Circuit Framework is a crypto-native multi-agent research and paper-trading framework that uses specialized analysts and a deterministic risk engine to approve or reject trades, never executing real orders.

Stars

399

7-day growth

-88

Forks

11

Open issues

0

License

Apache-2.0

Last updated

2026-07-16

AI repository intelligence
FR-AI / ANALYSIS

Why it is worth attention

It provides a deterministic, multi-agent research pipeline tailored for crypto markets, with offline testing and a transparent, risk-controlled paper trading environment built on Hyperliquid public data.

Who it is for

  • Crypto traders and quants
  • Developers building automated trading agents
  • Researchers studying multi-agent LLM frameworks
  • Educators and students learning about financial agent systems

Use cases

  • Paper-trading crypto strategies with deterministic risk checks
  • Backtesting multi-agent research pipelines on historical data
  • Educational experimentation with LLM-driven financial analysis
  • Prototyping and comparing strategy profiles (e.g., momentum vs. mean reversion)

Strengths

  • Offline unit tests with fixtures, no API key required for testing
  • Deterministic risk gate that enforces stop-loss, position limits, and volatility scalars
  • Multiple pre-built strategy profiles (balanced, momentum, derivatives, etc.)
  • Modular architecture with composable analysts and clear separation of concerns

Considerations

  • On-chain data not included; requires external provider configuration
  • LLM outputs may be incorrect; risk gate cannot invent unexpected edge cases
  • Paper fills use mid ± slippage and configured fees, not real exchange matching

README quick start

Installation

Description

Circuit Framework — multi-agent LLM trading research system

Related repositories

Similar projects matched by category, topics, and programming language.

lopopolo
Featured
lopopolo GitHub avatar

harness-engineering

Harness Engineering is a methodology for improving coding agent outputs by carefully crafting the environment around them—providing curated context, tools, and executable constraints that encode an organization’s nonfunctional requirements and cumulative lessons.

AI & Machine LearningAI Agents
2,390
slvDev
Featured
slvDev GitHub avatar

esp32-ai

A 28.9 million parameter language model runs on an $8 ESP32-S3 microcontroller entirely on-device, generating simple stories at about 9.5 tokens per second.

AI & Machine LearningLarge Language Models
1,960
littledivy
Featured
littledivy GitHub avatar

mimic

mimic captures traffic from any iOS or web app and automatically generates a Python client library that lets you call the app's API like a regular library.

AI & Machine Learning
1,482