Public repo atlasContext-ready

onboardy.dev/repos/arklexai/arksim

arklexai/arksim

Understand arklexai/arksim with an Onboardy architecture map, key systems, files to read first, evidence, and agent-ready context.

Published

Jun 3, 2026

Analysis

Jun 3, 2026

Files indexed

476

Evidence points

12

Files
476
Systems
8
Graph Edges
13
Freshness
Jun 3, 2026

Architecture map

How the repo is organized

Click systems in the graph to inspect responsibilities, important files, and nearby dependencies.

Diagram quality

Generated draftPoor0/100 layout score

Generated draft: use it for orientation, then verify components and edges in source before relying on the layout.

Nodes: 12
Edges: 13
Overlap risk: 22
Crossing risk: 4

Layout checks

  • - 22 node overlap risks detected.
  • - 4 likely edge crossings may reduce readability.
Mini Map
Node Types
Gateway
Client
Service
Database
External

Click a system in the map

Explore arklexai/arksim by selecting services, gateways, clients, and data stores. Each node shows the files, responsibilities, and neighboring systems an agent should keep in scope.

Pan, zoom, and use the minimap to keep large repos navigable.

Sign up to turn selected graph context into repo-aware agent sessions.

Key systems

What an agent should understand first

CLI Interface

Command-line entry point for simulate, evaluate, init, ui, and setup-claude commands

arksim/cli.pyarksim/__init__.py
Web UI Frontend

Interactive browser-based control plane for job management and result viewing

arksim/ui/frontend/app.js
Configuration System

YAML parsing, agent/simulation config validation, CLI override merging

arksim/config/core/agent.pyarksim/config/utils.py
API Gateway

FastAPI routes for simulation, evaluation, filesystem, and results endpoints

arksim/ui/app.pyarksim/ui/api/state.py
Simulation Engine

Multi-turn conversation orchestration with synthetic user LLM and agent execution

arksim/simulation_engine/simulator.pyarksim/simulation_engine/entities.py
Agent Factory

Creates agent instances from config: custom Python, Chat Completions HTTP, or A2A protocol

arksim/simulation_engine/agent/factory.pyarksim/simulation_engine/agent/base.py
Evaluator

Scores conversations with quantitative metrics, detects errors, matches trajectories

arksim/evaluator/evaluator.pyarksim/evaluator/evaluate.py
LLM Provider

Abstraction for OpenAI, Anthropic, Google LLM APIs (synthetic user and evaluator)

arksim/llms/chat/llm.py

Evidence coverage

What this context is grounded in

Coverage

Citations
7
Findings
5
Indexed entities
Unknown
Relationships
Unknown

Languages

PythonShellTXTJSONTypeScript