# nyallaiah/autonomous-voice-agent- architecture

> Architecture diagram of the GitHub repository nyallaiah/autonomous-voice-agent-, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2026-10-02). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/nyallaiah/autonomous-voice-agent-
- Repository: https://github.com/nyallaiah/autonomous-voice-agent-

## Overview

AVADP turns client meeting audio/transcripts and business documents into a deployable voice-agent package. Users create a project, provide source material, run the delivery pipeline, review generated requirements, prompts, call flows, tests and reliability results, then download or sandbox the agent. The workflow excerpt confirms orchestration and early stages; the README documents the broader agent stages and deliverables. Several later-stage implementation details and frontend-to-backend wiring are not shown, so those links are documented or marked unverified rather than inferred from module names.

Main entry points: [`backend/workflows/langgraph_workflow.py`](https://github.com/nyallaiah/autonomous-voice-agent-/blob/main/backend/workflows/langgraph_workflow.py) (Delivery orchestrator), [`backend/main.py`](https://github.com/nyallaiah/autonomous-voice-agent-/blob/main/backend/main.py) (REST API), [`frontend/src/App.tsx`](https://github.com/nyallaiah/autonomous-voice-agent-/blob/main/frontend/src/App.tsx) (Project dashboard), [`backend/services/chromadb_service.py`](https://github.com/nyallaiah/autonomous-voice-agent-/blob/main/backend/services/chromadb_service.py) (Project knowledge index)

## Diagram (Mermaid)

```mermaid
flowchart TD

subgraph group_product_ui["Project UI"]
  node_app["Project dashboard<br/>[App.tsx]"]
  node_project_forms["Project forms"]
  node_review_views["Delivery review views<br/>[CallFlowView.tsx]"]
  node_sandbox["Voice sandbox"]
  node_frontend_api["API client<br/>[api.ts]"]
end

subgraph group_api_data["Platform API and Data"]
  node_http_api["REST API<br/>[main.py]"]
  node_project_store[("Project persistence<br/>[db.py]")]
end

subgraph group_delivery["Agent Delivery Pipeline"]
  node_workflow["Delivery orchestrator"]
  node_meeting["Meeting intelligence<br/>[meeting_agent.py]"]
  node_knowledge_agent["Knowledge intelligence<br/>[knowledge_agent.py]"]
  node_prompt["Prompt engineering<br/>[prompt_agent.py]"]
  node_conversation["Conversation architect"]
  node_testing["Synthetic testing<br/>[testing_agent.py]"]
  node_reliability["Reliability validation"]
  node_optimization["Prompt optimization"]
  node_artifacts["Package generation"]
end

subgraph group_knowledge["Knowledge and Voice Services"]
  node_transcription["Audio transcription<br/>[whisper_service.py]"]
  node_vector_store[("Project knowledge index")]
  node_embeddings["Text embeddings"]
  node_llm["LLM generation<br/>[llm_service.py]"]
  node_tts["Speech synthesis<br/>[tts_service.py]"]
end

node_user(("Platform user"))
node_external_llm(("LLM provider"))

node_user -.->|"uses"| node_app
node_app -->|"opens"| node_project_forms
node_app -->|"renders"| node_review_views
node_app -->|"opens"| node_sandbox
node_app -->|"requests data"| node_frontend_api
node_frontend_api -.->|"HTTP requests"| node_http_api
node_http_api -->|"reads and writes"| node_project_store
node_http_api -->|"starts pipeline"| node_workflow
node_workflow -->|"ingests documents"| node_knowledge_agent
node_workflow -->|"extracts requirements"| node_meeting
node_workflow -->|"generates prompt"| node_prompt
node_workflow -->|"builds call flow"| node_conversation
node_workflow -->|"generates tests"| node_testing
node_workflow -->|"audits reliability"| node_reliability
node_workflow -->|"optimizes prompt"| node_optimization
node_workflow -->|"assembles package"| node_artifacts
node_meeting -->|"transcribes audio"| node_transcription
node_knowledge_agent -->|"indexes chunks"| node_vector_store
node_vector_store -->|"computes vectors"| node_embeddings
node_sandbox -.->|"queries agent"| node_http_api
node_http_api -.->|"retrieves grounding"| node_vector_store
node_http_api -->|"generates response"| node_llm
node_llm -.->|"calls provider"| node_external_llm
node_http_api -->|"synthesizes speech"| node_tts

click node_app "https://github.com/nyallaiah/autonomous-voice-agent-/blob/main/frontend/src/App.tsx"
click node_project_forms "https://github.com/nyallaiah/autonomous-voice-agent-/blob/main/frontend/src/components/NewProjectModal.tsx"
click node_review_views "https://github.com/nyallaiah/autonomous-voice-agent-/blob/main/frontend/src/components/CallFlowView.tsx"
click node_sandbox "https://github.com/nyallaiah/autonomous-voice-agent-/blob/main/frontend/src/components/AgentSandboxModal.tsx"
click node_frontend_api "https://github.com/nyallaiah/autonomous-voice-agent-/blob/main/frontend/src/api.ts"
click node_http_api "https://github.com/nyallaiah/autonomous-voice-agent-/blob/main/backend/main.py"
click node_project_store "https://github.com/nyallaiah/autonomous-voice-agent-/blob/main/backend/database/db.py"
click node_workflow "https://github.com/nyallaiah/autonomous-voice-agent-/blob/main/backend/workflows/langgraph_workflow.py"
click node_meeting "https://github.com/nyallaiah/autonomous-voice-agent-/blob/main/backend/agents/meeting_agent.py"
click node_knowledge_agent "https://github.com/nyallaiah/autonomous-voice-agent-/blob/main/backend/agents/knowledge_agent.py"
click node_prompt "https://github.com/nyallaiah/autonomous-voice-agent-/blob/main/backend/agents/prompt_agent.py"
click node_conversation "https://github.com/nyallaiah/autonomous-voice-agent-/blob/main/backend/agents/conversation_agent.py"
click node_testing "https://github.com/nyallaiah/autonomous-voice-agent-/blob/main/backend/agents/testing_agent.py"
click node_reliability "https://github.com/nyallaiah/autonomous-voice-agent-/blob/main/backend/agents/reliability_agent.py"
click node_optimization "https://github.com/nyallaiah/autonomous-voice-agent-/blob/main/backend/agents/optimization_agent.py"
click node_artifacts "https://github.com/nyallaiah/autonomous-voice-agent-/blob/main/backend/agents/artifact_generator.py"
click node_transcription "https://github.com/nyallaiah/autonomous-voice-agent-/blob/main/backend/services/whisper_service.py"
click node_vector_store "https://github.com/nyallaiah/autonomous-voice-agent-/blob/main/backend/services/chromadb_service.py"
click node_embeddings "https://github.com/nyallaiah/autonomous-voice-agent-/blob/main/backend/services/embedding_service.py"
click node_llm "https://github.com/nyallaiah/autonomous-voice-agent-/blob/main/backend/services/llm_service.py"
click node_tts "https://github.com/nyallaiah/autonomous-voice-agent-/blob/main/backend/services/tts_service.py"

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_app,node_project_forms,node_review_views,node_sandbox,node_frontend_api,node_user toneBlue
class node_http_api,node_project_store toneAmber
class node_workflow,node_meeting,node_knowledge_agent,node_prompt,node_conversation,node_testing,node_reliability,node_optimization,node_artifacts toneMint
class node_transcription,node_vector_store,node_embeddings,node_llm,node_tts toneRose
class node_external_llm toneIndigo
```

## Components

### Project UI

- [Project dashboard](https://github.com/nyallaiah/autonomous-voice-agent-/blob/main/frontend/src/App.tsx): `frontend/src/App.tsx`
- [Project forms](https://github.com/nyallaiah/autonomous-voice-agent-/blob/main/frontend/src/components/NewProjectModal.tsx): `frontend/src/components/NewProjectModal.tsx`
- [Delivery review views](https://github.com/nyallaiah/autonomous-voice-agent-/blob/main/frontend/src/components/CallFlowView.tsx): `frontend/src/components/CallFlowView.tsx`
- [Voice sandbox](https://github.com/nyallaiah/autonomous-voice-agent-/blob/main/frontend/src/components/AgentSandboxModal.tsx): `frontend/src/components/AgentSandboxModal.tsx`
- [API client](https://github.com/nyallaiah/autonomous-voice-agent-/blob/main/frontend/src/api.ts): `frontend/src/api.ts`

### Platform API and Data

- [REST API](https://github.com/nyallaiah/autonomous-voice-agent-/blob/main/backend/main.py): `backend/main.py`
- [Project persistence](https://github.com/nyallaiah/autonomous-voice-agent-/blob/main/backend/database/db.py): `backend/database/db.py`

### Agent Delivery Pipeline

- [Delivery orchestrator](https://github.com/nyallaiah/autonomous-voice-agent-/blob/main/backend/workflows/langgraph_workflow.py): `backend/workflows/langgraph_workflow.py`
- [Meeting intelligence](https://github.com/nyallaiah/autonomous-voice-agent-/blob/main/backend/agents/meeting_agent.py): `backend/agents/meeting_agent.py`
- [Knowledge intelligence](https://github.com/nyallaiah/autonomous-voice-agent-/blob/main/backend/agents/knowledge_agent.py): `backend/agents/knowledge_agent.py`
- [Prompt engineering](https://github.com/nyallaiah/autonomous-voice-agent-/blob/main/backend/agents/prompt_agent.py): `backend/agents/prompt_agent.py`
- [Conversation architect](https://github.com/nyallaiah/autonomous-voice-agent-/blob/main/backend/agents/conversation_agent.py): `backend/agents/conversation_agent.py`
- [Synthetic testing](https://github.com/nyallaiah/autonomous-voice-agent-/blob/main/backend/agents/testing_agent.py): `backend/agents/testing_agent.py`
- [Reliability validation](https://github.com/nyallaiah/autonomous-voice-agent-/blob/main/backend/agents/reliability_agent.py): `backend/agents/reliability_agent.py`
- [Prompt optimization](https://github.com/nyallaiah/autonomous-voice-agent-/blob/main/backend/agents/optimization_agent.py): `backend/agents/optimization_agent.py`
- [Package generation](https://github.com/nyallaiah/autonomous-voice-agent-/blob/main/backend/agents/artifact_generator.py): `backend/agents/artifact_generator.py`

### Knowledge and Voice Services

- [Audio transcription](https://github.com/nyallaiah/autonomous-voice-agent-/blob/main/backend/services/whisper_service.py): `backend/services/whisper_service.py`
- [Project knowledge index](https://github.com/nyallaiah/autonomous-voice-agent-/blob/main/backend/services/chromadb_service.py): `backend/services/chromadb_service.py`
- [Text embeddings](https://github.com/nyallaiah/autonomous-voice-agent-/blob/main/backend/services/embedding_service.py): `backend/services/embedding_service.py`
- [LLM generation](https://github.com/nyallaiah/autonomous-voice-agent-/blob/main/backend/services/llm_service.py): `backend/services/llm_service.py`
- [Speech synthesis](https://github.com/nyallaiah/autonomous-voice-agent-/blob/main/backend/services/tts_service.py): `backend/services/tts_service.py`

### Other components

- **Platform user**
- **LLM provider**

## Connections

- Platform user → Project dashboard: uses
- Project dashboard → Project forms: opens (evidence: `frontend/src/App.tsx`)
- Project dashboard → Delivery review views: renders (evidence: `frontend/src/App.tsx`)
- Project dashboard → Voice sandbox: opens (evidence: `frontend/src/App.tsx`)
- Project dashboard → API client: requests data (evidence: `frontend/src/App.tsx`)
- API client → REST API: HTTP requests (evidence: `frontend/src/api.ts`)
- REST API → Project persistence: reads and writes (evidence: `backend/main.py`)
- REST API → Delivery orchestrator: starts pipeline (evidence: `backend/main.py`)
- Delivery orchestrator → Knowledge intelligence: ingests documents (evidence: `backend/workflows/langgraph_workflow.py`)
- Delivery orchestrator → Meeting intelligence: extracts requirements (evidence: `backend/workflows/langgraph_workflow.py`)
- Delivery orchestrator → Prompt engineering: generates prompt (evidence: `backend/workflows/langgraph_workflow.py`)
- Delivery orchestrator → Conversation architect: builds call flow (evidence: `README.md`)
- Delivery orchestrator → Synthetic testing: generates tests (evidence: `README.md`)
- Delivery orchestrator → Reliability validation: audits reliability (evidence: `README.md`)
- Delivery orchestrator → Prompt optimization: optimizes prompt (evidence: `README.md`)
- Delivery orchestrator → Package generation: assembles package (evidence: `README.md`)
- Meeting intelligence → Audio transcription: transcribes audio (evidence: `backend/agents/meeting_agent.py`)
- Knowledge intelligence → Project knowledge index: indexes chunks (evidence: `backend/agents/knowledge_agent.py`)
- Project knowledge index → Text embeddings: computes vectors (evidence: `backend/services/chromadb_service.py`)
- Voice sandbox → REST API: queries agent
- REST API → Project knowledge index: retrieves grounding (evidence: `backend/main.py`)
- REST API → LLM generation: generates response (evidence: `backend/main.py`)
- LLM generation → LLM provider: calls provider (evidence: `backend/services/llm_service.py`)
- REST API → Speech synthesis: synthesizes speech (evidence: `backend/main.py`)
