AI Skill Hub 推荐使用:Herm AI编码助手 是一款优质的AI工具。AI 综合评分 7.8 分,在同类工具中表现稳健。如果你正在寻找可靠的AI工具解决方案,这是一个值得深入了解的选择。
Herm AI编码助手 是一款基于 Go 开发的开源工具,专注于 AI智能体、编码助手、工作流 等核心功能。作为 GitHub 开源项目,它拥有活跃的社区支持和持续的版本迭代,代码完全透明可审计,支持本地部署以保护数据隐私。无论是个人使用还是集成到企业工作流,都能提供稳定可靠的解决方案。
Herm AI编码助手 是一款基于 Go 开发的开源工具,专注于 AI智能体、编码助手、工作流 等核心功能。作为 GitHub 开源项目,它拥有活跃的社区支持和持续的版本迭代,代码完全透明可审计,支持本地部署以保护数据隐私。无论是个人使用还是集成到企业工作流,都能提供稳定可靠的解决方案。
# 方式一:go install(推荐) go install github.com/aduermael/herm@latest # 方式二:从源码编译 git clone https://github.com/aduermael/herm cd herm go build -o herm . # 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/aduermael/herm/releases
# 查看帮助 herm --help # 基本运行 herm [options] <input> # 详细使用说明请查阅文档 # https://github.com/aduermael/herm
# herm 配置说明 # 查看配置选项 herm --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 HERM_CONFIG="/path/to/config.yml"
A coding agent CLI that's containerized by default. Every command runs inside a Docker container, nothing touches your host. No approval prompts, no "are you sure?" dialogs. Just let it work.

herm is built on top of langdag, a Go library for managing LLM conversations as directed acyclic graphs with multi-provider support. This project originally started as a way to dogfood langdag.
curl -fsSL https://raw.githubusercontent.com/aduermael/herm/main/install.sh | bash
herm
You'll need a configured deployment such as Anthropic, OpenAI, OpenRouter, Gemini, Grok, Azure OpenAI, or local Ollama. Add credentials with /config on first run.
Herm stores model choices as canonical IDs like openai/gpt-4.1-2025-04-14. Langdag resolves those IDs through your configured deployments and routing policy at request time, so newly published catalog models can appear without a new herm build when they use an already-supported API. Routing rules are scoped provider/model overrides; models that do not match a rule keep using automatic deployment selection.
<details> <summary>How is it different from Claude Code?</summary>
Claude Code runs directly on your host and needs your approval for every potentially dangerous action. herm runs everything in containers, so the agent can act freely without risking your system. herm also supports multiple model providers and ships its system prompts in the open. </details>
<details> <summary>How is it different from OpenCode?</summary>
OpenCode is a great terminal AI assistant, but it runs on your host like most coding agents. herm's core idea is that containerization should be the default — not an afterthought. If the agent can't break anything, you don't need permission prompts. </details>
<details> <summary>How is it different from Pi Coding Agent?</summary>
Pi focuses on extensibility through TypeScript plugins and a large ecosystem of community packages. herm takes a different bet: safety through containerization. Instead of asking users to manage permissions, herm sandboxes everything by default so the agent can operate autonomously. </details>
<details> <summary>What is the logo supposed to represent?</summary>
It's an hermit crab called Herm, short for Herman. It represents the hermetic nature of the agent — everything sealed inside its shell. </details>
Herm融合AI智能体与容器安全隔离的创新方案,解决了AI编码的安全性问题。Go语言实现保证高效性,架构设计合理,但需完善文档和实战案例。
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。
总体来看,Herm AI编码助手 是一款质量良好的AI工具,在同类工具中具备一定竞争力。AI Skill Hub 将持续追踪其更新动态,建议收藏备用,结合自身场景选择合适时机引入使用。
| 原始名称 | herm |
| 原始描述 | 开源AI工作流:Terminal-native AI coding agent running in containers.。⭐192 · Go |
| Topics | AI智能体编码助手工作流容器化沙箱环境Go开发 |
| GitHub | https://github.com/aduermael/herm |
| License | MIT |
| 语言 | Go |
收录时间:2026-05-21 · 更新时间:2026-05-22 · License:MIT · AI Skill Hub 不对第三方内容的准确性作法律背书。