Command Code AI — the best coding agent for open models.
Command Code is an npm-installable CLI coding agent, invoked via the `cmd` command, that handles full-stack software tasks including building features, fixing bugs, writing tests, and refactoring code directly from the terminal. Its defining characteristic is a personalized learning system called "taste," driven by a proprietary `taste-1` model that tracks every accepted, rejected, or edited suggestion to build a persistent coding-style profile for the user. That profile can be shared across teams using `npx taste push/pull`. The interactive session layer supports slash commands (opened with `/`), a Bash mode triggered by `!`, and file path autocomplete via `@`. While the repository lists Anthropic, OpenAI, DeepSeek, GLM, and Kimi among its topics, suggesting multi-model support, the tool connects to these providers through its own CLI layer rather than directly through Claude Code or Claude Desktop. Developers who want a terminal-first coding agent that adapts to individual style preferences over time are the primary audience.
- ✓Actively maintained (<30d)
- ✓Healthy fork ratio
- ✓Clear description
- ✓Topics declared
- ✓Mature repo (>1y old)
- !No standard license detected
git clone https://github.com/CommandCodeAI/command-code && cp command-code/*.md ~/.claude/agents/Resumen de Subagents
Lo que la gente pregunta sobre command-code
¿Qué es CommandCodeAI/command-code?
+
CommandCodeAI/command-code es subagents para el ecosistema de Claude AI. Command Code AI — the best coding agent for open models. Tiene 3.9k estrellas en GitHub y su última actualización registrada es del 2026-08-15.
¿Cómo se instala command-code?
+
Puedes instalar command-code clonando el repositorio (https://github.com/CommandCodeAI/command-code) o siguiendo las instrucciones del README en GitHub. ClaudeWave también te ofrece bloques de instalación rápida en esta misma página.
¿Es seguro usar CommandCodeAI/command-code?
+
Nuestro agente de seguridad ha analizado CommandCodeAI/command-code y le ha asignado un Trust Score de 77/100 (tier: Trusted). Revisa el desglose completo de comprobaciones superadas y flags en esta página.
¿Quién mantiene CommandCodeAI/command-code?
+
CommandCodeAI/command-code es mantenido por CommandCodeAI. La última actividad registrada en GitHub es del 2026-08-15, con 281 issues abiertos.
¿Hay alternativas a command-code?
+
Sí. En ClaudeWave puedes explorar subagents similares en /categories/agents, ordenados por popularidad o actividad reciente.
Despliega command-code en tu cloud
Lleva este repo a producción en minutos. Cada plataforma genera su propio entorno con variables de entorno editables.
¿Mantienes este repo? Añade un badge a tu README
Pega el badge en tu README de GitHub para mostrar que está auditado por ClaudeWave. Cada badge enlaza de vuelta a esta página y muestra el Trust Score actual.
[](https://claudewave.com/repo/commandcodeai-command-code)<a href="https://claudewave.com/repo/commandcodeai-command-code"><img src="https://claudewave.com/api/badge/commandcodeai-command-code" alt="Featured on ClaudeWave: CommandCodeAI/command-code" width="320" height="64" /></a>Más Subagents
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
The agent that grows with you
Java 面试 & 后端通用面试指南，覆盖计算机基础、数据库、分布式、高并发、系统设计与 AI 应用开发
Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. Deploy on cloud, VPC, or self-hosted, so teams move from prototype to production without rebuilding the stack.
The agent engineering platform.
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.