Directory · Subagents

mini-claude-code

A simplified Java reimplementation of Claude Code's agent harness, split into 16 chapter branches for learning how coding agents work.

★ 177 stars · last updated 2026-07-07 · Free (check license) · View on GitHub

Best for

• Java developers learning how coding agent loops, tools, and permissions are built
• Studying subagent delegation and multi-agent team coordination in minimal code
• Understanding context compression, memory, and skill loading mechanisms step by step

Install

git switch s01-agent-loop
mvn -q compile exec:java -Dexec.mainClass=org.miniclaudecode.demo.S01AgentLoopDemo

Our take

This is an educational project, not a production agent. Each chapter lives on its own branch with minimal code for that mechanism, and it needs Java 17, Maven, and an Anthropic-compatible API endpoint set through ANTHROPIC_BASE_URL, MODEL_ID, and ANTHROPIC_API_KEY. The main README is in Chinese with an English version available, it has no license, and it credits learn-claude-code as its reference.

Similar subagents

• Awesome Claude Code Subagents (VoltAgent): A curated collection of 161+ Claude Code subagent definitions across 10 categories, installable as plugins or individual agent files.
• claude-devtools: Desktop and web app that reads local Claude Code session logs to show tool calls, token usage, subagent trees, and context.
• AI Marketing Suite for Claude Code: Claude Code skills and parallel subagents for marketing audits, copywriting, email sequences, ad copy, and client-ready reports.
• pentest-ai-agents: 50 Claude Code subagents turning Claude into an offensive security research assistant for authorized penetration testing.
• Translate Book: Agent skill for Claude Code, Codex, and OpenClaw that translates whole PDF/DOCX/EPUB books using parallel subagents per chunk.
• Claude Code Sub-Agents (lst97): A collection of 33 specialized Claude Code subagents for full-stack development, plus an agent-organizer for multi-agent orchestration.