Market democratization through conversational AI represents a critical frontier in financial technology, yet cryptocurrency analysis remains dominated by institutional players with sophisticated toolchains. We introduce AICrypto-Assistant, the first open-source platform to integrate multi-agent large language model orchestration with executable technical analysis in a real-time conversational interface. Our system employs supervisor that intelligently routes natural language queries to specialized agents: a Market Analyst executing Python-based indicators (moving averages, volume-price relationships, money flow metrics), a News Researcher synthesizing market developments through filtered sentiment analysis, and a Knowledge Management component delivering contextual information via retrieval-augmented generation. Unlike existing black-box solutions, every analytical step remains transparent and auditable, addressing critical barriers in accessibility, information overload, and methodological opacity that exclude retail participants. Controlled evaluation with 20 participants over four weeks demonstrated remarkable effectiveness: 11% collective portfolio growth, 95% user satisfaction, and 60% achieving positive returns despite market volatility. The modular architecture enables seamless integration of additional indicators without core system modifications, supporting long-term extensibility while advancing Open Finance principles of transparent, inclusive financial intelligence.

Keywords - Cryptocurrency, FinTech, ExplainableAI, Multi‑Agent Systems, Open Finance, Retail Investing

[1] “Live cryptocurrency charts & market data | CoinMarketCap,” CoinMarketCap. https://coinmarketcap.com/charts/

[2] S. Han, Q. Zhang, Y. Yao, W. Jin, and Z. Xu, “LLM Multi-Agent Systems: Challenges and open Problems,” arXiv.org, Feb. 05, 2024. https://arxiv.org/abs/2402.03578

[3] I. Okpala, A. Golgoon, and A. R. Kannan, “Agentic AI Systems Applied to tasks in Financial Services: Modeling and model risk management crews,” arXiv.org, Feb. 08, 2025. https://arxiv.org/abs/2502.05439

[4] S. Han, J. Zhang, Y. Shen, K. Yan, and H. Li, “FinSphere, a Real-Time stock analysis agent powered by Instruction-Tuned LLMs and domain tools,” arXiv.org, Jan. 08, 2025. https://arxiv.org/abs/2501.12399

[5] H. Ding, Y. Li, J. Wang, and H. Chen, “Large language model agent in Financial Trading: A survey,” arXiv.org, Jul. 26, 2024. https://arxiv.org/abs/2408.06361

[6] T. Ma, J. Du, W. Huang, W. Wang, L. Xie, X. Zhong, and J.T. Zhou, “LLM Knows Geometry Better than Algebra: Numerical Understanding of LLM-Based Agents in A Trading Arena,” arXiv.org, Feb. 25, 2025. https://arxiv.org/abs/2502.17967

[7] G. Fatouros, K. Metaxas, J. Soldatos, and M. Karathanassis, “MarketSenseAI 2.0: Enhancing Stock Analysis through LLM Agents,” arXiv.org, Feb. 01, 2025. https://arxiv.org/abs/2502.00415

[8] K.-T. Tran, D. Dao, M.-D. Nguyen, Q.-V. Pham, B. O’Sullivan, and H. D. Nguyen, “Multi-Agent Collaboration Mechanisms: A survey of LLMs,” arXiv.org, Jan. 10, 2025. https://arxiv.org/abs/2501.06322

[9] A. De La Cruz, “Multi-Agent Large Language Models for Traditional Finance and Decentralized Finance”, Journal of Industrial Engineering & Applied Science, vol. 3, no. 1, pp. 10–19, Feb. 2025. https://www.suaspress.org/ojs/index.php/JIEAS/article/view/v3n1a02

[10] Y. Xiao, E. Sun, D. Luo, and W. Wang, “TradingAgents: Multi-Agents LLM Financial Trading Framework,” arXiv.org, Dec. 28, 2024. https://arxiv.org/abs/2412.20138

[11] Y. Xiao, E. Sun, D. Luo, and W. Wang, “TradingAgents: Multi-Agents LLM Financial Trading Framework,” arXiv.org, Dec. 28, 2024. https://arxiv.org/abs/2412.20138