// Master Moon Dev's Ai Agents Github with 48+ specialized agents, multi-exchange support, LLM abstraction, and autonomous trading capabilities across crypto markets
| name | moon-dev-trading-agents |
| description | Master Moon Dev's Ai Agents Github with 48+ specialized agents, multi-exchange support, LLM abstraction, and autonomous trading capabilities across crypto markets |
Expert knowledge for working with Moon Dev's experimental AI trading system that orchestrates 48+ specialized AI agents for cryptocurrency trading across Hyperliquid, Solana (BirdEye), Asterdex, and Extended Exchange.
Use this skill when:
For New Users: This repo uses Python 3.10.9. If using conda, the README shows setting up an environment named tflow, but you can name it whatever you want. If you don't use conda, standard pip/venv works fine too.
# Activate your Python environment (conda, venv, or whatever you use)
# Example with conda: conda activate tflow
# Example with venv: source venv/bin/activate
# Use whatever environment manager you prefer
# Run main orchestrator (controls multiple agents)
python src/main.py
# Run individual agent
python src/agents/trading_agent.py
python src/agents/risk_agent.py
python src/agents/rbi_agent.py
# Update requirements after adding packages
pip freeze > requirements.txt
src/
├── agents/ # 48+ specialized AI agents (<800 lines each)
├── models/ # LLM provider abstraction (ModelFactory)
├── strategies/ # User-defined trading strategies
├── scripts/ # Standalone utility scripts
├── data/ # Agent outputs, memory, analysis results
├── config.py # Global configuration
├── main.py # Main orchestrator loop
├── nice_funcs.py # Core trading utilities (~1,200 lines)
├── nice_funcs_hl.py # Hyperliquid-specific functions
├── nice_funcs_extended.py # Extended Exchange functions
└── ezbot.py # Legacy trading controller
Agents (src/agents/)
LLM Integration (src/models/)
ModelFactory.create_model('anthropic')Trading Utilities
nice_funcs.py: Core functions (Solana/BirdEye)nice_funcs_hl.py: Hyperliquid exchangenice_funcs_extended.py: Extended Exchange (X10)Configuration
config.py: Trading settings, risk limits, agent behavior.env: API keys and secrets (never expose these)Trading: trading_agent, strategy_agent, risk_agent, copybot_agent
Market Analysis: sentiment_agent, whale_agent, funding_agent, liquidation_agent, chartanalysis_agent
Content: chat_agent, clips_agent, tweet_agent, video_agent, phone_agent
Research: rbi_agent (codes backtests from videos/PDFs), research_agent, websearch_agent
Specialized: sniper_agent, solana_agent, tx_agent, million_agent, polymarket_agent, compliance_agent, swarm_agent
See AGENTS.md for complete list with descriptions.
# Activate your environment first
python src/agents/[agent_name].py
Each agent is standalone and can run independently.
python src/main.py
Runs multiple agents in loop based on ACTIVE_AGENTS dict in main.py.
Edit agent file or config:
EXCHANGE = "hyperliquid" # or "birdeye", "extended"
Then import corresponding functions:
if EXCHANGE == "hyperliquid":
from src import nice_funcs_hl as nf
elif EXCHANGE == "extended":
from src import nice_funcs_extended as nf
Edit src/config.py:
AI_MODEL = "claude-3-haiku-20240307" # Fast, cheap
# AI_MODEL = "claude-3-sonnet-20240229" # Balanced
# AI_MODEL = "claude-3-opus-20240229" # Most powerful
Or use ModelFactory per-agent:
from src.models.model_factory import ModelFactory
model = ModelFactory.create_model('deepseek') # or 'openai', 'groq', etc.
response = model.generate_response(system_prompt, user_content, temperature, max_tokens)
python src/agents/rbi_agent.py
Provide: YouTube URL, PDF, or trading idea text → DeepSeek-R1 extracts strategy logic → Generates backtesting.py compatible code → Executes backtest, returns metrics
See WORKFLOWS.md for more examples.
pip freeze > requirements.txtCreating new agents:
# 1. Use ModelFactory for LLM
from src.models.model_factory import ModelFactory
model = ModelFactory.create_model('anthropic')
# 2. Store outputs in src/data/
output_dir = "src/data/my_agent/"
# 3. Make independently executable
if __name__ == "__main__":
# Standalone logic here
# 4. Follow naming: [purpose]_agent.py
# 5. Add to config.py if needed
backtesting.py library (NOT built-in indicators)pandas_ta or talib for indicatorssrc/data/rbi/BTC-USD-15m.csvconfig.py: Trading settings
MONITORED_TOKENS, EXCLUDED_TOKENSusd_size, max_usd_order_sizeCASH_PERCENTAGE, MAX_LOSS_USD, MAX_GAIN_USDSLEEP_BETWEEN_RUNS_MINUTES, ACTIVE_AGENTSAI_MODEL, AI_MAX_TOKENS, AI_TEMPERATURE.env: Secrets (NEVER expose)
BIRDEYE_API_KEY, MOONDEV_API_KEY, COINGECKO_API_KEYANTHROPIC_KEY, OPENAI_KEY, DEEPSEEK_KEY, GROQ_API_KEY, GEMINI_KEYSOLANA_PRIVATE_KEY, HYPER_LIQUID_ETH_PRIVATE_KEY, RPC_ENDPOINTX10_API_KEY, X10_PRIVATE_KEY, X10_PUBLIC_KEY, X10_VAULT_IDHyperliquid (nice_funcs_hl.py)
market_buy(), market_sell(), get_position(), close_position()BirdEye/Solana (nice_funcs.py)
token_overview(), token_price(), get_ohlcv_data()Extended Exchange (nice_funcs_extended.py)
See docs/hyperliquid.md, docs/extended_exchange.md for exchange-specific guides.
Config/Input → Agent Init → API Data Fetch → Data Parsing →
LLM Analysis (via ModelFactory) → Decision Output →
Result Storage (CSV/JSON in src/data/) → Optional Trade Execution
Add new package:
# Make sure your environment is activated first
pip install package-name
pip freeze > requirements.txt
Read market data:
from src.nice_funcs import token_overview, get_ohlcv_data, token_price
overview = token_overview(token_address)
ohlcv = get_ohlcv_data(token_address, timeframe='1H', days_back=3)
price = token_price(token_address)
Execute trade (Hyperliquid):
from src import nice_funcs_hl as nf
nf.market_buy("BTC", usd_amount=100, leverage=10)
position = nf.get_position("BTC")
nf.close_position("BTC")
Execute trade (Extended):
from src import nice_funcs_extended as nf
nf.market_buy("BTC", usd_amount=100, leverage=15)
position = nf.get_position("BTC")
nf.close_position("BTC")
Current branch: main Main branch for PRs: main
Recent commits:
Modified files (current):
Main docs (docs/):
CLAUDE.md: Project overview and development guidelineshyperliquid.md, hyperliquid_setup.md: Hyperliquid exchangeextended_exchange.md: Extended Exchange (X10) setuprbi_agent.md: Research-Based Inference agentwebsearch_agent.md: Web search capabilitiesswarm_agent.md: Multi-agent coordination[agent_name].md: Individual agent docsREADME files:
README.md: Project overviewsrc/models/README.md: LLM provider guideMAX_LOSS_USD, MINIMUM_BALANCE_USDSLEEP_BETWEEN_RUNS_MINUTES)This is an experimental, educational project:
Goal: Democratize AI agent development through practical trading examples.
For complete agent list, see AGENTS.md For workflow examples, see WORKFLOWS.md For architecture details, see ARCHITECTURE.md
Built with 🌙 by Moon Dev
"Never over-engineer, always ship real trading systems."