crypto-claude-desk
Active·★ 63·MIT·Updated 2026-08-23
This project transforms Claude Code into a comprehensive crypto trading desk using a multi-agent system, entirely defined by markdown and MCP servers, eliminating the need for Python orchestration code. It features 7 coordinated AI agents that perform market analysis, technical analysis, risk assessment, and portfolio management for simulated trading and cognitive learning.
#Multi-Agent System#Crypto Trading#LLM Orchestration#Markdown Driven#Paper Trading#Cognitive Learning#AI Agents
01
Features
017 Coordinated AI Agents: Specialists for market monitoring, technical analysis, news sentiment, risk, portfolio, learning, and system building.
02Markdown-Driven Orchestration: Agents, tools, and routing logic are defined in markdown files, requiring zero Python orchestration code.
0383 Real-time Tools via 9 MCP Servers: Access to various crypto data sources, exchanges, technical indicators, and on-chain analytics.
04Cognitive Learning System: Tracks predictions, evaluates trade outcomes in natural language, builds setup-centric track records, and maintains a pattern library.
05Paper Trading & Autonomous Mode: Supports simulated trading with $10,000 virtual capital and can run autonomously via cron for continuous monitoring and analysis.
02
Compatibility
Claude Code
Platform
Verified via docs
Python 3.11+
Runtime
Verified via docs
MacOS
OS
Verified via docs
Linux
OS
Verified via docs
Windows
OS
Verified via docs
03
Quick start
1
$ claude plugin marketplace add hugoguerrap/crypto-claude-desk
2
$ claude plugin install crypto-trading-desk@hugoguerrap
3
$ claude
04
Use cases
↳Automated Crypto Market Analysis: Get live market snapshots, detailed technical/news analysis, and trading decisions for various cryptocurrencies.
↳AI-Powered Simulated Trading: Practice crypto trading strategies with a paper trading system that learns and improves over time.
↳Multi-Agent System Development & Prototyping: Serve as a template for building new multi-agent systems for other domains using Claude Code's native agent capabilities.
↳Educational Tool for AI & Crypto: Understand how AI agents can collaborate for complex tasks and explore crypto market dynamics without real financial risk.
↳Continuous Market Monitoring & Alerting: Configure autonomous loops to monitor trades, validate predictions, and generate reports.
05
Alternatives
suede-creator-skills★ 125
67 open-source Agent Skills for Claude Code and Codex: Full Send orchestration, A-F code review, AI evals, CI ship-gates, design, copy, SEO/AEO/GEO, app shipping, creator rights, and consumer recovery.
www.gamedev.pl★ 15
Point Claude Code, Cursor, or any MCP-capable agent at this server and it builds a real, playable browser game for www.gamedev.pl. The platform itself is built by agents too — open source, shipped in public.
thread-keeper★ 13
Multi-agent shared brain across Claude Code/Desktop, Codex, Gemini, Copilot, VS Code. Cross-session memory, self-improving skill loops, inter-agent signaling — one local MCP server.
PraisonAI★ 9.3k
PraisonAI is a production-ready Multi AI Agents framework, designed to create AI Agents to automate and solve problems ranging from simple tasks to complex challenges. It provides a low-code solution to streamline the building and management of multi-agent LLM systems, emphasising simplicity, customisation, and effective human-agent collaboration.
ag2★ 5.0k
AG2 (formerly AutoGen): The Open-Source AgentOS. Join us at: https://discord.gg/sNGSwQME3x
AssetOpsBench★ 2.4k
AssetOpsBench - Industry 4.0: A unified benchmark and framework for building, orchestrating, and evaluating domain-specific AI agents for Industry 4.0 asset operations and maintenance, with 460+ scenarios, 4 specialist agents (IoT, FMSR, TSFM, Work Order), and multi-agent orchestration blueprints (MetaAgent, AgentHive) over MCP.
Comments
Log in to leave a comment
No comments yet. Be the first!