经 AI Skill Hub 精选评估,代码助手 获评「强烈推荐」。这款Agent工作流在功能完整性、社区活跃度和易用性方面表现出色,AI 评分 8.0 分,适合有一定技术背景的用户使用。
代码助手 是一套完整的 AI Agent 自动化工作流方案。通过可视化的节点编排,将复杂的多步骤任务拆解为清晰的自动化流程,实现全程无人值守的智能处理。支持与数百种外部服务和 API 无缝集成,适合构建数据处理管线、业务自动化和 AI 辅助决策系统。
代码助手 是一套完整的 AI Agent 自动化工作流方案。通过可视化的节点编排,将复杂的多步骤任务拆解为清晰的自动化流程,实现全程无人值守的智能处理。支持与数百种外部服务和 API 无缝集成,适合构建数据处理管线、业务自动化和 AI 辅助决策系统。
# 方式一:npm 全局安装 npm install -g code-buddy # 方式二:npx 直接运行(无需安装) npx code-buddy --help # 方式三:项目依赖安装 npm install code-buddy # 方式四:从源码运行 git clone https://github.com/phuetz/code-buddy cd code-buddy npm install npm start
# 命令行使用
code-buddy --help
# 基本用法
code-buddy [options] <input>
# Node.js 代码中使用
const code_buddy = require('code-buddy');
const result = await code_buddy.run(options);
console.log(result);
# code-buddy 配置说明 # 查看配置选项 code-buddy --config-example > config.yml # 常见配置项 # output_dir: ./output # log_level: info # workers: 4 # 环境变量(覆盖配置文件) export CODE_BUDDY_CONFIG="/path/to/config.yml"
<img src="https://img.shields.io/badge/🤖-Code_Buddy-blueviolet?style=for-the-badge&labelColor=1a1a2e" alt="Code Buddy"/>
1.6.0 GA — these aren't roadmap items. The captures above are unedited, and the core runs today:
$0 local coding agent — a local Ollama model reasons on screen, then calls tools to do real work. (the demos above)gpt-5.5 at $0 — buddy login, flat-fee, no API key, no per-token metering.peer.chat / peer.tool.invoke).Honest about scope: Hermes / OpenClaw parity lays out exactly what's shipped, what's externally-gated, and where the edges are — including which messaging channels are full integrations vs. in-process stubs.
---
git clone https://github.com/phuetz/code-buddy.git cd code-buddy && npm install && npm run build && npm link # exposes buddy globally
> **Requirements:** Node.js **≥ 18** for the CLI (the one-command installer provisions **≥ 20**). The **Cowork desktop app needs Node ≥ 22** plus a C++ build toolchain for native modules (`better-sqlite3`). Run **`buddy doctor`** anytime to check your environment (`--fix` to auto-remediate). Full install guide (one-command, Docker/VPS, npm): **[docs/install.md](docs/install.md)**.
Then pick a brain:
bash
buddy install-gui # one-time: install Electron + build the desktop bundle buddy gui # launch the desktop app (or: buddy desktop) buddy server --port 3000 # optional: shared backend for Cowork, Fleet, OpenAI-compatible clients
curl -fsSL https://raw.githubusercontent.com/phuetz/code-buddy/main/install.sh | sh
docker compose up -d # after: cp .env.example .env && set JWT_SECRET
```bash
export CODEBUDDY_PROVIDER=ollama buddy
buddy login # opens browser for OAuth → tokens persisted buddy whoami # ✅ connected · you@example.com · Plan: pro buddy # auto-routes to gpt-5.5 via the Codex backend, cost $0.0000
export GROK_API_KEY=... # or GEMINI_API_KEY / OPENAI_API_KEY / ANTHROPIC_API_KEY buddy
buddy login xai # browser OAuth → routes to Grok (grok-4-latest), cost $0
bash buddy --prompt "analyze the codebase structure" # one-shot task buddy --yolo # full autonomy
**Use several logins at once, or fail over automatically across them:**
bash buddy llm # list the LLMs you're logged into + the failover order buddy llm ensemble "is this approach sound?" # ask ChatGPT + Grok + Ollama together, then synthesize buddy council "compare REST vs GraphQL" # conductor roles + synthesis + judge + learned ranking buddy council --scoreboard # the learned ranking (which model is best for code / reasoning / …) CODEBUDDY_LLM_FAILOVER=1 buddy -p "…" # if the primary errors, auto-continue on the next active LLM ```
buddy council takes the ensemble further: for complex tasks, a lightweight conductor assigns complementary roles (architect, implementer, reviewer, verifier, skeptic, etc.) instead of asking every model the exact same prompt. It still routes by capability and past win rate, an impartial judge scores the candidates, a synthesis pass merges the best role-specialized contributions, and a scoreboard learns which AI is best for which kind of task and role over time — so future runs can put stronger models on reviewer/verifier/architect jobs. Use --no-conductor to force the old direct fan-out, or --no-synthesis to keep only the judge-selected answer. Works in Telegram too (council <task>).
<p align="center"> <img src="docs/assets/llm-demo.gif" alt="buddy llm lists your active LLMs, then auto-fails over from Grok to ChatGPT when the primary errors" width="760"/> <br/> <sub>Your logins at a glance — and automatic failover from one to the next when one has a problem, at <code>$0</code>. Real run, unedited.</sub> </p>
<p align="center"> <img src="docs/assets/ensemble-demo.gif" alt="buddy llm ensemble asks ChatGPT, Ollama and Grok the same question, then synthesizes one answer" width="760"/> <br/> <sub><code>buddy llm ensemble</code> — every brain you're logged into answers, then it's synthesized into one. Real run, unedited.</sub> </p>
See Getting Started for install options, headless mode, sessions, and typical workflows.
---
Configure via env vars, TOML profiles ([profiles.<name>], buddy --profile), and per-project .codebuddy/settings.json. Permission modes gate approvals, agent modes (plan/code/ask/architect) restrict the tool surface, and security modes (suggest/auto-edit/full-auto) tune the approval flow. Per-model capabilities (context window, max output, patch format) live in src/config/model-tools.ts. The UI ships in English and French (complete); de/es/ja/zh are registered locale scaffolds that currently fall back to English.
---
代码助手是一个高质量的开源AI工作流项目,具有自动化编码和工作流管理的能力
AI Skill Hub 为第三方内容聚合平台,本页面信息基于公开数据整理,不对工具功能和质量作任何法律背书。
建议在沙箱或测试环境中充分验证后,再部署至生产环境,并做好必要的安全评估。
✅ MIT 协议 — 最宽松的开源协议之一,可自由商用、修改、分发,仅需保留版权声明。
AI Skill Hub 点评:代码助手 的核心功能完整,质量优秀。对于自动化工程师和运维人员来说,这是一个值得纳入个人工具库的选择。建议先在非生产环境试用,再逐步推广。
| 原始名称 | code-buddy |
| 原始描述 | 开源AI工作流:An open-source multi-provider AI coding agent that runs directly in your termina。⭐9 · TypeScript |
| Topics | AI工作流TypeScript |
| GitHub | https://github.com/phuetz/code-buddy |
| License | MIT |
| 语言 | TypeScript |
收录时间:2026-05-28 · 更新时间:2026-05-30 · License:MIT · AI Skill Hub 不对第三方内容的准确性作法律背书。
选择 Agent 类型,复制安装指令后粘贴到对应客户端