AtomCode

Requirements

• 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)

Prerequisites

• Rust 1.88+ — install via rustup
• Git
• A supported LLM provider API key (for runtime testing)

Installation

Install using npm

npm install -g @atomgit.com/atomcode

Install using Homebrew

brew install --cask atomcode ```

Uninstall

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

Build from Source

```bash git clone https://atomgit.com/atomgit_atomcode/atomcode.git cd atomcode

Debug build (fast compilation, slower runtime)

cargo build

Release build (slower compilation, optimized binary)

cargo build --release ```

Check compilation without building

cargo check

Build and install to ~/.cargo/bin

cargo install --path crates/atomcode-cli ```

Quick Start

Guidelines

- 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

2. Configuration

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.

Daemon (HTTP API)

cargo run -p atomcode-daemon ```

Package Managers

AtomCode CLI can also be installed via the following package managers:

```bash