Risk governance for autonomous crypto agents

A deterministic policy engine that tells AI agents how much risk is allowed. 30+ real-time signals. 5-level policy. Verifiable audit trail.

Request API AccessDocumentation →
Request
curl -X POST https://riskstate.ai/v1/risk-state \
  -H "Authorization: Bearer $RISKSTATE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"asset": "BTC"}'
Response
{
  "exposure_policy": {
    "max_size_fraction": 0.42,
    "leverage_allowed": true,
    "max_leverage": "1.5x",
    "direction_bias": "LONG_PREFERRED",
    "reduce_recommended": false,
    "allowed_actions": ["LONG_SHORT_CONFIRMED", "DCA", "LEVERAGE_MODERATE"],
    "blocked_actions": ["ALL_IN", "LEVERAGE_GT_2X"]
  },
  "classification": {
    "tactical_state": "LEAN BULL",
    "structural_state": "POST-PEAK",
    "macro_state": "NEUTRAL",
    "market_regime": "RANGE",
    "volatility_regime": "NORMAL",
    "policy_level": 4,
    "confidence_score": 0.72,
    "data_quality_score": 88
  },
  "risk_flags": {
    "structural_blockers": [],
    "context_risks": ["HIGH_COUPLING", "TREND_NOT_CONFIRMED"]
  },
  "binding_constraint": {
    "source": "MACRO",
    "reason": "Macro regime NEUTRAL with normal coupling",
    "cap_value": 0.42
  },
  "audit": {
    "policy_hash": "a1b2c3d4e5f6...",
    "scoring_version": "score_v1",
    "version": "1.1.1",
    "timestamp": "2026-03-16T14:30:00Z",
    "ttl_seconds": 60
  }
}

The problem

Risk infrastructure doesn't exist yet.

No governance layer

25+ platforms handle execution, signals, payments, security. Zero handle risk governance. It's the missing layer.

Static limits don't adapt

Session caps and fixed guardrails work identically in a crash and a breakout. Markets change. Your limits should too.

Autonomous ≠ uncontrolled

AI agents managing millions in DeFi have authorization controls for what they CAN do. Nothing for what they SHOULD do.

How it works

From signals to permissions in 60 seconds.

01
30+ Signals

Market, on-chain, macro, derivatives, DeFi health

02
Risk Model

Normalize, composite score, regime detection

03
Policy Engine

4 independent caps × quality × volatility

04
Permissions

Max size, leverage, allowed/blocked actions

5-level policy output

L1
BLOCK
Survival
Reduce exposure, hedge only
L2
BLOCK
Defensive
Wait, hedge, small scalps
L3
CAUTIOUS
Preservation
DCA, R:R >2:1 only
L4
GREEN
Selective
Trade with confirmation
L5
GREEN
Expansion
Full operations, 2x leverage

API Preview

One endpoint. Full risk context.

Designed as a binding risk layer for agents and execution systems.

Request
curl -X POST https://riskstate.ai/v1/risk-state \
  -H "Authorization: Bearer $RISKSTATE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"asset": "BTC"}'
Response
{
  "exposure_policy": {
    "max_size_fraction": 0.42,
    "leverage_allowed": true,
    "max_leverage": "1.5x",
    "direction_bias": "LONG_PREFERRED",
    "reduce_recommended": false,
    "allowed_actions": ["LONG_SHORT_CONFIRMED", "DCA", "LEVERAGE_MODERATE"],
    "blocked_actions": ["ALL_IN", "LEVERAGE_GT_2X"]
  },
  "classification": {
    "tactical_state": "LEAN BULL",
    "structural_state": "POST-PEAK",
    "macro_state": "NEUTRAL",
    "market_regime": "RANGE",
    "volatility_regime": "NORMAL",
    "policy_level": 4,
    "confidence_score": 0.72,
    "data_quality_score": 88
  },
  "risk_flags": {
    "structural_blockers": [],
    "context_risks": ["HIGH_COUPLING", "TREND_NOT_CONFIRMED"]
  },
  "binding_constraint": {
    "source": "MACRO",
    "reason": "Macro regime NEUTRAL with normal coupling",
    "cap_value": 0.42
  },
  "audit": {
    "policy_hash": "a1b2c3d4e5f6...",
    "scoring_version": "score_v1",
    "version": "1.1.1",
    "timestamp": "2026-03-16T14:30:00Z",
    "ttl_seconds": 60
  }
}

Permissioning

Binding

What the agent is allowed to do. Max position size, leverage cap, allowed and blocked actions. These are hard constraints.

Classification

Informational

Market context for decision-making. Tactical state, cycle phase, macro regime, volatility. Informs strategy, doesn't constrain it.

Auditability

Verifiable

SHA-256 policy hash, scoring version, timestamp, data quality. Deterministic — same inputs always produce the same output.

View full API documentation →

Integration

Three ways to connect.

REST API

Live

Standard HTTP endpoint. Any language, any framework.

import requests

response = requests.post(
    "https://riskstate.ai/v1/risk-state",
    headers={"Authorization": "Bearer $TOKEN"},
    json={"asset": "BTC"}
)

policy = response.json()
max_size = policy["exposure_policy"]["max_size_fraction"]

SKILL.md

Live

Discovery standard for autonomous agent ecosystems.

# SKILL.md
name: riskstate
version: 1.1.1
category: risk-management
auth: bearer-token
endpoint: POST /v1/risk-state
assets: [BTC, ETH]
refresh: 60s cache, recommend 5min polling

MCP Server

Coming soon

Native integration for Claude Code, Cursor, and developer agents.

// MCP Server (coming soon)
const result = await mcp.callTool(
  "riskstate",
  "get_risk_state",
  { asset: "BTC" }
);

const maxSize = result.exposure_policy.max_size_fraction;
30+
real-time signals
Market, on-chain, macro, derivatives, DeFi
Deterministic
policy engine
Same inputs, same outputs, always
Versioned
audit trail
SHA-256 policy hashes, non-repudiation
60s
cache
Fresh data, always current
Calibration
in progress
Snapshot-based forward returns validation

Request early access.

Free during beta. We'll send your API key within 24 hours.