Why teams use it
- Choose frontier and open models from supported coding tools.
- Manage model routing without changing each engineer’s setup for every policy change.
- Use eligible Claude subscription allowance first through the optional on-device proxy.
- Track usage and savings per engineer.
How it works
- Configure a coding key with the Valar CLI.
- Connect each harness. Claude Code and Desktop can use the shared proxy or direct routing; other harnesses use their own integrations.
- Choose models in the harness. Your key’s policy controls requests served through Valar. With quota-first enabled on the proxy, eligible Claude requests can use your subscription instead.
- Review Valar-served usage and savings in the dashboard.
Get started
Set up ValarCode
Install the CLI, create a coding key, and connect a harness.
Model routing
Choose how your coding key routes model requests.
On-device proxy
Shared proxy setup and lifecycle.
Models
The open-weight targets and the frontier Claude tiers.
Analytics & savings
Per-engineer usage and how savings are worked out.
Supported harnesses
Each harness has its own page covering how to connect it and what the CLI writes behind the scenes:Claude Code
valar claude onClaude Desktop
valar claude-desktop onCursor
valar cursor onCodex
valar codex onopencode
valar opencode onPi
valar pi onOh My Pi
valar ohmypi onVS Code
valar copilot onLiteLLM
If you run a LiteLLM proxy, you can keep it and still use ValarCode. Claude Code (or Pi) points at LiteLLM, which forwards requests to Valar. For per-engineer routing and attribution, LiteLLM must preserve the client ID header when forwarding requests.LiteLLM integration
Route Claude Code through a LiteLLM proxy without losing per-engineer attribution.