Skip to main content

​
AI Coding Tools

Rigbox workspaces come with a full Linux environment, SSH access, and a managed AI proxy — making them a natural home for AI coding agents. Tools like Claude Code, Codex CLI, OpenCode, and Gemini CLI work out of the box when you activate managed credits.

​
How It Works

AI coding tools use the same provider SDKs (Anthropic, OpenAI, Google) that the managed proxy already supports. When you run rig proxy on inside a workspace, the proxy sets environment variables that redirect SDK traffic through Rigbox’s infrastructure. Your credits cover the usage — no API keys needed.

​
Supported Tools

ToolProviderWhat it does
Claude CodeAnthropicAgentic coding assistant that edits files, runs commands, and manages git
Codex CLIOpenAITerminal-based AI agent for code generation and refactoring
OpenCodeAnyOpen-source terminal coding agent, supports multiple providers
Gemini CLIGoogleGoogle’s terminal AI assistant for code and shell tasks
AiderAnyAI pair programming in your terminal

​
Quick Setup

​
1. Activate managed credits

From inside your workspace: 
eval $(rig proxy on)
This sets the environment variables each SDK needs (ANTHROPIC_BASE_URL, OPENAI_BASE_URL, etc.) to route through the Rigbox proxy.

​
2. Install your preferred tool

npm install -g @anthropic-ai/claude-code

​
3. Start coding

The tools pick up the proxy environment variables automatically — no API key configuration needed. 
claude
Use the dev or full image for AI coding tools. They include build toolchains that coding agents often need (compilers, linters, test runners).

​
Tool-Specific Setup

​
Claude Code

Claude Code works immediately after rig proxy on — it reads ANTHROPIC_BASE_URL from the environment. 
eval $(rig proxy on)
claude
Claude Code can edit files, run shell commands, manage git, and run tests inside the workspace. Since each workspace is an isolated VM, there’s no risk of the agent affecting other projects.
Claude Code uses Claude Sonnet by default. To use Opus, pass --model claude-opus-4-20250514. Credit consumption is higher for Opus.

​
Codex CLI

Codex reads OPENAI_BASE_URL from the environment. 
eval $(rig proxy on)
codex "add error handling to the API routes in src/routes/"

​
Gemini CLI

Gemini CLI reads GOOGLE_API_KEY or the configured base URL from the environment. 
eval $(rig proxy on)
gemini

​
Aider

Aider supports multiple providers. The proxy environment variables are picked up automatically. 
eval $(rig proxy on)

# Use with Anthropic (default after proxy on)
aider --model claude-sonnet-4-20250514

# Use with OpenAI
aider --model gpt-4o

# Use with Google
aider --model gemini/gemini-2.5-pro

​
OpenCode

OpenCode uses the same SDK environment variables. Configure it to use your preferred provider. 
eval $(rig proxy on)
opencode

​
Automate with Setup Scripts

If you regularly use AI coding tools, create a setup script that installs them automatically on workspace boot: 
#!/bin/bash
# Install AI coding tools
npm install -g @anthropic-ai/claude-code
pip install aider-chat
Attach this script to your workspace or template so every new workspace comes pre-configured.

​
Monitor Credit Usage

AI coding tools can consume credits quickly — especially agentic tools that make many API calls in a loop. Monitor your balance: 
curl -s https://api.rigbox.dev/api/users/me/credits \
  -H "Authorization: Bearer $RIGBOX_TOKEN" | jq .
Or from inside the workspace: 
rig status
Agentic tools like Claude Code and Codex can make dozens of API calls per task. A single complex refactoring session might use 50-200 credits depending on the model and codebase size. Monitor your balance if you’re on the free tier.

​
BYOK Alternative

If you burn through managed credits quickly, switch to BYOK mode and use your own API keys for unlimited usage: 
curl -X PUT https://api.rigbox.dev/api/workspaces/{workspace_id}/ai-config \
  -H "Authorization: Bearer $RIGBOX_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"mode": "byok", "provider": "anthropic", "api_key": "sk-ant-..."}'
Then run rig proxy on again to update the environment.

​
Why Rigbox for AI Coding

BenefitDetail
Isolated environmentAgents can run commands, install packages, and modify files without affecting your local machine
No key managementManaged credits mean zero API key configuration
Full Linux VMBuild tools, compilers, databases — everything agents need is available
SSH accessWork alongside the agent: SSH in to review changes, run tests, or pair-program
SnapshotsSnapshot before a big refactor, restore if the agent goes sideways

​
Next Steps