* [OmniRoute v3.8.7](https://github.com/diegosouzapw/OmniRoute) – AI gateway providing an OpenAI-compatible endpoint with multi-provider routing, load balancing, retries, rate limits, caching, and observability for cost-aware inference.

* [Ferro Labs AI Gateway v1.1.0](https://github.com/ferro-labs/ai-gateway) – High-performance Go-based AI gateway routing OpenAI-compatible LLM requests across 30+ providers with caching, guardrails, and cost controls.

* [Bifrost ent-v1.4.6-datasheet...](https://github.com/maximhq/bifrost) – High-performance AI gateway offering multi-provider access with automatic failover, load balancing, and zero-downtime deployments.

* [AlphaClaw v0.9.18](https://github.com/chrysb/alphaclaw) – OpenClaw-focused setup harness providing browser-based onboarding, self-healing watchdog, Git-backed rollback, prompt hardening, and managed integrations.

* [Unkey v2.0.141](https://github.com/unkeyed/unkey) – API authentication and authorization platform for modern developer workflows.

* [Discord API Types 0.38.48](https://github.com/discordjs/discord-api-types) – Type definitions for the Discord API, organized by API version.

* [Inference Gateway v0.24.6](https://github.com/inference-gateway/inference-gateway) – Cloud-native, high-performance proxy unifying multiple LLM providers with streaming, multimodal, MCP and function-calling support.

* [Tingly Box v0.260531.1](https://github.com/tingly-dev/tingly-box) – High-performance desktop LLM proxy that unifies access to many models and providers via a single OpenAI-compatible API.