Codecrafters Claude Code Cpp — AI skill for Claude Code
A high-performance C++ implementation of an autonomous AI coding agent inspired by Claude Code, built as part of the CodeCrafters challenge.
How to install Codecrafters Claude Code Cpp
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open Anshuk18/codecrafters-claude-code-cpp and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Codecrafters Claude Code Cpp does
A high-performance C++ implementation of an autonomous AI coding agent inspired by Claude Code, built as part of the CodeCrafters challenge. Powered by OpenRouter and equipped with file system and shell execution tools.
Alternatives in AI
- Inference Serving — ai-research-skills vLLM, SGLang, TensorRT-LLM, llama.cpp 5.4k ★
- Deepreasoning — A high-performance LLM inference API and Chat UI that integrates DeepSeek R1's CoT reasoning traces with Anthr 5.4k ★
- Osaurus — Own your AI. The native macOS harness for AI agents -- any model, persistent memory, autonomous execution, cry 5.1k ★
README
[](https://app.codecrafters.io/users/Anshuk18?r=2qF)
This is a starting point for C++ solutions to the ["Build Your own Claude Code" Challenge](https://codecrafters.io/challenges/claude-code).
Claude Code is an AI coding assistant that uses Large Language Models (LLMs) to understand code and perform actions through tool calls. In this challenge, you'll build your own Claude Code from scratch by implementing an LLM-powered coding assistant.
Along the way you'll learn about HTTP RESTful APIs, OpenAI-compatible tool calling, agent loop, and how to integrate multiple tools into an AI assistant.
**Note**: If you're viewing this repo on GitHub, head over to [codecrafters.io](https://codecrafters.io) to try the challenge.
Passing the first stage
The entry point for your `claude-code` implementation is in `src/main.cpp`. Study and uncomment the relevant code, and submit to pass the first stage:
codecrafters submit
Stage 2 & beyond
Note: This section is for stages 2 and beyond.
- Ensure you have
cmakeinstalled locally. - Run
./your_program.shto run your program, which is implemented insrc/main.cpp. - Run
codecrafters submitto submit your solution to CodeCrafters. Test output will be streamed to your terminal.
Related Skills
Kerux
A high-performance Rust implementation orchestration loop for LLM-driven tool execution.
Claude Code Ripper Rs
PikoClaw 2026: Rust-Powered AI Agent for High-Performance Devleopment
Codecrafters Claude Code Python
A minimal LLM coding agent in ~280 lines of Python — Read/Write/Edit/Bash/Glob/Grep tools with an agent loop.
Phantom Agent
Autonomous AI agent for BitGN PAC1 Challenge — ~86% score with 12 hot-reloadable skills, live dashboard, and s
Vllm Mlx
High-performance OpenAI and Anthropic compatible LLM inference server for Apple Silicon. Native MLX, continuou
Ataru
High-performance AI memory retrieval for local agent history — a Rust search core (SDK / API / JSON CLI) plus
Related Agents
Part 13: Memory Bridge (Give Coding Agents Your Brain)
When you spawn Codex or Claude Code to build something, they start blind. They don't know your architecture de
Hephaestus
Autonomous deep implementation worker. Full tool access for complex coding tasks. Explores codebase patterns,
Morningstar Runner
Autonomous coding agent that takes a PRD from Notion (or a Jira ticket) and ships an end-to-end implementation