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 credits or x402 wallet). Unifies OpenAI, Anthropic, Google, OpenRouter, GitHub Copilot, and OpenCode Zen/Go behind one endpoint. Also covers signup on bitrouter.ai, minting brk_ API keys, running auditable benchmarks, migrating off LiteLLM / OpenRouter / any OpenAI- or Anthropic-compatible gateway, editing bitrouter.yaml, and wiring coding-agent harnesses (Claude Code, Codex, Hermes Agent, Harbor Terminus-2, OpenClaw). Trigger on "set up a local LLM proxy", "managed AI gateway", "replace litellm", "point claude code at a proxy", "bitrouter cloud", "brk_ key", anything naming bitrouter.yaml, port 4356, Harbor Terminus-2, or api.bitrouter.ai — even when the user does not name BitRouter directly.

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.