godzilla.dev's answer:

godzilla.dev pairs a C++ execution core (microsecond-scale tick-to-trade latency on the local software path, designed for co-located deployment) with a Python strategy layer for fast iteration. It is fully self-hosted: API keys, private keys, and strategy configuration never leave machines you control. Most open-source trading frameworks optimize for connector breadth and ease of use; godzilla.dev optimizes for latency-critical, production-grade execution.

godzilla.dev's answer:

Choose godzilla.dev if execution latency and self-custody of infrastructure matter more to you than connector breadth. Frameworks like Hummingbot are excellent for connecting many venues quickly with ready-made strategies. godzilla.dev focuses on a different problem: running funding rate arbitrage and market making with a native C++ hot path, a journal-based event architecture with deterministic replay, and no cloud backend. If you need dozens of exchange connectors out of the box, a breadth-focused framework may serve you better — the two design goals are genuinely different.

godzilla.dev's answer:

Quantitative trading teams, individual quants with systems programming experience, and institutions (exchanges, market makers, arbitrage desks) that need self-hosted trading infrastructure. Users typically run delta-neutral funding rate arbitrage, low-latency market making, or custom strategies on centralized crypto exchanges, and prefer local deployment over hosted platforms for security and latency reasons.

godzilla.dev's answer:

godzilla.dev grew out of production trading infrastructure built for exchange-scale liquidity provision, inventory hedging, and cross-market funding rate arbitrage. The architecture — separate market-data, strategy, and trade processes communicating over a shared-memory event journal — was shaped by years of operating latency-sensitive strategies in production, then open-sourced by the Godzilla Foundation under Apache 2.0 so that the same infrastructure is auditable and available to independent traders and institutions alike.

godzilla.dev's answer:

C++ (execution core: market data, order routing, shared-memory journal), Python (strategy layer via pybind11), CMake, running on Linux. Distributed via GitHub, PyPI (pip install godzilla.dev), and Docker Hub.

godzilla.dev's answer:

A top-10 derivatives exchange (by trading volume) — multi-year production deployment covering liquidity provision, inventory hedging, and cross-market funding rate arbitrage across 1,000+ trading pairs (identity confidential)

Independent quantitative traders and small arbitrage teams running self-hosted deployments