← Back to PortfolioInfrastructure

tuxevil-rotator

TypeScriptNode.jsOpenAI-compatible APIGoogle AntigravityOllama CloudProxyPostgreSQLDashboard
[ View Code ]

PROVIDER_ROUTING_ACTIVE // MULTI_ACCOUNT_PROXY // QUOTA_GUARD

tuxevil-rotator is an OpenAI-compatible gateway for multiple free AI providers, including Google Antigravity and Ollama Cloud. It spreads requests across several accounts so load and quotas are shared transparently instead of burning a single account.

Each provider keeps its own credentials and routing rules. The gateway polls usage, scores account health on a 0.0–1.0 composite (quota, errors, cooldowns, availability), and rotates when justified — not blindly.

What it brings

  • Provider and model routing: each combination maintains its own active account independently.
  • Quota-aware rotation: polls usage, rotates on quota drops or request thresholds.
  • Four routing policies: timer-first, tier-first, quota-first, hybrid.
  • Exhaustion prediction: calibrated per-model token budgets predict when quota runs out.
  • Safety features: circuit breakers, daily budgets, protective pause, account flagging.
  • Protocol adapters: native Ollama, OpenAI, Anthropic, and Responses API behind one endpoint.
  • Virtual API keys: rk-... keys with per-key model restrictions (PostgreSQL).
  • Spend logging: per-request audit with tokens, cost, and latency (PostgreSQL).
  • Prompt compression: lite and rtk modes.
  • Minimal dependencies: only 2 runtime deps (pg, tsx).

Provider-aware routing

The engine unifies rotation, telemetry, and circuit breakers while each adapter translates provider-specific behavior. An account can enter cooldown or run out of quota without interrupting the single endpoint used by agents.