# sourabhrajdev/atlas architecture

> Architecture diagram of the GitHub repository sourabhrajdev/atlas, 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/sourabhrajdev/atlas
- Repository: https://github.com/sourabhrajdev/atlas

## Overview

ATLAS is a local Mac AI assistant that turns user requests into tool-backed responses, while retaining memory and coordinating safety checks. Its broader documented capabilities include perception and a world model, retrieval, proactive signals, integrations, long-horizon planning, self-improvement, and specialist agents. The README supplies the high-level system relationships; sampled source confirms the CLI startup, engine dependencies, tool execution, and several subsystem internals. Many subsystem connections are documented rather than verified from their unsampled implementation.

Main entry points: [`atlas/core/orchestrator.py`](https://github.com/sourabhrajdev/atlas/blob/main/atlas/core/orchestrator.py) (Orchestrator), [`atlas/core/engine.py`](https://github.com/sourabhrajdev/atlas/blob/main/atlas/core/engine.py) (LLM Engine), [`atlas/autonomy/loop.py`](https://github.com/sourabhrajdev/atlas/blob/main/atlas/autonomy/loop.py) (Autonomy Loop), [`atlas/interfaces/cli.py`](https://github.com/sourabhrajdev/atlas/blob/main/atlas/interfaces/cli.py) (CLI and Voice)

## Diagram (Mermaid)

```mermaid
flowchart TD

subgraph group_interaction["User Interaction"]
  node_entry["Application Startup<br/>[main.py]"]
  node_cli["CLI and Voice<br/>[cli.py]"]
end

subgraph group_execution["Request Execution"]
  node_orchestrator["Orchestrator<br/>[orchestrator.py]"]
  node_engine["LLM Engine<br/>[engine.py]"]
  node_trust["Trust Layer<br/>[layer.py]"]
  node_tools["Tool Registry<br/>[registry.py]"]
  node_control["Action Control<br/>[router.py]"]
end

subgraph group_knowledge["Knowledge Systems"]
  node_memory[("Persistent Memory<br/>[store.py]")]
  node_perception["Perception<br/>[daemon.py]"]
  node_world[("World Model<br/>[world_model.py]")]
  node_rag["Production RAG<br/>[retriever.py]"]
end

subgraph group_autonomy["Autonomous Systems"]
  node_proactive["Proactive Intelligence<br/>[engine.py]"]
  node_autonomy_loop["Autonomy Loop<br/>[loop.py]"]
  node_scheduler["Task Scheduler<br/>[scheduler.py]"]
end

subgraph group_capabilities["Product Capabilities"]
  node_integrations["External Integrations<br/>[manager.py]"]
  node_planning["Long-Horizon Planning<br/>[engine.py]"]
  node_agents["Multi-Agent Coordination<br/>[coordinator.py]"]
  node_improvement["Self-Improvement<br/>[engine.py]"]
end

node_user(("User"))

node_user -->|"submits request"| node_cli
node_entry -->|"starts CLI"| node_cli
node_cli -->|"routes request"| node_orchestrator
node_orchestrator -->|"processes request"| node_engine
node_engine -->|"checks actions"| node_trust
node_engine -->|"executes tools"| node_tools
node_engine -->|"stores responses"| node_memory
node_orchestrator -->|"uses observations"| node_perception
node_orchestrator -->|"coordinates planning"| node_planning
node_orchestrator -->|"routes agent tasks"| node_agents
node_orchestrator -->|"coordinates integrations"| node_integrations
node_orchestrator -->|"coordinates learning"| node_improvement
node_orchestrator -->|"coordinates autonomy"| node_autonomy_loop
node_perception -->|"updates context"| node_world
node_world -->|"supplies knowledge"| node_rag
node_integrations -->|"informs knowledge graph"| node_world
node_autonomy_loop -->|"checks scheduled tasks"| node_scheduler
node_autonomy_loop -->|"executes tasks"| node_tools
node_proactive -->|"injects signals"| node_orchestrator
node_trust -->|"guards actions"| node_control

click node_entry "https://github.com/sourabhrajdev/atlas/blob/main/atlas/main.py"
click node_cli "https://github.com/sourabhrajdev/atlas/blob/main/atlas/interfaces/cli.py"
click node_orchestrator "https://github.com/sourabhrajdev/atlas/blob/main/atlas/core/orchestrator.py"
click node_engine "https://github.com/sourabhrajdev/atlas/blob/main/atlas/core/engine.py"
click node_trust "https://github.com/sourabhrajdev/atlas/blob/main/atlas/trust/layer.py"
click node_tools "https://github.com/sourabhrajdev/atlas/blob/main/atlas/tools/registry.py"
click node_control "https://github.com/sourabhrajdev/atlas/blob/main/atlas/control/router.py"
click node_memory "https://github.com/sourabhrajdev/atlas/blob/main/atlas/memory/store.py"
click node_perception "https://github.com/sourabhrajdev/atlas/blob/main/atlas/perception/daemon.py"
click node_world "https://github.com/sourabhrajdev/atlas/blob/main/atlas/world/world_model.py"
click node_rag "https://github.com/sourabhrajdev/atlas/blob/main/atlas/rag/retriever.py"
click node_integrations "https://github.com/sourabhrajdev/atlas/blob/main/atlas/integrations/manager.py"
click node_planning "https://github.com/sourabhrajdev/atlas/blob/main/atlas/planning/engine.py"
click node_agents "https://github.com/sourabhrajdev/atlas/blob/main/atlas/agents/coordinator.py"
click node_improvement "https://github.com/sourabhrajdev/atlas/blob/main/atlas/improvement/engine.py"
click node_proactive "https://github.com/sourabhrajdev/atlas/blob/main/atlas/proactive/engine.py"
click node_autonomy_loop "https://github.com/sourabhrajdev/atlas/blob/main/atlas/autonomy/loop.py"
click node_scheduler "https://github.com/sourabhrajdev/atlas/blob/main/atlas/scheduler/scheduler.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_entry,node_cli,node_user toneBlue
class node_orchestrator,node_engine,node_trust,node_tools,node_control toneAmber
class node_memory,node_perception,node_world,node_rag toneMint
class node_proactive,node_autonomy_loop,node_scheduler toneRose
class node_integrations,node_planning,node_agents,node_improvement toneIndigo
```

## Components

### User Interaction

- [Application Startup](https://github.com/sourabhrajdev/atlas/blob/main/atlas/main.py): `atlas/main.py`
- [CLI and Voice](https://github.com/sourabhrajdev/atlas/blob/main/atlas/interfaces/cli.py): `atlas/interfaces/cli.py`

### Request Execution

- [Orchestrator](https://github.com/sourabhrajdev/atlas/blob/main/atlas/core/orchestrator.py): `atlas/core/orchestrator.py`
- [LLM Engine](https://github.com/sourabhrajdev/atlas/blob/main/atlas/core/engine.py): `atlas/core/engine.py`
- [Trust Layer](https://github.com/sourabhrajdev/atlas/blob/main/atlas/trust/layer.py): `atlas/trust/layer.py`
- [Tool Registry](https://github.com/sourabhrajdev/atlas/blob/main/atlas/tools/registry.py): `atlas/tools/registry.py`
- [Action Control](https://github.com/sourabhrajdev/atlas/blob/main/atlas/control/router.py): `atlas/control/router.py`

### Knowledge Systems

- [Persistent Memory](https://github.com/sourabhrajdev/atlas/blob/main/atlas/memory/store.py): `atlas/memory/store.py`
- [Perception](https://github.com/sourabhrajdev/atlas/blob/main/atlas/perception/daemon.py): `atlas/perception/daemon.py`
- [World Model](https://github.com/sourabhrajdev/atlas/blob/main/atlas/world/world_model.py): `atlas/world/world_model.py`
- [Production RAG](https://github.com/sourabhrajdev/atlas/blob/main/atlas/rag/retriever.py): `atlas/rag/retriever.py`

### Autonomous Systems

- [Proactive Intelligence](https://github.com/sourabhrajdev/atlas/blob/main/atlas/proactive/engine.py): `atlas/proactive/engine.py`
- [Autonomy Loop](https://github.com/sourabhrajdev/atlas/blob/main/atlas/autonomy/loop.py): `atlas/autonomy/loop.py`
- [Task Scheduler](https://github.com/sourabhrajdev/atlas/blob/main/atlas/scheduler/scheduler.py): `atlas/scheduler/scheduler.py`

### Product Capabilities

- [External Integrations](https://github.com/sourabhrajdev/atlas/blob/main/atlas/integrations/manager.py): `atlas/integrations/manager.py`
- [Long-Horizon Planning](https://github.com/sourabhrajdev/atlas/blob/main/atlas/planning/engine.py): `atlas/planning/engine.py`
- [Multi-Agent Coordination](https://github.com/sourabhrajdev/atlas/blob/main/atlas/agents/coordinator.py): `atlas/agents/coordinator.py`
- [Self-Improvement](https://github.com/sourabhrajdev/atlas/blob/main/atlas/improvement/engine.py): `atlas/improvement/engine.py`

### Other components

- **User**

## Connections

- User → CLI and Voice: submits request (evidence: `README.md`)
- Application Startup → CLI and Voice: starts CLI (evidence: `atlas/main.py`)
- CLI and Voice → Orchestrator: routes request (evidence: `atlas/interfaces/cli.py`)
- Orchestrator → LLM Engine: processes request (evidence: `README.md`)
- LLM Engine → Trust Layer: checks actions (evidence: `atlas/core/engine.py`)
- LLM Engine → Tool Registry: executes tools (evidence: `atlas/core/engine.py`)
- LLM Engine → Persistent Memory: stores responses (evidence: `atlas/core/engine.py`)
- Orchestrator → Perception: uses observations (evidence: `README.md`)
- Orchestrator → Long-Horizon Planning: coordinates planning (evidence: `README.md`)
- Orchestrator → Multi-Agent Coordination: routes agent tasks (evidence: `README.md`)
- Orchestrator → External Integrations: coordinates integrations (evidence: `README.md`)
- Orchestrator → Self-Improvement: coordinates learning (evidence: `README.md`)
- Orchestrator → Autonomy Loop: coordinates autonomy (evidence: `README.md`)
- Perception → World Model: updates context (evidence: `README.md`)
- World Model → Production RAG: supplies knowledge (evidence: `README.md`)
- External Integrations → World Model: informs knowledge graph (evidence: `README.md`)
- Autonomy Loop → Task Scheduler: checks scheduled tasks (evidence: `atlas/autonomy/loop.py`)
- Autonomy Loop → Tool Registry: executes tasks (evidence: `atlas/autonomy/loop.py`)
- Proactive Intelligence → Orchestrator: injects signals (evidence: `atlas/proactive/engine.py`)
- Trust Layer → Action Control: guards actions (evidence: `README.md`)