#117117th of 118 in Agent frameworks and SDKsFor finance and business, trading, stocks and crypto, finance and accounting
autohedge
Multi-agent Python pipeline that analyzes markets and trades on Solana
- Stars
- 6.7k
- License
- MIT
- Last commit
- Mar 2026
- Language
- Python
1,332 on 21 Apr 20266,679 on 10 Nov 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
AutoHedge chains four agents (Director, Quant, Risk Manager, Execution) built on the Swarms framework. They generate a trading thesis, run technical analysis, size the position and place orders on Solana, with JSON-structured output and configurable logging. Coinbase and other exchanges are listed as planned, not available.
Who it is for: Developers experimenting with autonomous LLM-driven crypto trading on Solana
Strengths
- Clear four-stage pipeline: thesis, quant analysis, risk sizing, execution
- Structured JSON output suitable for downstream systems
- Installs with pip; built on the Swarms agent framework
- Configurable logging for audit and debugging
Weaknesses
- Only Solana is supported; Coinbase and other exchanges are not yet available
- Needs a wallet private key in environment variables to trade
- Basic usage section is just `autohedge`, with no real code example
- No backtesting or performance results documented
What it needs
- no GPU
- Needs Swarms, Jupiter API key, OpenAI API key, Anthropic API key, Solana wallet private key
- Models: OpenAI, Anthropic
Quick answers
Is autohedge open source?
Yes. Its code is on GitHub under the MIT license.
Does autohedge need a GPU?
No, it runs without one.
Also in Agent frameworks and SDKs
See all 118| Rank | Project | Score |
|---|---|---|
| 1 | ppt-masterAgent skill that turns documents into natively editable PowerPoint decks | 95 out of 100 |
| 2 | openai-agents-pythonPython SDK for multi-agent workflows with handoffs, guardrails and tracing | 91 out of 100 |
| 3 | mastraTypeScript framework for building AI agents, workflows and MCP servers | 91 out of 100 |
| #4 | browser-usePython library that lets an LLM agent control a web browser | 90 out of 100 |
| #5 | copilotkitSDK for adding agent chat, generative UI and shared state to apps | 90 out of 100 |