经 AI Skill Hub 精选评估,智能编码代理 获评「推荐使用」。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 7.5 分,适合有一定技术背景的用户使用。
智能编码代理 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。
智能编码代理 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:go install(推荐) go install github.com/mochow13/keen-code@latest # 方式二:从源码编译 git clone https://github.com/mochow13/keen-code cd keen-code go build -o keen-code . # 方式三:下载预编译二进制 # 访问 Releases 页面下载对应平台二进制文件 # https://github.com/mochow13/keen-code/releases
# 查看帮助 keen-code --help # 基本运行 keen-code [options] <input> # 详细使用说明请查阅文档 # https://github.com/mochow13/keen-code
# keen-code 配置说明 # 查看配置选项 keen-code --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 KEEN_CODE_CONFIG="/path/to/config.yml"
<img src="./assets/keen-code.png" alt="Keen Code" width="350"/>
</div>
Keen Code is a terminal-based AI coding agent like Claude Code or Codex CLI. Written in Go, it is simpler, lighter, minimalistic but useful coding agent for typical software engineering tasks.
Keen Code is highly opinionated. It avoids features that are not necessarily needed or useful for a regular software engineer. It tries to avoid unnecessary complexity and attempts to keep the agent harness as simple as possible.
From requirements to implementation, Keen Code was engineered using a wide range of coding agents and agentic IDEs like Cursor, Windsurf, Claude Code, OpenCode, Codex CLI, and Kimi CLI. At any given time, Keen Code was developed by a single agent, meaning, no multi-agent orchestration was used.
By far, AI coding agents are the most ubiquitous use case in the era of AI agents. The goal of the project is to showcase how coding agents can be used to develop coding agents themselves. This is why most prompts and output docs are saved as markdown files in the .ai-interactions directory.
Keen Code is also an experiment to play with the new way of working where engineers work with AI agents to develop software. In this setting, engineers are sometimes referred to as "orchestrators".
Every line of code in this repo was written by an AI agent. The full paper trail — prompts, plans, design docs — is preserved in .ai-interactions/. See TOUR.md for the full story.
/model. More providers will be added in the future.read_file, write_file, edit_file, glob, grep, bash. Deliberately lean./thinking to change the thinking effort level for the current model. All models that support thinking can be configured.TurnMemory summaries instead of raw tool traces. More information can be found in docs/turn-memory.md. An analysis of the tradeoffs and rationale can be found in docs/turn-memory-analysis.md./compact to compact the context.curl -fsSL https://raw.githubusercontent.com/mochow13/keen-code/main/scripts/install.sh | bash
To pin a specific version:
curl -fsSL https://raw.githubusercontent.com/mochow13/keen-code/main/scripts/install.sh | bash -s -- -v v0.16.1
Installs to /usr/local/bin if writable, otherwise $HOME/.local/bin.
Install the CLI globally:
npm install -g keen-code
Check that the install worked:
keen --version
which keen
You can also run it without a global install:
npx keen-code --version
All features follow a spec → plan → task → review cycle. Here's a concrete example — the read_file tool from Phase 3:
Spec — prompts/phase-3/prompt-3_read-file-tool.md Requirements defined upfront: ask permission before reading, respect FileGuard path rules, text files only, 1 MB limit, support relative and absolute paths.
Plan — outputs/phase-3/output-3_read-file-tool.md Design doc produced by the agent: how Guard.CheckPath maps to the REPL permission prompt, exact struct contracts, permission flow diagram.
Task — prompts/phase-3/prompt-2_phase-3-tasks.md Implementation broken into steps — tool contract, permission bridge, REPL selector, unit tests — each approved before the next began.
Review — (inline feedback during implementation) The LLM was rejecting .go files because MIME detection flagged them as binary. Review caught this; switched to character-based text validation. The fix landed in the same iteration.
极简的AI编码代理,值得关注
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:智能编码代理 的核心功能完整,质量良好。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 | keen-code |
| 原始描述 | 开源AI工作流:A minimal CLI-based coding agent written in Go。⭐17 · Go |
| Topics | ai-agentai-assistantgo |
| GitHub | https://github.com/mochow13/keen-code |
| License | MIT |
| 语言 | Go |
收录时间:2026-06-02 · 更新时间:2026-06-02 · 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