Autohedge swarm

Skill mahmoud20138/Tradecraft/plugins/tradecraft/skills/autohedge-swarm

AutoHedge — enterprise-grade autonomous hedge fund using swarm agent architecture. Sequential pipeline: Director → Quant → Risk Manager → Execution agents. Risk-first design: position sizing before any trade execution. Currently supports Solana; CoinFrom its SKILL.md

Install

npx -y skills add mahmoud20138/Tradecraft --skill autohedge-swarm

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

3 things to look at

reads credentialsReads from 4 credential sources: `JUPITER_API_KEY` and 3 more.
10 stars10 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
runs commandsInstructs the agent to run 2 commands, including `pip install -U autohedge` and 1 more.

SKILL.md

3.1 KB, 665 tokens by cl100k_base, as published. Nobody here has run it

autohedge-swarm

USE FOR:

"autonomous hedge fund agent"
"swarm agents for trading"
"director + quant + risk manager pipeline"
"Solana autonomous trading"
"enterprise AI trading system"
"risk-first automated trading" tags: [swarm, agents, hedge-fund, autonomous, Solana, risk-and-portfolio, enterprise, multi-agent, quant] kind: framework category: quant-ml-trading

What Is AutoHedge?

Enterprise-grade autonomous agent hedge fund using swarm intelligence. Specialized agents sequentially handle strategy, analysis, risk, and execution.

Repo: https://github.com/The-Swarm-Corporation/AutoHedge
Install: pip install -U autohedge
Current: Solana trading (Coinbase planned)
Philosophy: Risk-first — position sizing happens before execution

Swarm Agent Pipeline

Director Agent
    ↓ Strategy generation + market context
Quant Agent
    ↓ Quantitative analysis + signal generation
Risk Manager Agent
    ↓ Position sizing + risk assessment + approval
Execution Agent
    ↓ Order construction + submission
Trade Output (JSON)

Installation

pip install -U autohedge

Environment variables:

JUPITER_API_KEY="..."          # Solana DEX aggregator
OPENAI_API_KEY="sk-..."        # or ANTHROPIC_API_KEY
WALLET_PRIVATE_KEY="..."       # Solana wallet

Usage

autohedge

Or programmatically:

from autohedge import AutoHedge

fund = AutoHedge(
    llm_provider="anthropic",     # Director/Quant use Claude
    risk_threshold=0.02,          # Max 2% portfolio risk per trade
    chain="solana",
)

result = fund.analyze_and_trade("SOL/USDC")
print(result)  # JSON: analysis + decision + risk metrics

Agent Responsibilities

Agent	Role
Director	Market context, strategy selection
Quant	Price analysis, signals, technicals
Risk Manager	Position sizing, max drawdown limits
Execution	Order construction, submission

Output Format (JSON)

{
  "ticker": "SOL/USDC",
  "director_analysis": "Bullish momentum...",
  "quant_signals": {"rsi": 58, "macd": "bullish"},
  "risk_assessment": {"position_size": 0.015, "stop_loss": 0.02},
  "decision": "BUY",
  "execution": {"order_type": "market", "size": 10.5}
}

Key Design Principles

Risk-first: Never execute without risk approval
Audit trail: Enterprise logging at every step
Modular: Swap any agent or add custom stages
Structured outputs: All agents return JSON for system integration

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.