REST API v2.0 · Live

Build with
sovereign AI.

165 specialized agents. 410+ endpoints. Zero data extraction. While Limova caps at 9 agents and ChatGPT offers 1 generic model, PolpAI delivers purpose-built intelligence — ship faster, stay sovereign.

Get API key View endpoints
165
Agents
410+
Endpoints
<200ms
p95 latency
99.9%
Uptime SLA
# pip install polpai
import polpai

client = polpai.Client(
    api_key="pk_live_..."
)

# Run Shadow AI Auditor agent
result = client.agents.execute(
    agent="shadow_ai_auditor",
    task="Scan org for uncontrolled AI usage",
    context={
        "employee_count": 50,
        "sector": "finance"
    }
)

# result.risk_score, result.violations, result.report
print(result.risk_score)  # 8.4 / 10
// npm install @polpai/sdk
import { PolpAI } from '@polpai/sdk'

const client = new PolpAI({
  apiKey: 'pk_live_...'
})

// Run Market Signal Monitor agent
const result = await client.agents.execute({
  agent: 'market_signal_monitor',
  task: 'Weekly signal report',
  context: {
    sector: 'saas',
    competitors: ['limova', 'moltbot']
  }
})

console.log(result.signals)  // 847 signals
curl -X POST https://api.polpai.io/v2/agents/execute \
  -H "Authorization: Bearer pk_live_..." \
  -H "Content-Type: application/json" \
  -d '{
    "agent": "competitive_intel",
    "task": "Compare vs Limova.ai",
    "context": {
      "competitors": ["limova"],
      "dimensions": ["agents","pricing","sovereignty"]
    }
  }'

# Response: { "result": {...}, "confidence": 0.96,
#   "agent_id": "B30", "latency_ms": 142 }
0 CVE
BYOS by default
LPRPDE compliant
99.9% uptime SLA
Post-quantum ready
724 patents
API Reference

410+ endpoints. 8 tentacles.

Every agent accessible via REST. JWT-authenticated. Rate-limited per plan. Zero data retention after response.

POST /v2/agents/execute Run any of 165 agents by name. Pass context, task, and optional parameters. Returns structured result + confidence score. Core
GET /v2/agents/list List all available agents grouped by tentacle (T1–T8). Filter by domain, capability, or patent family. Core
GET /v2/agents/metrics Performance metrics: confidence score, execution time, fitness evolution, predict()/evolve() trajectory. Core
POST /v2/memory/store Write to sovereign memory layer (L1–L5). AES-256-GCM encrypted. Stored on your infrastructure via BYOS. Memory
GET /v2/memory/recall Recall with semantic search. Cross-session context, decay scoring, L5 relational anchors. Memory
POST /v2/pme/audit Shadow AI compliance audit. Detects unauthorized AI usage, quantifies LPRPDE risk, auto-generates $1,500+ proposal. PME Suite
POST /v2/pme/intelligence Full B35+B36 intelligence stack: market signals, MRR forecast, client health score, opportunity detection. PME Suite
POST /v2/finance/forecast Oracle agent (B35). 3-scenario MRR model with linear+EMA blend, churn adjustment, confidence intervals. PME Suite
POST /v2/quantum/audit PQC security assessment. Scans infrastructure for post-quantum readiness. Audit report value: $1,500–$3,000. Security
POST /v2/chat Conversational interface to the full agent team. Session-aware. Natural language agent routing via IABROKER. Core
POST /v2/auth/token Exchange API key for short-lived JWT. 1-hour expiry with automatic refresh. Supports PKCE flow. Auth
GET /v2/health System status, agent availability by tentacle, current API version. No authentication required. Core
Pricing

Scale with your usage.

No per-seat pricing. Pay for API calls. Upgrade or downgrade anytime. No credit card required for Starter.

Starter
$0
10,000 calls / mo
  • All 8 tentacles
  • 60 req/min
  • Zero data retention
  • Community support
Start free
Developer
$7.99 / mo
100,000 calls / mo
  • All tentacles + priority queue
  • 300 req/min
  • Webhook events
  • Email support
Start free trial
Production
$29.99 / mo
1,000,000 calls / mo
  • All agents + BYOS
  • 1,000 req/min
  • Dedicated endpoints
  • Priority support + SLA
Contact us
Enterprise
Custom
Unlimited
  • Self-hosted deployment
  • Custom agent cluster
  • Custom SLA + MSA
  • PME pipeline included
Talk to us
SDKs

Your language. Our agents.

Official SDKs with type-safe models, async support, and automatic retry logic.

Python
Full async support with Pydantic v2 models. FastAPI-ready. 100% type coverage.
$ pip install polpai
Available
JavaScript / TypeScript
Node.js and browser. Zod schemas. React hooks. ESM and CJS builds.
$ npm install @polpai/sdk
Coming Q2 2026
Rust
Zero-overhead bindings. Tokio async runtime. WASM-ready for edge deployments.
$ cargo add polpai
Coming Q3 2026
Security

OWASP compliant. Sovereign by default.

Every API call protected at the structural level — not policy level. 72 patent families, 792 unique IDs covering the architecture.

JWT Authentication
Short-lived tokens with automatic rotation. No static API keys in production environments.
OWASP Top 10
Injection scan on every input. ASVS Level 2. Automated threat modeling per release cycle.
Rate Limiting
Per-key, per-IP, per-agent rate limits. DDoS protection via Cloudflare edge network.
Zero Data Retention
API responses are ephemeral by default. No conversation stored server-side unless explicitly opted in via BYOS.
Adversarial Compliance
95%+ ACT score across all agents. 50-scenario adversarial test suite run against every release.
Key Sovereignty (B27)
AES-256-GCM key vault. GitHub PAT rotation. Cloudflare token management. Zero-chat key transmission.
PolpAI ecosystem
polpai.ai polpai.com polpai.io polpai.bot polpai.space polpai.online polpai.xyz