经 AI Skill Hub 精选评估,代码智能助手 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。
自动化AI工作流,读取项目、运行命令、写入代码
代码智能助手 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。
自动化AI工作流,读取项目、运行命令、写入代码
代码智能助手 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 codeep # 方式二:npx 直接运行(无需安装) npx codeep --help # 方式三:项目依赖安装 npm install codeep # 方式四:从源码运行 git clone https://github.com/VladoIvankovic/Codeep cd Codeep npm install npm start
# 命令行使用
codeep --help
# 基本用法
codeep [options] <input>
# Node.js 代码中使用
const codeep = require('codeep');
const result = await codeep.run(options);
console.log(result);
# codeep 配置说明 # 查看配置选项 codeep --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 CODEEP_CONFIG="/path/to/config.yml"
<p align="center"> <img src="Codeep.svg" alt="Codeep Logo" width="200"> </p>
<p align="center"> <strong>Deep into Code.</strong> </p>
<p align="center"> <img src="promo/sources/tui-current.png" alt="Codeep terminal UI with agent timeline, changed files, checks, and resource estimates" width="1000"> </p>
<p align="center"> Autonomous AI coding agent that reads your project, runs commands, and writes & verifies code — deeper than autocomplete. Any model (Claude, Gemini, DeepSeek, GLM, OpenAI, or your own local/custom), in the terminal and your editor. </p>
<p align="center"> <a href="https://www.npmjs.com/package/codeep"><img src="https://img.shields.io/npm/v/codeep.svg" alt="npm version"></a> <a href="https://www.npmjs.com/package/codeep"><img src="https://img.shields.io/npm/dm/codeep.svg" alt="npm downloads"></a> <a href="https://github.com/VladoIvankovic/Codeep/blob/main/LICENSE"><img src="https://img.shields.io/npm/l/codeep.svg" alt="license"></a> </p>
/settings/tasks add and /tasks doneRun the test suite, build, then npm run deploy:staging. If the build fails, surface the error and stop — don't deploy a broken build. ```
The agent gets the bundle catalog injected into its system prompt on every iteration and can invoke any bundle via the invoke_skill tool:
/skills bundles — list installed bundles/skills create-bundle <name> — scaffold a new project skill/skills show <name> — print the SKILL.md/skills browse [query] — search the public marketplace/skills install <owner>/<slug> — pull from marketplace/skills publish <name> [--public] — share to codeep.dev/skills unpublish <owner>/<slug> — remove your published skillWeb marketplace: publish skills to codeep.dev/skills as public (browseable by anyone) or private (only you). Manage your published skills at /dashboard/skills. From the VS Code extension, use the Codeep: Browse Skill Bundles… / Codeep: Create Skill Bundle… / Codeep: Open Skills Folder commands.
curl -fsSL https://github.com/VladoIvankovic/Codeep/releases/latest/download/codeep-macos-arm64 -o codeep chmod +x codeep sudo mv codeep /usr/local/bin/ ```
```bash
npm install -g codeep
Update:
npm update -g codeep
For a machine without Node. The script is served from codeep.dev and fetched from this repository's newest release, so the command does not change if the repository moves.
curl -fsSL https://codeep.dev/install.sh | bash
Custom installation directory:
curl -fsSL https://codeep.dev/install.sh | INSTALL_DIR=~/.local/bin bash
Specific version:
curl -fsSL https://codeep.dev/install.sh | VERSION=3.1.1 bash
Download the latest binary for your platform from GitHub Releases:
| Platform | Binary |
|---|---|
| macOS Apple Silicon (M1/M2/M3/M4) | codeep-macos-arm64 |
| macOS Intel | codeep-macos-x64 |
| Linux x86_64 | codeep-linux-x64 |
```bash
You write safe, reversible DB migrations… ```
tools is an allowlist enforced at dispatch (a researcher literally can't write files). Sub-agents inherit your profile + project rules, and their changes are covered by /undo.
Guaranteed review: enable Agent Auto-Review in /settings (agentAutoReview) and after any run that changes files, Codeep automatically delegates to the reviewer and appends its findings — a review stage that always happens. Off by default.
codeep-min-version: 2.0.0 codeep-requires-mcp: [postgres] allowed-tools: [read_file, write_file, execute_command]
When enabled in Settings, the agent can automatically verify its changes by running build, tests, or type checking after completing a task. Disabled by default — the agent works freely and you decide when to verify.
Configure in Settings → Agent Auto-Verify: - Off (default) — no automatic verification - Build only — checks compilation after changes - Typecheck only — runs TypeScript/PHP type checking - Test only — runs test suite after changes - Build + Typecheck + Test — full verification
If errors are found, the agent tries to fix them automatically (up to 3 attempts, configurable).
Supported project types:
| Language | Build | Test | Type Check |
|---|---|---|---|
| **Node.js/TypeScript** | npm/yarn/pnpm/bun run build | npm test, vitest, jest | tsc --noEmit |
| **Python** | - | pytest | - |
| **Go** | go build | go test | - |
| **Rust** | cargo build | cargo test | - |
| **PHP/Laravel** | composer run build | phpunit, artisan test | php -l (syntax) |
account sync / account push also carry your personalities and custom slash commands between machines — the Markdown files in ~/.codeep/personalities/ and ~/.codeep/commands/:
codeep account push # Upload local personalities + commands to codeep.dev
codeep account sync # Download them onto a new machine
A manual sync treats the dashboard personality as current. When a changed cloud personality replaces a local file, Codeep first saves the local version under ~/.codeep/backups/personalities/ and then swaps the new file in atomically. Custom commands keep the older additive merge and are never overwritten by a pull. View and edit custom bots in Agent Studio, and prune commands under Custom commands, on the dashboard.
Hooks and MCP server configs are deliberately not synced: hooks run arbitrary shell, and MCP configs often embed tokens, so both stay local to each machine.
| Command | Description |
|---|---|
/provider | Switch AI provider |
/model | Switch AI model |
/model <name> | Load a saved profile shortcut (e.g. /model fast) |
/protocol | Switch API protocol (OpenAI/Anthropic) |
/lang | Set response language (12 languages supported) |
/settings | Adjust temperature, max tokens, timeout, rate limits |
/profile save <name> | Save current provider+model as a named profile |
/profile load <name> | Load a saved profile |
/profile <name> | Shorthand for /profile load <name> |
/profile list | List all saved profiles |
/profile delete <name> | Delete a saved profile |
/cost /stats | Show session token usage and estimated API cost per model |
Model favorites — save provider+model combos and switch instantly:
> /provider # switch to z.ai
> /model glm-5.2
> /profile save fast
> /provider # switch to openai
> /model gpt-5.6-sol
> /profile save work
> /model fast # instantly switch to z.ai / glm-5.2
> /model work # instantly switch to openai / gpt-5.6-sol
| Type | Location |
|---|---|
| Global config | ~/.config/codeep/config.json |
| Project config | .codeep/config.json |
| Global sessions | ~/.codeep/sessions/ |
| Project sessions | .codeep/sessions/ |
| Global logs | ~/.codeep/logs/ |
| Project logs | .codeep/logs/ |
| Variable | Description |
|---|---|
ZAI_API_KEY | Z.AI (international) API key |
ZAI_CN_API_KEY | Z.AI China API key |
OPENAI_API_KEY | OpenAI API key |
ANTHROPIC_API_KEY | Anthropic Claude API key |
DEEPSEEK_API_KEY | DeepSeek API key |
GOOGLE_API_KEY | Google AI (Gemini) API key |
MINIMAX_API_KEY | MiniMax (international) API key |
MINIMAX_CN_API_KEY | MiniMax China API key |
KIMI_CODE_API_KEY | Kimi Code subscription key |
MOONSHOT_API_KEY | Kimi international pay-per-use key |
MOONSHOT_CN_API_KEY | Kimi China pay-per-use key |
XAI_API_KEY | Grok (xAI) API key |
BAILIAN_CODING_PLAN_API_KEY | Qwen international Coding Plan key |
BAILIAN_TOKEN_PLAN_API_KEY | Qwen international Token Plan key |
DASHSCOPE_API_KEY | Qwen international pay-per-use key |
BAILIAN_CODING_PLAN_CN_API_KEY | Qwen China Coding Plan key |
DASHSCOPE_CN_API_KEY | Qwen China pay-per-use key |
MODELSCOPE_API_KEY | ModelScope token for its live model catalog |
OPENROUTER_API_KEY | OpenRouter API key |
| Setting | Default | Description |
|---|---|---|
| Temperature | 0.7 | Response creativity (0.0 - 2.0) |
| Max Tokens | 8192 | Maximum response length |
| API Timeout | 60000ms | Request timeout |
| API Rate Limit | 30/min | Max API calls per minute |
| Command Rate Limit | 100/min | Max commands per minute |
| Agent Mode | ON | ON = agent runs automatically (requires write permission via /grant), Manual = use /agent |
| Agent API Timeout | 180000ms | Timeout per agent API call (auto-adjusted for complexity) |
| Agent Max Duration | 20 min | Maximum time for agent to run (5-60 min) |
| Agent Max Iterations | 50 | Maximum agent iterations (10-500). Modern models finish typical tasks in 3–8 iterations — raise for large autonomous refactors. |
| Agent Confirmation | Dangerous | Never, Dangerous (default), or Always |
| Agent Auto-Commit | Off | Automatically commit after agent completes |
| Agent Branch | Off | Create new branch for agent commits |
| Agent Auto-Verify | Off | Off, Build only, Typecheck only, Test only, or Build + Typecheck + Test |
| Agent Max Fix Attempts | 1 | Max attempts to auto-fix errors when Auto-Verify is enabled. More than 1 usually means the agent is stuck — bail and let the user decide. |
Add keys once on the dashboard, then sync them to any machine:
codeep account sync # Pull keys + config from codeep.dev → local
codeep account push # Push local keys + config → codeep.dev
Keys are encrypted at rest using AES-256-GCM.
/diff - Review unstaged changes with AI assistance/diff --staged - Review staged changes/commit - Generate conventional commit messages| Command | Description |
|---|---|
/diff | Review unstaged git changes |
/diff --staged | Review staged git changes |
/commit | Generate commit message for staged changes |
/git-commit [msg] | Commit current changes with message |
/push | Push to remote repository |
/pull | Pull from remote repository |
Codeep supports the [Agent Client Protocol (
Codeep 是一个自主的 AI 编程代理,能够读取您的项目,运行命令,写入和验证代码。它比自动完成更深入,支持多种编程语言和模型(包括 Claude、Gemini、DeepSeek、GLM 和 Op)。
Codeep 提供了多项安全功能,包括 API 密钥的安全存储(macOS Keychain / Linux Secret Service)、项目权限控制(读取或写入)、输入验证和清理、可配置的速率限制、代理沙盒化到项目目录以及危险命令的阻止(rm -rf /、sudo 等)。
安装 Codeep 需要以下步骤:1. 全局安装 Codeep:npm install -g codeep 2. 在 Zed 的 settings.json 中添加 Codeep 配置:"agent_servers": { "Codeep": { "type": "custom", "command": "codeep", "args": ["acp"] } } 3. 确保您的 API 密钥已设置在 Zed 使用的环境中:export DEEPSEEK_API_KEY=your_key # 或者使用其他提供商 4. 在 Zed 的 AI 面板中选择 Codeep 作为代理。
使用 Codeep 的示例包括:在 macOS Apple Silicon 上使用 curl 命令下载 Codeep 二进制文件并将其安装到 /usr/local/bin 中。
Codeep 的配置包括 maxIterations(可选的预算)、tools(允许列表,用于防止研究人员写入文件)以及 agentAutoReview(自动审查功能)等。
Codeep 提供了 API 密钥的同步功能,允许您在 Codeep.dev 上添加密钥,然后在任何机器上同步它们:codeep account sync # 从 codeep.dev 拉取密钥和配置 codeep account push # 将本地密钥和配置推送到 codeep.dev
Codeep 支持 Git 集成,包括 /diff(查看未暂存的更改)、/diff --staged(查看暂存的更改)、/commit(生成规范的提交消息)以及 /git-commit [msg](提交当前更改)等命令。它还支持 Zed 编辑器集成(ACP),允许您在 Zed 中直接使用 Codeep 作为 AI 编程代理。
高潜力自动化AI工作流工具
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。
✅ Apache 2.0 — 宽松开源协议,可商用,需保留版权声明和 NOTICE 文件,含专利授权条款。
AI Skill Hub 点评:代码智能助手 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 | Codeep |
| 原始描述 | 开源AI工作流:An autonomous AI agent that reads your whole project, runs commands, and writes 。⭐20 · TypeScript |
| Topics | aiai-agenttypescriptcli-app |
| GitHub | https://github.com/VladoIvankovic/Codeep |
| License | Apache-2.0 |
| 语言 | TypeScript |
收录时间:2026-06-09 · 更新时间:2026-06-11 · License:Apache-2.0 · 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