Skip to main content
Code-specialized execution engine optimized for development workflows. Built on Anthropic’s Claude Code SDK with advanced file operations and extended history.

​
Key Features

Code-Optimized

Multi-file awareness, repository analysis, safe refactoring

Extended History

200 messages with session resumption

Claude Models

Opus, Sonnet 4, Sonnet, Haiku

​
Capabilities

FeatureSupport
Streaming✅ Yes
Tool Calling✅ Yes (MCP)
MCP Servers✅ First-class
History200 messages
Session Resume✅ Yes
File Operations✅ Advanced
Code Analysis✅ Yes

​
Supported Models

Claude Code Runtime supports all Claude (Anthropic) models through LiteLLM. While optimized for Claude models, it can route to any model your LiteLLM proxy is configured to support. Commonly used Claude models:
  • Claude 3.5 Sonnet (Recommended) - Best balance of capability, speed, and cost
  • Claude 3 Opus - Maximum intelligence for complex tasks
  • Claude 3 Sonnet - Balanced performance
  • Claude 3 Haiku - Fast and economical
  • Any other Claude model - Including future releases
Note: Model support is dynamic and configured at the LiteLLM proxy level, not hardcoded in the runtime. Learn more: Anthropic Models

​
When to Use

Best for:
  • Code generation and refactoring
  • Repository analysis
  • Technical documentation
  • Long development sessions
  • Claude-committed organizations
Consider alternatives:

​
Trade-offs

Pros:
  • ✅ Code-specialized capabilities
  • ✅ 200-message extended history
  • ✅ Session resumption
  • ✅ Multi-file awareness
Cons:
  • ❌ Optimized for Claude (not multi-provider like Agno)
  • ❌ Slower startup (~150ms vs ~50ms)
  • ❌ Not ideal for general tasks

Anthropic Docs

Official Claude documentation

MCP Protocol

Model Context Protocol specs

​
Next Steps

Compare Runtimes

See side-by-side comparison

Agent Setup

Configure agents with Claude Code