* [Bifrost cli/v1.0.0](https://github.com/maximhq/bifrost) – High-performance AI gateway offering multi-provider access with automatic failover, load balancing, and zero-downtime deployments.

* [LLM Gateway v1.21.0](https://github.com/theopenco/llmgateway) – API gateway that routes and manages requests across multiple LLM providers with an OpenAI-compatible API, usage analytics, and cost tracking.

* [Octelium v0.45.0](https://github.com/octelium/octelium) – Next-gen self-hosted unified zero-trust secure access platform for VPNs, ZTNA, API/AI gateways, PaaS, and homelab infrastructure.

* [Oh My CPA v0.2.0](https://github.com/WizisCool/oh-my-cpa) – Self-hosted control-plane and usage observability console that manage providers, OAuth, and pricing for CLIProxyAPI with an embedded Go web UI and local SQLite storage.

* [ccLoad v4.12.0](https://github.com/caidaoli/ccLoad) – Go-based API server integrating Claude, Codex, Gemini and OpenAI models with Gin, DB support and Docker deployment.

* [CPA Manager Plus v1.14.6](https://github.com/seakee/CPA-Manager-Plus) – Management panel and Docker-ready manager server providing SQLite-backed usage analytics, request monitoring, model pricing, quota views, and Codex inspection for CLI Proxy API.

* [SubLane v0.6.0](https://github.com/murongg/SubLane) – Lightweight, multi-workspace AI subscription gateway providing isolated team workspaces, account pooling, access control, and usage tracking via a Go service and web dashboard.

* [GoModel v0.1.100](https://github.com/ENTERPILOT/GoModel) – High-performance Go-based AI gateway providing an OpenAI-compatible API and unified access to multiple LLM providers with observability, guardrails, and streaming.

* [1flowbase v0.5.6](https://github.com/taichuy/1flowbase) – Agent-native platform that provides an OpenAI/Claude-compatible AI gateway with model fusion workflows, tool support, and full end-to-end tracing.

* [ThinkWatch Lite v2026.10.18](https://github.com/ThinkWatchProject/ThinkWatch-Lite) – Local gateway that connects AI clients once, records every request with cost and routing, redacts secrets, blocks dangerous tool calls, and enables safe upstream switching.

* [Yolorouter v0.2.8](https://github.com/yolorouter/yolorouter) – Low-overhead streaming LLM gateway that proxies four chat protocols and OpenAI Images/Videos, translating requests across providers with failover and key pooling plus a built-in admin console.

* [Casbin Gateway nightly](https://github.com/apache/casbin-gateway) – Casbin Gateway provides an endpoint that tracks AI coding agents’ requests and grades whether the accessed model API matches the paid provider, with per-agent permissions and records.

* [New API v1.0.0-rc.44](https://github.com/QuantumNous/new-api) – Next-generation LLM gateway and AI asset management system supporting multiple languages.