AtomCode 是 AI Skill Hub 本期精选AI工具之一。综合评分 8.0 分,整体质量较高。我们强烈推荐将其纳入你的 AI 工具库,帮助提升工作效率。
AtomCode 是一款基于 Rust 开发的开源工具,专注于 代码编辑、AI工具、Rust 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。
AtomCode 是一款基于 Rust 开发的开源工具,专注于 代码编辑、AI工具、Rust 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:cargo install(推荐) cargo install atomcode # 方式二:从源码编译 git clone https://github.com/atomgit-atomcode/atomcode cd atomcode cargo build --release # 二进制在 ./target/release/atomcode
# 查看帮助 atomcode --help # 基本运行 atomcode [options] <input> # 详细使用说明请查阅文档 # https://github.com/atomgit-atomcode/atomcode
# atomcode 配置说明 # 查看配置选项 atomcode --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 ATOMCODE_CONFIG="/path/to/config.yml"
_ _ ____ _
/ \ | |_ ___ _ __ ___ / ___|___ __| | ___
/ _ \| __/ _ \| '_ _ \ | / _ \ / _ |/ _ \
/ ___ \ || (_) | | | | | | |__| (_) | (_| | __/
/_/ \_\__\___/|_| |_| |_|\____\___/ \__,_|\___|
<p align="center"> <strong>Open-source terminal AI coding agent written in Rust</strong> </p>
<p align="center"> English · <a href="./README.zh-CN.md">简体中文</a> </p>
<p align="center"> <a href="#installation">Install</a> · <a href="#quick-start">Quick Start</a> · <a href="#features">Features</a> · <a href="#architecture">Architecture</a> · <a href="#development">Development</a> · <a href="#contributing">Contributing</a> · <a href="#community">Community</a> </p>
<p align="center"> <img src="https://img.shields.io/badge/version-5.0.9-blue" alt="version"> <img src="https://img.shields.io/badge/rust-1.88%2B-orange" alt="rust"> <img src="https://img.shields.io/badge/license-MIT-green" alt="license"> <img src="https://img.shields.io/badge/platform-macOS%20%7C%20Linux%20%7C%20HarmonyOS%20PC%20%7C%20Windows-lightgrey" alt="platform"> <a href="https://atomgit.com/atomgit_atomcode/atomcode" target="_blank"> <img src="https://atomgit.com/atomgit_atomcode/atomcode/star/badge.svg" alt="AtomGit Star"/> </a> </p>
---
This project is 100% AI-generated. Every line of code, every architectural decision's implementation, and every commit was written by AI. The human developer serves solely as the decision-maker and product manager — defining what to build, not how to build it.
---
AtomCode is an AI coding agent that lives in your terminal. Give it a task in natural language, and it will read your codebase, edit files, run commands, and verify its work — autonomously.
Think of it as an open-source alternative to Claude Code / Cursor Agent, but running entirely in your terminal and connecting to any OpenAI-compatible API.
crates/atomcode-codingplan-crypto/ in this repository is an open-source placeholder. The real request-signing implementation is closed-source and is only overlaid by the official release pipeline, so a self-built binary cannot sign requests to AtomCode's official service. Binaries installed via the official installer above (or the package managers below) are official builds and include the signer. In practice this means:
- /login cannot claim the official free CodingPlan models in self-built binaries. Signing is kept closed-source to prevent the free plan from being abused outside official builds. - Connecting your own API providers is unaffected: any provider configured under providers.* in ~/.atomcode/config.toml (DeepSeek, OpenAI, or any OpenAI-compatible endpoint) works without the signer.
- Rust 1.88+ (for building; older Cargo versions cannot parse the current lockfile) - An API key from any supported provider (or an AtomGit account for /login; the free CodingPlan models require an official build — see "About the official CodingPlan" above)
For Windows PowerShell users:
irm https://raw.atomgit.com/atomgit_atomcode/atomcode/raw/main/scripts/install.ps1 | iex
For Linux / macOS / WSL / MSYS / Git-Bash / HarmonyOS PC users:
curl -fsSL https://raw.atomgit.com/atomgit_atomcode/atomcode/raw/main/scripts/install.sh | sh
Both scripts download the official prebuilt binary for the latest release (auto-detected from the AtomGit API), install it, and add it to your PATH. As official builds they include the request signer, so /login can claim the free CodingPlan models (see "About the official CodingPlan" below).
Environment variable overrides: ATOMCODE_VERSION pins a release tag, ATOMCODE_PREFIX picks the install directory (see the script headers for details).
npm run build # outputs webui/dist/, embedded by the next Rust build cd ..
Skip this step if you don't use the webui. The release scripts build the
frontend automatically before `cargo build`. After rebuilding the frontend,
force a daemon recompile so the new bundle is re-embedded (`cargo clean -p
atomcode-daemon`) — cargo does not track changes under `webui/dist/`. Then
build and install:
bash cargo install --path crates/atomcode-cli --locked
The binary will be generated at `target/release/atomcode` and installed to
`~/.cargo/bin/atomcode` for macOS / Linux / HarmonyOS PC and `$env:USERPROFILE/.cargo/bin/atomcode.exe`
for Windows. Make sure that `~/.cargo/bin` (or `%USERPROFILE%\.cargo\bin` on Windows) is
in your `PATH`.
To compile without installing, run:
bash
npm install -g @atomgit.com/atomcode
brew install --cask atomcode ```
Remove AtomCode and (optionally) its data:
atomcode uninstall # interactive: per-group prompts
atomcode uninstall --keep-data # only remove binary + PATH edit
atomcode uninstall --purge # remove everything, including ~/.atomcode
atomcode uninstall --dry-run # show plan, change nothing
If the binary is already broken or missing:
```bash curl -fsSL https://raw.atomgit.com/atomgit_atomcode/atomcode/raw/main/scripts/uninstall.sh | sh
```bash git clone https://atomgit.com/atomgit_atomcode/atomcode.git cd atomcode
cargo build
cargo build --release ```
cargo check
cargo install --path crates/atomcode-cli ```
- Follow the project's core principles — especially tech-stack neutrality (no language/framework-specific logic in the core engine; detect via probes like package.json / Cargo.toml / pom.xml and route through adapters) - All tool failures must be graceful — return the error as an observation to the LLM, never panic - Destructive operations must require user approval - Keep the system prompt compact (~1.5K tokens) - Run cargo fmt and cargo clippy before submitting
Config is stored at ~/.atomcode/config.toml. A minimal single-provider setup looks like this:
default_provider = "deepseek"
[providers.deepseek]
type = "openai"
api_key = "sk-..."
model = "deepseek-chat"
base_url = "https://api.deepseek.com/v1"
context_window = 64000
You can declare multiple providers and switch between them with /model or /provider. A complete reference covering Claude / OpenAI / OpenAI-compatible endpoints (DeepSeek, GLM, SiliconFlow, OpenRouter...) / Ollama, plus the [datalog] section, lives at docs/config.example.toml — copy and edit the bits you need.
After editing config.toml by hand, run /reload inside atomcode to pick up the changes without restarting.
Review all changes in the current git diff. If specific files are given, review only: $ARGUMENTS EOF ```
Run /help commands to list all loaded custom commands.
Priority rule. A custom command cannot shadow a built-in command with the same name. If a built-in/reviewalready exists, a project-levelreview.mdwon't appear in completion or dispatch.
cargo run -p atomcode-daemon ```
AtomCode CLI can also be installed via the following package managers:
```bash
atomcode 是一款基于 Rust 开发的开源终端 AI Coding Agent。它旨在为开发者提供一个高效、轻量且强大的命令行 AI 编程助手,通过直接在终端环境中运行,实现智能化的代码编写与任务处理能力。
atomcode 具备强大的 AI 驱动能力,能够理解并执行复杂的编程任务。其核心设计遵循技术栈中立原则,能够通过探测 package.json、Cargo.toml 或 pom.xml 等文件自动识别项目���境,并通过适配器进行路由,确保在不同编程语言和框架下的高度兼容性。
在使用 atomcode 之前,请确保您的系统已安装 Rust 1.88+ 版本(旧版 Cargo 可能无法解析当前的 lockfile),并已安装 Git。此外,您需要准备一个支持的 LLM Provider 的 API key 用于运行时测试,或者拥有 AtomGit 账号以使用 /login 功能。
您可以通过多种方式安装 atomcode:使用 npm 进行全局安装(npm install -g @atomgit.com/atomcode),或者使用 Homebrew 进行安装(brew install --cask atomcode)。此外,开发者也可以通过源码进行构建。
atomcode 遵循核心设计原则:保持技术栈中立,不将特定语言逻辑硬编码在核心引擎中;所有工具调用失败时必须优雅处理,将错误作为 Observation 返回给 LLM 而非直接 Panic;对于破坏性操作,系统会强制要求用户审批,以确保开发过程的安全与可控。
项目的配置文件存储在用户目录下的 ~/.atomcode/config.toml 中。您可以在配置文件中定义多个 Provider,并支持通过 /model 命令在不同模型间快速切换。配置格式遵循 TOML 标准,允许您自定义 api_key、base_url 及 context_window 等关键参数。
atomcode 提供 Daemon 模式,可以通过运行 cargo run -p atomcode-daemon 来启动 HTTP API 服务,为其他集成环境或外部调用提供后端支持。
atomcode CLI 支持通过多种包管理器进行安装,并能够通过探测项目配置文件(如 package.json、Cargo.toml 等)来智能识别开发环境,从而实现自动化的工作流适配。
高质量的开源AI代码编辑工具
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。
✅ 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。
经综合评估,AtomCode 在AI工具赛道中表现稳健,质量优秀。如果你已有明确的使用需求,可以直接上手体验;如果还在评估阶段,建议对比同类工具后再做决策。
| 原始名称 | atomcode |
| 原始描述 | 开源AI工具:An open-source alternative to Claude Code. Connect any LLM, edit code, run comma。⭐148 · Rust |
| Topics | 代码编辑AI工具Rust |
| GitHub | https://github.com/atomgit-atomcode/atomcode |
| License | MIT |
| 语言 | Rust |
收录时间:2026-07-02 · 更新时间:2026-07-03 · License:MIT · AI Skill Hub 不对第三方内容的准确性作法律背书。