Risk limits
for crypto trading agents.

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

LLM AgnosticClaude·GPT·Gemini·Kimi·MiniMax·DeepSeek·LlamaAny Agent FrameworkOpenClaw·Hermes·LangChain·CrewAI·AutoGenAgent EcosystemGiza·BNKR·NickAI·Ottie·HeyElsa·AsterAny Execution LayerDEX·CEX·Trading System·Ethereum·L2·EVM·BitcoinWalletsCoinbase Agentic Wallet·SafeAgent Paymentsx402·AgentCash·L402DeFi LendingAave·Spark·MorphoAssetsBTC·ETHLLM AgnosticClaude·GPT·Gemini·Kimi·MiniMax·DeepSeek·LlamaAny Agent FrameworkOpenClaw·Hermes·LangChain·CrewAI·AutoGenAgent EcosystemGiza·BNKR·NickAI·Ottie·HeyElsa·AsterAny Execution LayerDEX·CEX·Trading System·Ethereum·L2·EVM·BitcoinWalletsCoinbase Agentic Wallet·SafeAgent Paymentsx402·AgentCash·L402DeFi LendingAave·Spark·MorphoAssetsBTC·ETH

The problem

AI agents lack risk enforcement before execution.

No policy gate

Execution stacks handle signals, routing, custody and security. Market-aware risk permissioning is still missing.

Static limits don't adapt

Fixed caps and static guardrails behave the same in a crash and a breakout. Markets change. Your limits should too.

Autonomous ≠ uncontrolled

Agents can decide what to do. A separate policy layer should decide how much risk is allowed.

Raw models find reasons to break discipline.
RiskState prevents:

  • Blowups and ruin risk
  • Oversized positions in weak conditions
  • Leverage when the market doesn't support it
  • Overtrading in low-quality setups
  • Blind risk-taking on top of unhealthy DeFi loans

How it works

From signals to permissions in seconds.

RiskState policy engine converts market state into dynamic risk permissions.

01
30+ Signals

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

02
Market State

Normalize, composite score, regime detection

03
Policy Engine

4 independent caps × quality × volatility

04
Risk Permissions

Max size, leverage, allowed/blocked actions

5-level policy output

L1
BLOCK
Survival
Reduce exposure, hedge only
L2
DEFENSIVE
Protection
Wait, hedge, small scalps
L3
CAUTIOUS
Controlled risk
R:R >2:1 only, DCA
L4
SELECTIVE
Conditional
Trade with confirmation
L5
EXPANSION
Full
Leverage, full operations

Integration

Pre-trade risk gate for any system

Three ways to connect RiskState to agents, bots, and execution stacks.

REST API

Live

Standard HTTP endpoint. Any language, any framework.

import requests

response = requests.post(
    "https://api.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: 1.4.0
category: risk-management
auth: bearer-token
endpoint: POST https://api.riskstate.ai/v1/risk-state
assets: [BTC, ETH]
refresh: 60s cache, recommend 5min polling

MCP Server

Live

Native integration for Claude Desktop, Claude Code, and MCP-compatible clients.

// claude_desktop_config.json
{
  "mcpServers": {
    "riskstate": {
      "command": "npx",
      "args": ["-p", "@riskstate/mcp-server", "riskstate-mcp"],
      "env": {
        "RISKSTATE_API_KEY": "your-api-key"
      }
    }
  }
}

API Preview

One endpoint. Full risk enforcement.

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

Request
curl -X POST https://api.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,            // ◀
    "allowed_actions": ["DCA", "LONG_SHORT_CONFIRMED"],
    "blocked_actions": ["ALL_IN", "LEVERAGE_GT_2X"]
  },
  "tactical_state": "LEAN BULL",        // ◀
  "market_regime": "TREND",
  "policy_level": 4,
  "binding_constraint": {
    "source": "MACRO",                   // ◀
    "reason_codes": ["MACRO_NEUTRAL", "COUPLING_NORMAL"]
  },
  "risk_flags": {
    "structural_blockers": [],
    "context_risks": ["HIGH_COUPLING", "TREND_NOT_CONFIRMED"]
  }
}

Market State

Contextual

But why? Every number is auditable.

  • Tactical + structural + regime in 3 fields. Context, not a wall of text.
  • binding_constraint tells your agent exactly why it’s limited — debuggable.
  • include_details=true unlocks: squeeze detector, whale pressure, trend decomposition.

Risk Permissions

Binding

How much can I risk?

  • max_size_fraction. Your agent’s hard ceiling on position size.
  • Enum actions (DCA, WAIT, LEVERAGE_2X) your agent reads directly. No parsing.
  • structural_blockers empty = go. Not empty = halt. Zero ambiguity.

DeFi-Aware

Unified Risk

Your health factor changes your position limit in real-time.

  • Pass a wallet address. Health factor feeds directly into max_size_fraction.
  • DeFi lending risk × market risk = one position limit.
  • Protocol-aware: Spark and Aave V3 with per-collateral thresholds.

Trust

Why RiskState is trustworthy.

Built for systems that require consistent, auditable risk decisions.

Deterministic
policy engine

Same inputs, same outputs, always. SHA-256 policy hashes on every response. No stochastic decisions, no hidden state. Scoring version is frozen in 6-month minimums — no silent tuning.

Mathematically Audited
externally reviewed + publicly documented

External mathematical review of all scoring functions and normalization curves. Smooth sigmoids, logistic policy caps, Fisher z-transform confidence intervals. Every formula and every cap is published at conceptual level — calibration is not, but the shape is.

Read the methodology →
Forward-Validated
600+ live snapshots

Every scoring finding is tested against real forward returns. Permutation tests, circular block bootstrap for time-series dependency, honest confidence intervals. Framework and editorial standards published in Backtest; dated findings in Research.

See the backtest framework →
Not a black box
Inspect the risk engine in real time.

A human-readable view of how RiskState reaches risk decisions.

RiskState Visualizer
Independent
External and pluggable

RiskState does not generate signals, execute trades or custody assets. It plugs into your stack as an independent risk layer between market state and capital deployment.

Procurement-ready
audit · mandate · security · SIG Lite

Pre-vendor due-diligence brief: architecture, data classification, audit trail with 365-day retention (7-year export tier on request), mandate enforcement via per-key policy_config, security posture, and a SIG Lite mapping table. NDA pilot scope negotiated separately.

Read the institutional guide →

Request early access.

Free during beta. API key delivered instantly.

v1.4.0 live · deterministic · verifiable outputs

FAQ

Frequently asked questions.