graph LR
Agent_Orchestration_Core["Agent Orchestration Core"]
Pydantic_AI_Coder_Agent["Pydantic AI Coder Agent"]
Agent_Tooling_Utilities["Agent Tooling & Utilities"]
Documentation_Ingestion_System["Documentation Ingestion System"]
Refiner_Agents["Refiner Agents"]
Advisor_Agent["Advisor Agent"]
Streamlit_UI_Configuration_Management["Streamlit UI - Configuration & Management"]
Streamlit_UI_Agent_Interaction_Service_Control["Streamlit UI - Agent Interaction & Service Control"]
Streamlit_UI_Documentation_Management["Streamlit UI - Documentation Management"]
Agent_Orchestration_Core -- "Orchestrates" --> Pydantic_AI_Coder_Agent
Agent_Orchestration_Core -- "Orchestrates" --> Refiner_Agents
Agent_Orchestration_Core -- "Orchestrates" --> Advisor_Agent
Agent_Orchestration_Core -- "Utilizes" --> Agent_Tooling_Utilities
Pydantic_AI_Coder_Agent -- "Utilizes" --> Agent_Tooling_Utilities
Refiner_Agents -- "Utilizes" --> Agent_Tooling_Utilities
Advisor_Agent -- "Utilizes" --> Agent_Tooling_Utilities
Streamlit_UI_Documentation_Management -- "Initiates" --> Documentation_Ingestion_System
Streamlit_UI_Agent_Interaction_Service_Control -- "Invokes" --> Agent_Orchestration_Core
Streamlit_UI_Configuration_Management -- "Manages" --> Documentation_Ingestion_System
click Agent_Orchestration_Core href "https://github.com/CodeBoarding/GeneratedOnBoardings/blob/main/Archon/Agent Orchestration Core.md" "Details"
click Pydantic_AI_Coder_Agent href "https://github.com/CodeBoarding/GeneratedOnBoardings/blob/main/Archon/Pydantic AI Coder Agent.md" "Details"
click Agent_Tooling_Utilities href "https://github.com/CodeBoarding/GeneratedOnBoardings/blob/main/Archon/Agent Tooling & Utilities.md" "Details"
click Documentation_Ingestion_System href "https://github.com/CodeBoarding/GeneratedOnBoardings/blob/main/Archon/Documentation Ingestion System.md" "Details"
click Refiner_Agents href "https://github.com/CodeBoarding/GeneratedOnBoardings/blob/main/Archon/Refiner Agents.md" "Details"
click Advisor_Agent href "https://github.com/CodeBoarding/GeneratedOnBoardings/blob/main/Archon/Advisor Agent.md" "Details"
click Streamlit_UI_Configuration_Management href "https://github.com/CodeBoarding/GeneratedOnBoardings/blob/main/Archon/Streamlit UI - Configuration & Management.md" "Details"
click Streamlit_UI_Agent_Interaction_Service_Control href "https://github.com/CodeBoarding/GeneratedOnBoardings/blob/main/Archon/Streamlit UI - Agent Interaction & Service Control.md" "Details"
click Streamlit_UI_Documentation_Management href "https://github.com/CodeBoarding/GeneratedOnBoardings/blob/main/Archon/Streamlit UI - Documentation Management.md" "Details"
This architecture analysis describes the high-level data flow and component interactions within the Archon project. The system is centered around an Agent Orchestration Core that coordinates various AI agents (Coder, Refiners, Advisor) to achieve specific tasks, primarily code generation and refinement. A robust Documentation Ingestion System feeds relevant information to these agents via a shared Agent Tooling & Utilities layer. User interaction and system management are handled through a set of Streamlit-based User Interface components, allowing for configuration, agent interaction, and documentation management.
The central control module responsible for initiating and coordinating various AI agents (Coder, Advisor, Refiners) and defining their operational scope within the Archon system. It manages the overall workflow of agent creation and refinement, routing user messages and finishing conversations.
Related Classes/Methods:
Archon.archon.archon_graph:define_scope_with_reasoner(83:117)Archon.archon.archon_graph:advisor_with_examples(120:143)Archon.archon.archon_graph:coder_agent(146:204)Archon.archon.archon_graph:refine_prompt(234:245)Archon.archon.archon_graph:refine_tools(248:266)Archon.archon.archon_graph:refine_agent(269:286)Archon.archon.archon_graph:route_user_message(216:231)Archon.archon.archon_graph:finish_conversation(289:309)
An intelligent agent specialized in generating code, primarily by interacting with and leveraging documentation. It is designed to produce structured outputs, likely using Pydantic models, and is a core component in the agent creation process.
Related Classes/Methods:
Archon.archon.pydantic_ai_coder:pydantic_ai_coder(44:49)Archon.archon.pydantic_ai_coder:PydanticAIDeps(41:45)Archon.archon.pydantic_ai_coder:retrieve_relevant_documentation(67:78)Archon.archon.pydantic_ai_coder:list_documentation_pages(81:88)Archon.archon.pydantic_ai_coder:get_page_content(91:102)
A foundational library providing essential tools and utility functions for various agents, including capabilities for documentation retrieval, page content access, file content access, and text embedding generation. These tools abstract away the complexities of interacting with external services like Supabase and OpenAI.
Related Classes/Methods:
archon.agent_tools:get_embedding(12:22)archon.agent_tools:retrieve_relevant_documentation_tool(24:57)archon.agent_tools:list_documentation_pages_tool(59:84)archon.agent_tools:get_page_content_tool(86:123)archon.agent_tools:get_file_content_tool(full file reference)
Manages the entire lifecycle of documentation processing, from crawling and extracting content to chunking, embedding, and storing it for efficient retrieval by AI agents. It handles the interaction with external documentation sources and the Supabase database.
Related Classes/Methods:
Archon.archon.crawl_pydantic_ai_docs:CrawlProgressTracker(64:141)Archon.archon.crawl_pydantic_ai_docs:chunk_text(143:186)Archon.archon.crawl_pydantic_ai_docs:get_title_and_summary(188:208)Archon.archon.crawl_pydantic_ai_docs:get_embedding(210:220)Archon.archon.crawl_pydantic_ai_docs:process_chunk(222:246)Archon.archon.crawl_pydantic_ai_docs:insert_chunk(248:266)Archon.archon.crawl_pydantic_ai_docs:process_and_store_document(268:310)Archon.archon.crawl_pydantic_ai_docs:crawl_parallel_with_requests(332:402)Archon.archon.crawl_pydantic_ai_docs:main_with_requests(433:488)Archon.archon.crawl_pydantic_ai_docs:start_crawl_with_requests(490:507)archon.crawl_pydantic_ai_docs:clear_existing_records(421:429)archon.crawl_pydantic_ai_docs:get_pydantic_ai_docs_urls(402:419)
A collection of AI agents dedicated to enhancing and optimizing various aspects of the AI agent being built, including refining the prompt, the tools used, and the agent's definition itself. These agents provide iterative improvement capabilities.
Related Classes/Methods:
archon.refiner_agents.tools_refiner_agent:tools_refiner_agent(44:49)archon.refiner_agents.tools_refiner_agent:ToolsRefinerDeps(42:44)archon.refiner_agents.agent_refiner_agent:agent_refiner_agent(44:49)archon.refiner_agents.agent_refiner_agent:AgentRefinerDeps(42:44)archon.refiner_agents.prompt_refiner_agent:prompt_refiner_agent(30:33)
An AI agent designed to provide guidance and recommendations, potentially by leveraging a knowledge base of examples and pre-built tools/MCP servers. It helps in establishing a starting point for the AI agent creation process.
Related Classes/Methods:
archon.advisor_agent:advisor_agent(44:49)archon.advisor_agent:AdvisorDeps(37:38)archon.advisor_agent:get_file_content(60:70)
Provides the user interface for managing various aspects of the Archon system, including Multi-Component Project (MCP) configurations, database interactions, and environment variable settings. It allows users to set up and monitor the system.
Related Classes/Methods:
Archon.streamlit_pages.mcp:mcp_tab(67:172)Archon.streamlit_pages.mcp:get_paths(6:18)Archon.streamlit_pages.mcp:generate_mcp_config(20:65)Archon.streamlit_pages.database:database_tab(59:180)Archon.streamlit_pages.database:load_sql_template(9:12)Archon.streamlit_pages.database:get_supabase_sql_editor_url(14:30)Archon.streamlit_pages.database:show_manual_sql_instructions(32:57)
Offers user interfaces for direct interaction with Archon agents through a chat interface and for monitoring and controlling the underlying agent services. This component allows users to initiate and observe the agent's execution.
Related Classes/Methods:
Archon.streamlit_pages.agent_service:agent_service_tab(13:230)Archon.streamlit_pages.agent_service:is_service_running(24:28)Archon.streamlit_pages.agent_service:kill_process_on_port(30:68)Archon.streamlit_pages.chat:chat_tab(41:86)Archon.streamlit_pages.chat:run_agent_with_streaming(17:39)
Provides a dedicated user interface for managing the documentation within Archon, allowing users to initiate crawls and clear existing documentation records. It displays the progress and status of documentation ingestion.
Related Classes/Methods: