Developer Documentation

Documentation Center

Complete guide to setting up local LLM models, configuring multi-agent orchestration networks, injecting custom skills, and running full-stack sandboxes.

Part 1 • Model Selection Guide

Model Architectures & LLM Routing

Optimize inference speed, context length, and token costs for multi-agent workloads.

Part 2 • Multi-Agent Guide

Multi-Agent Orchestration

Watch specialized design, development, and quality agents collaborate in real-time.

Part 3 • Extension Skills

Skills & Knowledge Injections

Inject custom system knowledge, workspace APIs, and persistent databases.

Part 4 • Execution Environments

Web & Python Sandboxing

Safely execute, test, and render reactive apps or terminal calculations.

Part 5 • Browser Integration

Browser Extension Companion

Bring multi-agent AI assistant to any webpage or web application.

Articles & Insights

Technical Blog & Research

Explore in-depth articles on AI model benchmarks, open-weights, and agent workflows.