登录 注册
开发者工具AI 应用与 AI Agent自动化与工作流
316
Stars
28
Forks
0
Watchers
1
Open Issues
NOASSERTION
许可证
Zig
语言
2026-06-14
创建时间
2026-11-11
最近更新

项目能做什么

用 Zig 编写的高速智能编程框架,支持多服务商、MCP、工作流及 TS/Python SDK。
来源:基于仓库元数据 · 内容以仓库实际 README 为准

使用说明 查看原始 README 原仓库文档

中文使用说明暂未生成。下面保留原仓库 README 摘录,命令与配置均以原文为准。
原始 README 摘录(英文原文,节选前 3000 字符)
<p align="center">
  <img src="docs/images/readme-rats.png" alt="CodeGraff workshop rats in coral coats" width="280" height="280">
</p>

<h1 align="center">CodeGraff</h1>

<p align="center">An AI coding agent for your terminal. One small binary, no dependencies.</p>

<p align="center">Want a desktop app? <a href="https://github.com/justrach/harness"><strong>Harness</strong></a> runs graff with chat, review, files, and terminals in one window.</p>

<p align="center">
  <img alt="macOS · Linux · Windows" src="https://img.shields.io/badge/macOS%20·%20Linux%20·%20Windows-555">
  <img alt="One binary, 3.7 MB" src="https://img.shields.io/badge/one%20binary-3.7%20MB-44cc11">
  <img alt="Zero dependencies" src="https://img.shields.io/badge/dependencies-0-44cc11">
  <img alt="Built in Zig 0.17 dev" src="https://img.shields.io/badge/built%20in-Zig%200.17%20dev-f7a41d?logo=zig&logoColor=white">
</p>

<p align="center">
  <a href="https://trendshift.io/repositories/84216?utm_source=repository-badge&utm_medium=badge&utm_campaign=badge-repository-84216" target="_blank" rel="noopener noreferrer"><img src="https://trendshift.io/api/badge/repositories/84216" alt="justrach/codegraff | Trendshift" width="250" height="55"></a>
</p>

<p align="center">
  <a href="#install">Install</a> ·
  <a href="#what-it-does">What it does</a> ·
  <a href="#mcp-servers">MCP</a> ·
  <a href="#desktop-app">Desktop app</a> ·
  <a href="#use-it-from-code">SDKs</a> ·
  <a href="#evaluation-results">Evaluations</a> ·
  <a href="#development">Development</a>
</p>

## Install

On macOS or Linux:

```sh
curl -fsSL https://github.com/justrach/codegraff/releases/latest/download/install.sh | sh
```

On Windows, in PowerShell (no WSL needed):

```powershell
irm https://github.com/justrach/codegraff/releases/latest/download/install.ps1 | iex
```

It verifies the download against the release's `SHA256SUMS`, installs
`graff.exe` under `%LOCALAPPDATA%\Programs\graff\bin` and adds that to your user
`PATH`. The desktop app, [Harness](https://github.com/justrach/harness), installs
`graff` for you.

```sh
graff login                      # sign in
graff                            # start an interactive session
graff -p "Explain this project"  # ask one question, answer on stdout
```

`graff update` installs the latest stable release, and `graff update --beta`
the newest beta. Both check the download against the release's `SHA256SUMS`.

<details>
<summary>Other sign-ins, installing from a checkout, and editors</summary>

```sh
graff login chatgpt             # ChatGPT sign-in (same as: graff login codex)
graff login anthropic           # Claude subscription browser sign-in (alias: ant)
graff login kimi
graff login zai
graff login xai
graff login console             # Anthropic Console account (API credits), via Anthropic's `ant` CLI
graff key set deepseek sk-...   # any provider by API key
graff --model grok-4.6
```

Anthropic browser login uses native OAuth, not the Claude CLI or its credential
files. 
阅读完整原文

商业机会分析 规则生成(AI 未配置)

综合评分 42.1 分。该项目在“个人可实施性”维度得 35 分,“付费可能性”维度得 32.0 分,差异化空间 45.0 分(评分依据见评分卡)。

面向细分需求的二次开发产品

产品构想基于 codegraff 的核心能力,聚焦一个更窄的场景(如某平台、某行业)做差异化。
目标用户该细分场景用户
难度/周期中 · 2~6 周
收费模式买断制 / 订阅制 / 广告
竞争风险细分需求规模需验证
依据 AI 推测:基于项目主题标签的判断
以上为规则引擎基于仓库公开数据生成的参考结论,包含推测成分,不构成投资或创业承诺;配置 AI 后可获得更深入的分析。
报告会保存到 个人中心

竞品与相似项目 GitHub Search 真实检索

项目中文简介Stars语言
justrach/codegraff2 中文介绍暂未生成
CodeGraff: a faster, lightweight coding agent for focused te
27 Rust
justrach/browse 中文介绍暂未生成
More page. Less browser. A WebKit browser for the Mac with C
12 Swift
justrach/relay-sdk 中文介绍暂未生成
TypeScript SDK for relay — multi-agent rooms for coding agen
2 JavaScript
justrach/graff-skills 中文介绍暂未生成
Public catalog of Agent Skills (SKILL.md playbooks) for Code
1 -
swapnilkr/CodeGraffiti 中文介绍暂未生成
Welcome to CodeGraffiti, my canvas of creativity! 🎨 This Git
0 JavaScript
vaibhavpoojary/codegraff.github.io 中文介绍暂未生成
0 TypeScript
以上为通过 GitHub 官方 Search API 检索的相似项目,功能差异与优劣势需进一步人工确认,配置 AI 后可生成对比分析。

项目优势与风险

技术成熟度创建于 2026-06-14,近 30 天仍在推送,发布过 100 个 Release
社区活跃Star 316 / Fork 28 / Issue 1(数据支持,可自行核实)
许可证NOASSERTION
主要风险上游项目方向可能变化;同赛道竞争者较多(见竞品表);热度与需求不完全等价

安装与使用

快速开始(以仓库 README 为准)
git clone https://github.com/justrach/codegraff.git
cd codegraff
docker compose up -d   # 或参考 README 中的 docker run 命令
阅读原仓库文档
术语说明:Docker=应用容器(把程序和依赖打包运行);API Key=调用外部服务的密钥;Git Clone=把仓库代码下载到本地。常见错误:API Key 未配置 / 端口占用 / 数据库连接失败,多数项目在 README 的 Troubleshooting 章节有说明。