# zda25m005-netizen/agentic-ai-os architecture

> Architecture diagram of the GitHub repository zda25m005-netizen/agentic-ai-os, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2026-10-01). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/zda25m005-netizen/agentic-ai-os
- Repository: https://github.com/zda25m005-netizen/agentic-ai-os

## Overview

Enterprise Agentic AI OS provides agent-driven research and career workflows through a FastAPI service, with a browser interface, retrieval, persistent missions and memory, and report generation. The documented request path is a client submitting a goal, the agent planning and using tools, then returning an answer; a separate RAG path ingests documents and produces cited answers. The graph also preserves the documented GraphRAG, observability, feedback, and fine-tuning capabilities. Some subsystem links are grounded only in README or import references; unsampled implementation details are not inferred.

Main entry points: [`app/api/main.py`](https://github.com/zda25m005-netizen/agentic-ai-os/blob/main/app/api/main.py) (FastAPI service), [`app/agents/graph.py`](https://github.com/zda25m005-netizen/agentic-ai-os/blob/main/app/agents/graph.py) (Agent graph), [`app/missions/runtime.py`](https://github.com/zda25m005-netizen/agentic-ai-os/blob/main/app/missions/runtime.py) (Mission runtime), [`app/missions/worker.py`](https://github.com/zda25m005-netizen/agentic-ai-os/blob/main/app/missions/worker.py) (Mission worker)

## Diagram (Mermaid)

```mermaid
flowchart TD

subgraph group_interface["Client Interface"]
  node_frontend["Web workspace"]
  node_api["FastAPI service<br/>[main.py]"]
  node_knowledge_api["Knowledge API client<br/>[knowledgeApi.ts]"]
end

subgraph group_orchestration["Agent Orchestration"]
  node_agent_graph["Agent graph<br/>[graph.py]"]
  node_agent_stages["Planner executor critic"]
  node_tool_loop["Tool use<br/>[tool_loop.py]"]
  node_tool_registry["Tool registry<br/>[registry.py]"]
end

subgraph group_knowledge["Knowledge Retrieval"]
  node_rag_ingest["Document ingestion<br/>[ingest.py]"]
  node_rag_retrieval["Hybrid retrieval<br/>[retriever.py]"]
  node_vector_store[("Vector store<br/>[vectorstore.py]")]
  node_graph_rag["GraphRAG"]
end

subgraph group_missions["Missions And Reports"]
  node_mission_api["Mission endpoints<br/>[missions.py]"]
  node_mission_worker["Mission worker<br/>[worker.py]"]
  node_mission_runtime["Mission runtime<br/>[runtime.py]"]
  node_mission_store[("Mission repository<br/>[repository.py]")]
  node_analysis["Evidence analysis<br/>[pipeline.py]"]
  node_report_render["Report rendering<br/>[pipeline.py]"]
  node_career_services["Career services"]
end

subgraph group_platform["Platform Services"]
  node_memory[("Long-term memory<br/>[orchestrator.py]")]
  node_llm["LLM client<br/>[llm.py]"]
  node_feedback["Feedback loop"]
  node_observability["Metrics and tracing"]
  node_finetuning["LoRA pipeline"]
end

node_client(("Client"))

node_client -->|"uses"| node_frontend
node_client -->|"calls"| node_api
node_api -->|"runs"| node_agent_graph
node_agent_graph -->|"dispatches"| node_agent_stages
node_agent_graph -.->|"uses"| node_tool_loop
node_tool_loop -.->|"invokes"| node_tool_registry
node_api -->|"answers with RAG"| node_rag_retrieval
node_rag_ingest -->|"writes vectors"| node_vector_store
node_rag_retrieval -->|"searches"| node_vector_store
node_api -->|"offers GraphRAG"| node_graph_rag
node_api -->|"registers routes"| node_mission_api
node_mission_worker -->|"ticks"| node_mission_runtime
node_mission_worker -->|"lists missions"| node_mission_store
node_mission_runtime -.->|"persists state"| node_mission_store
node_mission_runtime -.->|"builds evidence"| node_analysis
node_analysis -.->|"supplies artifact"| node_report_render
node_agent_graph -->|"uses memory"| node_memory
node_agent_stages -.->|"calls"| node_llm
node_api -->|"records feedback"| node_feedback
node_api -->|"exposes metrics"| node_observability
node_llm -->|"records usage"| node_observability
node_api -.->|"serves career routes"| node_career_services
node_api -->|"supports fine-tuned serving"| node_finetuning
node_knowledge_api -.->|"serves knowledge UI"| node_frontend

click node_frontend "https://github.com/zda25m005-netizen/agentic-ai-os/tree/main/frontend/app"
click node_api "https://github.com/zda25m005-netizen/agentic-ai-os/blob/main/app/api/main.py"
click node_agent_graph "https://github.com/zda25m005-netizen/agentic-ai-os/blob/main/app/agents/graph.py"
click node_agent_stages "https://github.com/zda25m005-netizen/agentic-ai-os/tree/main/app/agents"
click node_tool_loop "https://github.com/zda25m005-netizen/agentic-ai-os/blob/main/app/agents/tool_loop.py"
click node_tool_registry "https://github.com/zda25m005-netizen/agentic-ai-os/blob/main/app/tools/registry.py"
click node_rag_ingest "https://github.com/zda25m005-netizen/agentic-ai-os/blob/main/app/rag/ingest.py"
click node_rag_retrieval "https://github.com/zda25m005-netizen/agentic-ai-os/blob/main/app/rag/retriever.py"
click node_vector_store "https://github.com/zda25m005-netizen/agentic-ai-os/blob/main/app/rag/vectorstore.py"
click node_graph_rag "https://github.com/zda25m005-netizen/agentic-ai-os/tree/main/app/graph"
click node_mission_api "https://github.com/zda25m005-netizen/agentic-ai-os/blob/main/app/api/missions.py"
click node_mission_worker "https://github.com/zda25m005-netizen/agentic-ai-os/blob/main/app/missions/worker.py"
click node_mission_runtime "https://github.com/zda25m005-netizen/agentic-ai-os/blob/main/app/missions/runtime.py"
click node_mission_store "https://github.com/zda25m005-netizen/agentic-ai-os/blob/main/app/missions/repository.py"
click node_analysis "https://github.com/zda25m005-netizen/agentic-ai-os/blob/main/app/analysis/pipeline.py"
click node_report_render "https://github.com/zda25m005-netizen/agentic-ai-os/blob/main/app/exec/latex/pipeline.py"
click node_memory "https://github.com/zda25m005-netizen/agentic-ai-os/blob/main/app/memory/orchestrator.py"
click node_llm "https://github.com/zda25m005-netizen/agentic-ai-os/blob/main/app/core/llm.py"
click node_feedback "https://github.com/zda25m005-netizen/agentic-ai-os/tree/main/app/feedback"
click node_observability "https://github.com/zda25m005-netizen/agentic-ai-os/tree/main/app/obs"
click node_finetuning "https://github.com/zda25m005-netizen/agentic-ai-os/tree/main/app/finetune"
click node_career_services "https://github.com/zda25m005-netizen/agentic-ai-os/tree/main/app"
click node_knowledge_api "https://github.com/zda25m005-netizen/agentic-ai-os/blob/main/frontend/app/lib/knowledgeApi.ts"

classDef toneNeutral fill:#f8fafc,stroke:#334155,stroke-width:1.5px,color:#0f172a
classDef toneBlue fill:#dbeafe,stroke:#2563eb,stroke-width:1.5px,color:#172554
classDef toneAmber fill:#fef3c7,stroke:#d97706,stroke-width:1.5px,color:#78350f
classDef toneMint fill:#dcfce7,stroke:#16a34a,stroke-width:1.5px,color:#14532d
classDef toneRose fill:#ffe4e6,stroke:#e11d48,stroke-width:1.5px,color:#881337
classDef toneIndigo fill:#e0e7ff,stroke:#4f46e5,stroke-width:1.5px,color:#312e81
classDef toneTeal fill:#ccfbf1,stroke:#0f766e,stroke-width:1.5px,color:#134e4a
class node_frontend,node_api,node_knowledge_api,node_client toneBlue
class node_agent_graph,node_agent_stages,node_tool_loop,node_tool_registry toneAmber
class node_rag_ingest,node_rag_retrieval,node_vector_store,node_graph_rag toneMint
class node_mission_api,node_mission_worker,node_mission_runtime,node_mission_store,node_analysis,node_report_render,node_career_services toneRose
class node_memory,node_llm,node_feedback,node_observability,node_finetuning toneIndigo
```

## Components

### Client Interface

- [Web workspace](https://github.com/zda25m005-netizen/agentic-ai-os/tree/main/frontend/app): `frontend/app`
- [FastAPI service](https://github.com/zda25m005-netizen/agentic-ai-os/blob/main/app/api/main.py): `app/api/main.py`
- [Knowledge API client](https://github.com/zda25m005-netizen/agentic-ai-os/blob/main/frontend/app/lib/knowledgeApi.ts): `frontend/app/lib/knowledgeApi.ts`

### Agent Orchestration

- [Agent graph](https://github.com/zda25m005-netizen/agentic-ai-os/blob/main/app/agents/graph.py): `app/agents/graph.py`
- [Planner executor critic](https://github.com/zda25m005-netizen/agentic-ai-os/tree/main/app/agents): `app/agents`
- [Tool use](https://github.com/zda25m005-netizen/agentic-ai-os/blob/main/app/agents/tool_loop.py): `app/agents/tool_loop.py`
- [Tool registry](https://github.com/zda25m005-netizen/agentic-ai-os/blob/main/app/tools/registry.py): `app/tools/registry.py`

### Knowledge Retrieval

- [Document ingestion](https://github.com/zda25m005-netizen/agentic-ai-os/blob/main/app/rag/ingest.py): `app/rag/ingest.py`
- [Hybrid retrieval](https://github.com/zda25m005-netizen/agentic-ai-os/blob/main/app/rag/retriever.py): `app/rag/retriever.py`
- [Vector store](https://github.com/zda25m005-netizen/agentic-ai-os/blob/main/app/rag/vectorstore.py): `app/rag/vectorstore.py`
- [GraphRAG](https://github.com/zda25m005-netizen/agentic-ai-os/tree/main/app/graph): `app/graph`

### Missions And Reports

- [Mission endpoints](https://github.com/zda25m005-netizen/agentic-ai-os/blob/main/app/api/missions.py): `app/api/missions.py`
- [Mission worker](https://github.com/zda25m005-netizen/agentic-ai-os/blob/main/app/missions/worker.py): `app/missions/worker.py`
- [Mission runtime](https://github.com/zda25m005-netizen/agentic-ai-os/blob/main/app/missions/runtime.py): `app/missions/runtime.py`
- [Mission repository](https://github.com/zda25m005-netizen/agentic-ai-os/blob/main/app/missions/repository.py): `app/missions/repository.py`
- [Evidence analysis](https://github.com/zda25m005-netizen/agentic-ai-os/blob/main/app/analysis/pipeline.py): `app/analysis/pipeline.py`
- [Report rendering](https://github.com/zda25m005-netizen/agentic-ai-os/blob/main/app/exec/latex/pipeline.py): `app/exec/latex/pipeline.py`
- [Career services](https://github.com/zda25m005-netizen/agentic-ai-os/tree/main/app): `app`

### Platform Services

- [Long-term memory](https://github.com/zda25m005-netizen/agentic-ai-os/blob/main/app/memory/orchestrator.py): `app/memory/orchestrator.py`
- [LLM client](https://github.com/zda25m005-netizen/agentic-ai-os/blob/main/app/core/llm.py): `app/core/llm.py`
- [Feedback loop](https://github.com/zda25m005-netizen/agentic-ai-os/tree/main/app/feedback): `app/feedback`
- [Metrics and tracing](https://github.com/zda25m005-netizen/agentic-ai-os/tree/main/app/obs): `app/obs`
- [LoRA pipeline](https://github.com/zda25m005-netizen/agentic-ai-os/tree/main/app/finetune): `app/finetune`

### Other components

- **Client**

## Connections

- Client → Web workspace: uses (evidence: `README.md`)
- Client → FastAPI service: calls (evidence: `README.md`)
- FastAPI service → Agent graph: runs (evidence: `app/api/main.py`)
- Agent graph → Planner executor critic: dispatches (evidence: `app/agents/graph.py`)
- Agent graph → Tool use: uses
- Tool use → Tool registry: invokes
- FastAPI service → Hybrid retrieval: answers with RAG (evidence: `README.md`)
- Document ingestion → Vector store: writes vectors (evidence: `app/rag/ingest.py`)
- Hybrid retrieval → Vector store: searches (evidence: `app/rag/retriever.py`)
- FastAPI service → GraphRAG: offers GraphRAG (evidence: `README.md`)
- FastAPI service → Mission endpoints: registers routes (evidence: `app/api/main.py`)
- Mission worker → Mission runtime: ticks (evidence: `app/missions/worker.py`)
- Mission worker → Mission repository: lists missions (evidence: `app/missions/worker.py`)
- Mission runtime → Mission repository: persists state
- Mission runtime → Evidence analysis: builds evidence
- Evidence analysis → Report rendering: supplies artifact
- Agent graph → Long-term memory: uses memory (evidence: `app/agents/graph.py`)
- Planner executor critic → LLM client: calls (evidence: `app/agents/graph.py`)
- FastAPI service → Feedback loop: records feedback (evidence: `README.md`)
- FastAPI service → Metrics and tracing: exposes metrics (evidence: `README.md`)
- LLM client → Metrics and tracing: records usage (evidence: `app/core/llm.py`)
- FastAPI service → Career services: serves career routes (evidence: `app/api/main.py`)
- FastAPI service → LoRA pipeline: supports fine-tuned serving (evidence: `README.md`)
- Knowledge API client → Web workspace: serves knowledge UI (evidence: `frontend/app/lib/knowledgeApi.ts`)
