claude-ctrl and build-your-claude-code-from-scratch
One tool provides a control plane for managing Claude code, while the other offers a guide to building a Claude-like CLI agent, making them ecosystem siblings where one provides an operational framework and the other teaches the underlying construction.
About claude-ctrl
juanandresgs/claude-ctrl
The Systems Thinker's Deterministic Claude Code Control Plane
# Technical Summary Enforces deterministic governance over Claude Code through shell-script hooks that intercept every tool call (bash commands, file writes, agent dispatches) and mechanically deny unsafe operations—write-on-main attempts, untested code, undocumented changes—regardless of model context drift. Four specialized agents (Planner, Implementer, Tester, Guardian) divide responsibilities across a self-correcting pipeline, with unified SQLite state (WAL mode) eliminating race conditions in concurrent worktrees. v4.0 reduces token-per-success by 1.4% while maintaining 100% task completion through environment-tiered database safety gates, pre/post-write interception hooks, and compaction-free prompt design.
About build-your-claude-code-from-scratch
woodx9/build-your-claude-code-from-scratch
Build a Claude Code–like CLI coding agent from scratch.
Implements a progressive multi-chapter learning framework for agentic AI systems, from basic tool calling (native function calls and XML formats) through advanced patterns like ReAct loops, real-time streaming with character-by-character output, intelligent conversation history compression with token tracking, and sub-agent delegation with async execution. Architecture centers on the "Quick Star" CLI agent that integrates with Claude/OpenAI-compatible APIs via OpenRouter, including native MCP (Model Context Protocol) server support for dynamic external tool loading, while demonstrating practical code generation workflows through interactive debugging and file management.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work