English static mirror for SEO/GEO · AI-assisted translation · Read Chinese original

AlphaGPT Deep Dive: A 15-Year-Old Developer's Automated Factor Factory for Crypto Quant Trading

Forum topic · 小凯 · 2026-05-21

Summary

AlphaGPT is an open-source crypto quant trading framework by GitHub user imbue-bit, a 15-year-old developer who reportedly manages a ~5 million CNY quant fund. Rather than predicting prices with AI, it operates as an automated factor factory: a Transformer generates candidate trading factors as token sequences, a stack-based virtual machine (StackVM) executes them into interpretable mathematical formulas, a backtest engine scores them by Sharpe ratio and drawdown, and reinforcement learning (policy gradient) optimizes the generator. The system pulls Solana token and OHLCV data from Birdeye and DexScreener into Postgres/TimescaleDB, filters candidates with risk rules, and executes trades via the Jupiter DEX aggregator. The same author also released no_JIT, a Uniswap V4 Hook defending against JIT liquidity attacks using differential game theory and the Hamilton-Jacobi-Isaics framework. The README hints at a prior dispute that has been settled, suggesting the formerly closed-source profitable system was opened partly because discovered patterns decay once public. The project illustrates a broader trend: automating hypothesis generation in quant research via symbolic regression plus RL, while acknowledging that historically valid patterns eventually stop working as markets adapt.

Overview

AlphaGPT (https://github.com/imbue-bit/AlphaGPT) is an open-source crypto quant trading framework by GitHub user imbue-bit, a 15-year-old developer who reportedly manages a quant fund of roughly 5 million CNY. The project is not an "AI predicts coin price" tool — it is an automated factor factory built on deep reinforcement learning, released after having been a closed-source "money-making machine," per community commentary. The author has also published a companion paper on defending Uniswap V4 against JIT liquidity attacks using differential game theory.

Key Points

  • Core philosophy: not prediction, but discovery — find patterns that were statistically valid historically and assume they persist briefly.
  • Architecture layers: data_pipeline (Birdeye/DexScreener → Postgres/TimescaleDB), model_core (feature engineering + Transformer formula generation), strategy_manager (signals, risk, orders), execution (Solana RPC + Jupiter aggregator), dashboard (Streamlit).
  • Factor language: 18 features (log return, liquidity/FDV health, buy-sell pressure, volume acceleration, deviation from mean, volatility clustering, momentum reversal, etc.) and 12 operators (ADD/SUB/MUL/DIV, NEG/ABS/SIGN, GATE, JUMP, DECAY, DELAY1, MAX3) form a small executable language.
  • StackVM execution: formulas are token sequences executed on a stack-based VM. Example: [ret, fomo, MUL, liq_score, DIV, DECAY] computes a decayed, liquidity-normalized momentum signal. This makes every generated factor fully interpretable.
  • Training loop: Transformer generates candidates → StackVM executes → backtest scores via Sharpe ratio / max drawdown / win rate → policy-gradient RL updates the generator. This mirrors AlphaTensor's approach of modeling mathematical discovery as sequence generation.
  • Live execution: strategy scores top tokens, risk filters drop illiquid/high-slippage assets, orders route through Jupiter on Solana, positions persist to local JSON. The README warns that default parameters are not optimal for live trading.
  • no_JIT: The Companion Research Project

    The same author released no_JIT (https://github.com/imbue-bit/no_JIT), a Uniswap V4 Hook that models JIT (Just-In-Time) liquidity attacks as a predator-prey differential game under the Hamilton-Jacobi-Isaacs (HJI) framework. It computes Nash-equilibrium defensive strategies and enforces them in-hook, offering atomic deterrence, no oracle dependencies, and gas-efficient swaps. Paper: *Defense in Predatory Markets: A Differential Game Framework for AMM Liquidity via Uniswap V4 Hooks*.

    Author Profile

    imbue-bit's GitHub profile lists papers spanning deep learning theory, LLM alignment and inference, reward modeling, long-context decoding, hyperparameter loss landscapes, autonomous driving (VLA), and non-stationary deep learning for quant finance, plus solid DevOps/CTF experience. The profile quotes Nabokov's *Speak, Memory*.

    Controversy and Release Context

    The README notes "both parties have reached a settlement" and warns against ritual "check-in" issues, hinting at an earlier dispute. A near-identical copy exists (yuz0101/AlphaGPTCopy). Likely motivations for open-sourcing a formerly profitable system include strategy decay, reputation-building, or settlement terms.

    Strengths and Limitations

    Strengths: clean layered architecture; interpretability-first design; expressive 12-operator mini-language; Solana/meme-coin focus where liquidity actually is; strong mathematical grounding.

    Limitations: no dependency manifest or .env template; no pre-trained strategy file included (best_meme_strategy.json must be trained by the user); incomplete risk management (position sizing, stop-loss left to users); placeholder documentation.

    Deeper Significance

    AlphaGPT exemplifies the automation of hypothesis generation in quant research: humans define the search space of factors and operators, while Transformer + RL explore it at hour/day cycles instead of week/month human iteration — the same direction as AutoML and neural architecture search. Its fundamental constraint remains quant's core dilemma: any discovered and publicized pattern arbitrages itself away, which may itself be why the author open-sourced it.

    Links

  • AlphaGPT repo: https://github.com/imbue-bit/AlphaGPT
  • Technical details: https://github.com/imbue-bit/AlphaGPT/blob/main/CATREADME.md
  • no_JIT repo: https://github.com/imbue-bit/no_JIT
  • Author: https://github.com/imbue-bit
  • SourcePulse page: https://www.sourcepulse.org/projects/22459563

Tags

#quant-trading#alpha-gpt#reinforcement-learning#symbolic-regression#solana#defi#factor-mining#uniswap-v4

This page is an English static mirror generated for search and AI citation. It may be a full translation or structured summary of the Chinese original. Canonical interactive discussion lives on the Chinese page: https://zhichai.net/topic/177620527