Home / LLM agents & research
sadighian/crypto-rl
Record crypto order books and train a DDQN trading agent
What it is
A deep reinforcement learning toolkit built around cryptocurrency limit order book data. It can record order book updates, replay them later, and train a DDQN agent on that replayed market, so data capture and model training live in one workflow. Researchers exploring how reinforcement learning behaves on order book microstructure have a ready starting point here. It is research code focused on crypto markets and one agent type, not a production trading system.
At a glance
Research onlyOur rating, based on popularity, maintenance and how ready it is for real use.
| Best for | Professional quants |
|---|---|
| Used for | Strategy research, Backtesting |
| Markets | Crypto |
| Stack | Python |
| Learning curve | Steep learning curve |
| Practical value | Medium practical value |
| Cost | Free and open source |
| Hardware | GPU optional |
| Maintenance | No commits in over six months |
GitHub stars, last 30 days
Daily snapshots since 2026-09-28 (up to 30 days): −1 over the period, now 966. Gaps mean no snapshot was taken that day.
Deep Reinforcement Learning toolkit: record and replay cryptocurrency limit order book data & train a DDQN agent
Similar tools
Gym environment for reinforcement learning in crypto trading
High-frequency trading and market-making backtesting in Rust and Python
AI-oriented quantitative investment platform with full ML pipeline
Vectorized Python backtesting and strategy research toolkit
Event-driven backtesting engine for Python trading algorithms
LLM quant tools and market research for US stocks and crypto