Search

More Filters

Show More
Add Listing
Go Back

ai-hedge-fund-crypto

0
Finance & Web3
Report

Report Abuse

Basic Information

This repository provides an algorithmic trading framework focused on cryptocurrency markets that combines technical analysis, a directed acyclic graph workflow, and large language model reasoning to generate and evaluate trading signals. It is built around LangGraph-style computational graphs where modular nodes perform data fetching, multi-timeframe processing, strategy execution, risk evaluation, and portfolio decisioning. The system supports both backtesting and live analysis modes, is configurable via a central config.yaml and environment variables, and is designed to run with Python 3.9+ (Python 3.12 recommended) using the uv toolchain. It integrates with Binance for market data and planned order execution and supports multiple LLM providers for decision refinement. The repo also includes tooling for visualizing the computational graph, caching market data, running comprehensive backtests, and adding custom strategy modules.

Links

Stars
345
Language
App URL
https://github.com/51bitquant/ai-hedge-fund-crypto
Github Repository
https://github.com/51bitquant/ai-hedge-fund-crypto/blob/main/README.md

Categorization

App Details

Features
The project uses a node-based DAG architecture with separate start, data, strategy, risk management, and portfolio management nodes. It offers multi-timeframe analysis by dynamically creating data nodes for configured intervals and an ensemble approach that aggregates weighted signals from multiple strategies. Built-in strategies and indicators include MACD, RSI, Bollinger bands and support for custom indicators. LLM integration enables portfolio decision reasoning and supports providers such as OpenAI, Groq, OpenRouter, Gemini, Anthropic, and Ollama. Users can run detailed backtests with performance metrics and visualizations, generate live signals, and optionally execute trades on Binance once gateway functionality is enabled. The system is configured via config.yaml and .env files and is extensible by adding strategy classes to src/strategies.
Use Cases
For trading researchers and developers the framework centralizes data ingestion, indicator calculation, strategy testing, and decision orchestration in a reusable workflow so teams can iterate faster. Backtesting tools provide historical performance metrics and charts to validate strategies before risking capital. Multi-timeframe and ensemble signal aggregation aim to produce more robust signals across market regimes. LLM-enhanced portfolio management offers a way to combine human-readable reasoning with quantitative signals for position sizing and trade selection. The modular structure makes it straightforward to add or swap strategies, change intervals, and visualize the decision graph. Live mode enables real-time signal generation and, with proper API keys and permissions, eventual order execution on Binance while the README highlights cautious deployment and testing to manage financial risk.

Categories

Content Creation (5042)
Monetization & Business (2246)
Development Tools (1407)
Marketing & Social Media (1403)
Education & Career (1380)
Multi-Agent Platforms & Frameworks (1230)
Health & Life (957)
AI Resources (920)
Agents & Automation (778)
Data & Analytics (766)
Productivity Tools (679)
Writing & Editing (666)

Similar Listings

listing image

cyber-doctor

0 (0 review)
listing image

LLM-Powered-RAG-System

0 (0 review)
listing image

xpert

0 (0 review)
listing image

Curie

0 (0 review)
listing image

awesome-llm-plaza

0 (0 review)

Featured Listings

Tags

Please fill the required fields*