llm-gateway

Single-binary Rust WebSocket gateway for a self-hosted AI assistant: streaming, sessions that survive a reconnect, human-in-the-loop permissions, RAG memory and tool execution.

Audit OpenAI-compatible LLM gateways for transparency gaps and suspicious behavior.

⚡ AI API 网关 / 中转 / 反代生态精选清单 — 把 Claude、OpenAI、Gemini、Grok 聚合到统一接口的开源方案与托管服务

Open-source LLM gateway & observability plane. One OpenAI-compatible API in front of OpenAI, Anthropic, Gemini & Ollama — with cost tracking, caching, rate limiting & automatic fallback. Self-host in one command.

A provider-agnostic OpenAI-shape gateway with tiered routing, confidence escalation, semantic and exact caching, and a cost-per-1k-tokens ledger.

Route Codex and Claude Code main agents and subagents to different models and providers.

AI API gateway / relay: 307 models behind one OpenAI-compatible key. image2.5 $0.0085/image, Seedance 2.0 Mini $0.01056/sec, LLM from $0.0228/M tokens. USD settlement, pay-as-you-go, $1 minimum top-up.

AI API gateway / relay: 307 models behind one OpenAI-compatible key. image2.5 $0.0085/image, Seedance 2.0 Mini $0.01056/sec, LLM from $0.0228/M tokens. USD settlement, pay-as-you-go, $1 minimum top-up.

Hosted TokenLab Model Explorer for ChatGPT Apps and Streamable HTTP MCP

Effortlessly route HTTP requests with powerful, flexible pattern matching and middleware for modern applications.

基于 Spring Boot 3 + WebFlux 的 LLM 统一网关｜OpenAI 兼容入口 · 多供应商路由与熔断降级 · 多租户配额 · Prometheus 可观测

X search for any Pi model through xAI or your own Responses API gateway, with zero runtime dependencies.

Curated list of 200+ AI API providers with daily ranking, OpenAI-compatible API checks, and live /v1/models probing for Claude, DeepSeek, Gemini, and more.

CrossModel organization profile (this README renders as the org homepage).

OpenAI-compatible SDK and tool configuration examples for testing AI8 as a multi-model API gateway

oh-my-pi (omp) plugin: register an AxonHub LLM gateway as the axonhub model provider — auto model discovery, per-model protocol routing (OpenAI/Anthropic/Gemini wires), models.dev enrichment

The cost layer for LLM applications. Open-core gateway, code scanner, and replay simulator for OpenAI/Anthropic/Gemini and 7+ others.

Gateway LLM em Python sobre LiteLLM para Azure OpenAI: virtual keys por usuário/time com orçamento, segredos do vault, observabilidade e deploy no Kubernetes

Cheapest-first LLM routing with response caching, automatic failover and a cost ledger. Runs offline.

Browser-based compatibility checker for OpenAI-compatible and Anthropic Messages endpoints. Tests routes, auth headers, SSE streaming and response shapes, with raw request/response inspection.