bitrouter

Use this skill when the user wants to install, configure, run, or troubleshoot BitRouter — an LLM proxy that runs two ways: a local Rust daemon at http://localhost:4356 (BYOK) or BitRouter Cloud at https://api.bitrouter.ai/v1 (managed, brk_* keys, Stripe…

Use when evaluating BitRouter route decisions or Eval Exchange subjects with task-native verifiers, human reviewers, private enterprise evaluators, agentic judges, or genuinely uncategorized evaluator sources.

Use when planning, launching, resuming, auditing, or reproducing a BitRouter Terminal-Bench 2.1 benchmark with Harbor, Terminus 2, and AWS EC2, including short policy iterations, one-time controls, model comparisons, or public full runs.

Set up and run BitRouter as a local LLM proxy that routes requests to OpenAI, Anthropic, Google, and custom providers through a single endpoint. Use this skill when you need to install bitrouter, configure LLM providers, start the proxy server, or route model…

Select the best LLM model for a task from 33 available models routed through BitRouter. Use this skill when choosing which model to use for a specific task, optimizing cost vs quality, switching models mid-workflow, or creating task-specific routes. Triggers…

Use this skill when driving pi-agent with the BitRouter provider — choosing local vs cloud target, configuring env vars, obtaining keys, and troubleshooting model discovery. Trigger when the user mentions the BitRouter pi package, BITROUTER_TARGET,…

Analyze this codebase's LLM usage and reduce spend with BitRouter — run estimate, audit, or optimize, and read the live observed-savings widget. Use when the user asks about LLM cost, model routing, or BitRouter policy.