every outcome is logged.

POST /authorize → POST /execute → GET /audit
04

Monitor risk & incidents

Gemini AI generates behavioral summaries, flags anomalies, and creates incidents automatically.

GET /risk/:agentId → GET /incidents → GET /audit/summary/:agentId

Start auditing your AI agents today

Free tier — 3 agents, 500 executions/month. No credit card required.

Simple, transparent pricing

Start free. Scale when you need to. No hidden fees.

Free
₹0
forever
  • 3 AI agents
  • 500 executions / month
  • Basic audit logs
  • All 20 API endpoints
  • 7-layer execution validation
  • Gemini AI risk analysis
  • Behavioral summaries
  • Priority support
Enterprise
Custom
contact us
  • Unlimited agents
  • Unlimited executions
  • SOC 2 / ISO 27001 reports
  • Custom policy engine
  • Dedicated Gemini AI
  • SLA guarantee
  • On-premise option
  • Dedicated support
FeatureFreeGrowthEnterprise
Agents325Unlimited
Executions/month50050,000Unlimited
Audit log retention7 days90 daysUnlimited
Gemini AI analysis✓ Dedicated
Risk scoringBasicFullCustom model
Incident detection✓ + Alerts
API rate limit100/min1000/minCustom
SupportCommunityEmailDedicated SLA

Developer Documentation

All endpoints accept JSON. Authenticate with your API key in the x-api-key header.

Base URL
https://api.agentpassport.in
Authentication Header
x-api-key: ak_your_key_here
POST/orgCreate organization
GET/org/meGet current org details
GET/analytics/orgOrg analytics overview
POST/agentsRegister agent
GET/agentsList all agents
GET/agents/:idGet agent by ID
PATCH/agents/:id/suspendSuspend agent
PATCH/agents/:id/activateActivate agent
DELETE/agents/:idDelete agent (suspend first)
POST/policiesCreate policy rule
GET/policiesList all policies
POST/authorizeCreate time-limited authorization
POST/executeExecute with 7 security checks
GET/auditOrg audit log (paginated)
GET/audit/:agentIdAgent audit log
GET/audit/summary/:agentIdAI behavioral summary (Gemini)
GET/incidentsList incidents
GET/risk/:agentIdAgent risk profile
GET/analytics/overviewReal-time analytics
GET/healthHealth check
# 1. Register an agent
curl -X POST https://api.agentpassport.in/agents \
  -H "x-api-key: ak_your_key" \
  -d '{"name":"my-agent","capabilities":["read","write"]}'

# 2. Authorize an action
curl -X POST https://api.agentpassport.in/authorize \
  -H "x-api-key: ak_your_key" \
  -d '{"agentId":"agent_abc","action":"write","ttl":300}'

# 3. Execute
curl -X POST https://api.agentpassport.in/execute \
  -H "x-api-key: ak_your_key" \
  -d '{"agentId":"agent_abc","authToken":"auth_xyz","action":"write"}'

The trust layer the AI era needs

As AI agents proliferate across fintech, SaaS, and enterprise software, one question gets ignored: who's watching what the AI does?

AgentAudit was built to answer that. We provide the infrastructure layer that lets companies deploy AI agents confidently — with real-time authorization, behavioral risk scoring powered by Gemini AI, and immutable audit trails.

Think of us as the compliance layer between your AI agents and the real world. Like Stripe handles payments, we handle trust.

20
API Endpoints
7
Security Checks
99.9%
Uptime SLA
0
Data Brokers
Roadmap

Backend & Core API ✓

All 20 endpoints live. Supabase DB, Gemini AI, Render hosting.

Marketing Website ✓

agentpassport.in live with 8-page SPA.

Auth System — In Progress

Email/password signup. API key delivery via dashboard.

Razorpay Integration

Growth plan payments, plan upgrades, billing portal.

Live Dashboard

Real-time analytics, agent management, incident console.

SDK & Integrations

Node.js SDK, Python SDK, LangChain integration.

Security-first by design

Every architectural decision prioritizes the security of your agents and your data.

🔑 API Key Hashing Active

All API keys stored as SHA-256 hashes. Raw keys are shown once at creation and never stored in plaintext.

⏱️ Token Expiry Active

Every authorization token has a TTL (default 300s). Expired tokens are rejected automatically — no replay attacks.

🔒 7-Layer Validation Active

Every /execute call checks: token validity, token expiry, agent status, rate limits, policy rules, org plan limits, and action allowlist.

📊 Rate Limiting Active

Per-agent rate limits enforced at execution layer. Automatic incident creation and suspension on repeated violations.

🛑 Suspension Controls Active

Agents can be suspended instantly. Suspended agents cannot be authorized or execute — immediate hard stop.

🌐 HTTPS Only Active

All API traffic over TLS 1.3. SSL certificate on api.agentpassport.in. HTTP requests rejected.

🧠 AI Behavioral Analysis Active

Gemini AI continuously analyzes agent behavior patterns and flags anomalies. Behavioral summaries available per agent.

📋 Immutable Audit Logs Active

Every execution, authorization, and incident is logged immutably in Supabase. Audit logs cannot be modified after creation.

🏗️ Supabase PostgreSQL Active

Data stored in Supabase with row-level security, automatic backups, and enterprise-grade PostgreSQL infrastructure.

Found a security vulnerability? We take security reports seriously. Please email us at [email protected] with details. We will respond within 48 hours and provide a fix timeline. We do not take legal action against good-faith security researchers.

Get in touch

📧

Email

[email protected]

Response within 24 hours

📍

Location

Rajkot, Gujarat, India

For Enterprise Sales

Need unlimited agents, custom SLA, or on-premise deployment? Let's talk.

Service Status

All Systems Operational

Last checked: just now · Next check: in 60s

API — api.agentpassport.in

Core REST API endpoints

● Operational

Authorization Service

Token creation and validation

● Operational

Execution Validation

7-layer security check engine

● Operational

Gemini AI Analysis

Risk scoring & behavioral summaries

● Operational

Supabase Database

PostgreSQL — audit logs, agents, orgs

● Operational

Audit Log Service

Execution logging & retrieval

● Operational

Incident Detection

Anomaly detection engine

● Operational

Website — agentpassport.in

Marketing site & docs

● Operational
90-Day Uptime
90 days ago 99.9% uptime Today

Create your account

Free forever · 3 agents · 500 executions/month

Already have an account? Log in

By signing up you agree to our Terms of Service

Welcome back

Log in to your AgentAudit account

Don't have an account? Sign up free

Welcome,

Current Plan
free
Your API Key

⚠️ This key was shown once at signup. Use it in the x-api-key header for all API calls.

3
Max Agents
500
Executions/mo
0
Incidents
Quick Start
# Register your first agent
curl -X POST https://api.agentpassport.in/agents \
  -H "x-api-key: your_key" \
  -d '{"name":"my-first-agent"}'