open-claude-code

Name: open-claude-code
Rating: 77 (1 reviews)
Author: ruvnet

ruvnet/open-claude-code

Open Claude Code is a fully functional, open-source clean-room implementation of Anthropic's Claude Code CLI. It mirrors the original architecture with 25 tools, 40 slash commands, and multi-provider AI support.

472 165MITUpdated 2026-08-13

Great

View on GitHub Open source file

Overview

Designed as an alternative terminal interface for AI-assisted development, Open Claude Code recreates the core features of Anthropic's tool ecosystem based on public intelligence and clean-room implementation. It supports interactive REPL sessions, one-shot prompt execution, multiple AI providers including Anthropic, OpenAI, and Google, as well as extensive configuration options through local settings and custom project instructions.

Capabilities

▸Interactive REPL with slash commands
▸One-shot prompt execution
▸Multi-provider AI support (Anthropic, OpenAI, Google, AWS Bedrock, Vertex)
▸File manipulation through 25 built-in tools
▸MCP transport support (stdio, SSE, Streamable HTTP, WebSocket)
▸Custom agent definitions and skill loading
▸Automated session state management and history recovery

Best for

Executing terminal-based code generation and refactoring tasks, Running automated software debugging sessions using local file tools, Querying codebases with specialized multi-turn assistant workflows, Connecting external Model Context Protocol (MCP) servers for custom tool extensions

Works with

Claude Code

Evoa Score breakdown= Σ (score × weight)

Task usefulness20%100 → +20.0

実タスクにどれだけ役立つか（機能の豊富さ・用途の明確さ）。 — AIによるcapabilities/use-cases解析

Code quality15%95 → +14.3

実装・指示の品質。 — AIによるSKILL.md/README解析

Maintenance15%100 → +15.0

リポジトリがどれだけ活発に保守されているか。 — GitHub 最終push日時の新しさ

Documentation12%37 → +4.4

ドキュメントの充実度・分かりやすさ。 — README/独自要約の情報量

Security15%50 → +7.5

危険・不審な挙動が無いか。 — AIによるセキュリティレビュー

Originality10%85 → +8.5

ありふれたラッパーではない独自性。 — AIによる独自性判定

Popularity8%73 → +5.8

コミュニティの採用度。 — GitHub Stars/Forks（対数スケール）

Compatibility5%25 → +1.3

対応AIエージェントの広さ。 — AIによる対応エージェント判定

Weighted total76.8 / 100

ライセンス不明/制限あり（Red）のSkillは総合スコアに0.85倍の補正を適用します。ランキングはこのScoreのみで決まり、広告で変わりません。算出方法の詳細 →

Security considerations

The CLI tool executes local shell commands and modifies project files depending on the configured permission mode. Users should exercise caution and use restricted permission modes when running untrusted scripts or interacting with sensitive repositories.