Docs: Choose an agent framework | Maritime

Choose a framework

A framework is the agent software that runs inside your agent's machine. Every ready-made template is a real agent framework, pre-configured and one image pull from live. Pick one, name it, deploy. Each guide covers the image, how it works, its environment variables, and how to talk to it.

Framework Template ID Runtime Best for LLM key
Claude Code claude_code Node.js (Claude Agent SDK) A coding agent with real bash and file tools in a persistent workspace Your ANTHROPIC_API_KEY (required)
Codex codex Node.js (Codex CLI) OpenAI's coding agent with shell and file tools in a persistent workspace, plus the interactive TUI in the terminal Optional (Maritime LLM by default; your OpenAI key or ChatGPT sign-in)
OpenClaw openclaw Node.js A general autonomous assistant: 100+ skills, channels, web browsing Optional (Maritime LLM by default)
Hermes hermes Python A self-improving agent with persistent memory and its own full dashboard Optional (Maritime LLM by default)
ZeroClaw zeroclaw Rust (single binary) Ultra-light agents: <5 MB RAM, sub-second start, good for running many Optional (Maritime LLM by default)
DeepSeek Harness dsh Node.js (plugin runtime) DeepSeek's agent harness with a full web workbench and session replay None needed (Maritime LLM by default)

Deploying a template

In the dashboard: New agent, pick the template, name it. From the terminal:

maritime templates                       # list what's available
maritime create my-agent --template openclaw

Worth knowing

None of these fit?

Any Docker image that speaks a two-endpoint contract becomes a full Maritime agent: CrewAI, LangGraph, AutoGen, or your own code. See Deploy any container.