Simudyne Pulse

official

A high-fidelity intraday market simulator for testing how markets react to orders. Built using both an Agent-Based Model and a Foundation Model.

View on simudyne.comTry this MCPSponsored

What can you do with Simudyne Pulse MCP?

  • Generate synthetic orderbook data — Ask for millisecond-resolution L1/L2 quotes, depth, trades, and order flow via the Python SDK for model training.
  • Backtest trading algorithms — Replay your strategy against synthetic market data to evaluate performance without relying on historical tapes.
  • Simulate market impact — Measure how your orders affect prices in a market that reacts realistically to your trading activity.
  • Estimate pre-trade costs — Use synthetic order flow to calculate transaction cost analysis (TCA) before executing real trades.
  • Create stress test scenarios — Generate market conditions for crises that never happened to test strategy resilience under extreme scenarios.

Documentation

Pulse is synthetic orderbook data for training

Millisecond-resolution L1/L2 quotes, depth, trades, and order flow — via a Python SDK. Free to get started.

Simulation run in Pulse · 700.HK 09:30:01

Order book · 700.HK

PriceSize

609.5014,600

609.005,500

608.503,800

608.0014,900

607.504,700

607.004,800

Spread 1.00Mid 606.50

606.002,500

605.506,200

605.0023,100

604.503,300

604.002,000

603.502,400

L3 message feed

  • Waiting for messages…

Use cases

What can Pulse do?

  1. 01 · Algo backtesting

    Replay your algo over synthetic markets

  2. 02 · Market impact

    Measure impact in a market that reacts realistically

  3. 03 · Pre-trade TCA

    Estimate cost before you trade

  4. 04 · Stress scenarios

    Trade through crises that never happened

  5. 05 · Training data

    Unlimited tape for models that need more than history

Free tier Quickstart →

cached run 0000 — 50k TWAP sell replay (unreactive)

execution window 604.50 604.90 605.30

09:3010:3011:3012:3013:30

mid pricebid / askchild fills (on bid)avg fill 604.86 (dashed)

Pull a cached Pulse run and backtest your strategy against synthetic data. A classic replay backtest, but on unlimited synthetic days instead of one historical tape. The market doesn't react to your orders here; when you need impact, the same data model goes reactive on Pro.