evolving-agents

get the best of both worlds: the conceptual flexibility of LLMunix with the high-performance, low-cost execution of a compiled framework. The article is a deep dive into the architecture and the journey that led us here. I'm looking for critical feedback on the core concept. Does this JIT/LORA compiler approach seem viable? What are the potential pitfalls we're not seeing? We're planning to build a complete, open-source POC of this system, and we're actively looking for feedback and potential collaborators. Happy to answer any questions.

-> Process -> Execute flow managed by the SystemAgent. The recent discussions on ACP (https://github.com/orgs/i-am-bee/discussions/284) have been super insightful and are guiding the next steps: Dual Bus Architecture: Based on @ismaelfaro's suggestion, I'm planning to split the SmartAgentBus implementation into a dedicated system bus (for metadata, discovery, system-level messages) and a data bus (for agent-to-agent payload communication). This feels like a cleaner way to manage the different communication needs. Smart Context/Memory: Addressing concerns raised by @QuantGeekDev and others about context pollution and determinism, I'll be exploring concepts for smart memory and smart context. The goal is to develop mechanisms that help agents pass only the most relevant context during interactions over the agent bus, potentially using prioritization or summarization. I also evaluated how MCP might fit in. Components like the SmartLibrary or SmartAgentBus could conceptually act as MCP servers, while agents like SystemAgent or ArchitectZero could be MCP clients. However, I ran into a fundamental question: If agents themselves can also act as tools (like in the OpenAI Agents SDK), does requiring potentially numerous MCP servers (one per agent/tool instance) scale well? Or is a different abstraction needed for direct agent/tool comms? Given this, my immediate focus will be on refining the core communication patterns (dual bus, smart context) before deciding on the best way to integrate MCP specifically for agent-to-agent communication. This is all evolving (pun intended!), and I'm actively working on the dual bus and smart context POCs now. You can see the current architecture details in the ARCHITECTURE.md link above. Keen to hear your thoughts on this direction!

healthcare assessment systems, autonomously designing teams of agents capable of managing complex tasks. Please note that the toolkit is actively under development. The ultimate aim is to achieve robust production capabilities, but more improvements—especially to the Agent Bus—are needed before reaching that stage. Explore the latest updates and examples: GitHub Repository: https://github.com/matiasmolinas/evolving-agents Run new examples: python evolving_agents/financial_example.py python evolving_agents/medical_example.py Your ongoing feedback is very important. Feel free to share your thoughts on Architect-Zero and these recent updates!

k across different environments, improving scalability and coordination. Why? Most agent-based AI frameworks today require manual orchestration. This project takes a different approach by allowing agents to decide and adapt based on the task at hand. Instead of always creating new agents, it determines if existing ones can be reused or evolved. Example Use Case: Let’s say you need an invoice analysis agent. Instead of manually configuring one, our framework: Checks if a similar agent exists (e.g., a document analyzer) Decides whether to reuse, evolve, or create a new agent Runs the best agent and returns the extracted information Here's a simple example in Python: import asyncio from evolving_agents.smart_library.smart_library import SmartLibrary from evolving_agents.core.llm_service import LLMService from evolving_agents.core.system_agent import SystemAgent async def main(): library = SmartLibrary("agent_library.json") llm = LLMService(provider="openai", model="gpt-4o") system = SystemAgent(library, llm) result = await system.decide_and_act( request="I need an agent that can analyze invoices and extract the total amount", domain="document_processing", record_type="AGENT" ) print(f"Decision: {result['action']}") # 'reuse', 'evolve', or 'create' print(f"Agent: {result['record']['name']}") if __name__ == "__main__": asyncio.run(main()) Next Steps Validating in real-world use cases and improving agent evolution strategies Adding distributed multi-agent support for better scalability Full integration with BeeAI Agent Communication Protocol (ACP) Better visualization tools for debugging Would love feedback from the HN community! What features would you like to see? Repo: https://github.com/matiasmolinas/evolving-agents