rate limiting

A lightweight API key proxy for self-hosted llama.cpp servers with per-user token usage tracking, rate limiting, and multi-server routing.

Wyolet Relay is a self-hosted LLM router that exposes OpenAI- and Anthropic-compatible endpoints in front of multiple providers. It pools API keys, handles failover and rate limits, tracks usage and cost, and includes a quickstart plus Docker-based deployment.

A Python framework for building OAuth 2.0 authorization servers for MCP servers, with token storage, PKCE, device flow, introspection, and rate limiting.

A Redis-backed concurrency lease manager for FastAPI and Starlette that limits active SSE, LLM, and WebSocket streams instead of request counts.

Self-hosted AI gateway in Go that routes requests across 30+ LLM providers through a single OpenAI- and Anthropic-compatible API.

A Claude Code mod that prevents runaway subagent fan-out, heavy-context prompts, and retry loops from burning through usage limits too quickly.

A governance plugin for OpenClaw that registers instances with a Recursant registry and intercepts tool calls, LLM prompts, and chat messages for auth, PII redaction, rate limiting, and auditing.

vernLLM is a TypeScript LLM call framework that keeps retries, fallback, rate limiting, circuit breaking, caching, and middleware inside your own process. It supports OpenAI-compatible providers plus Anthropic, Gemini, Bedrock, and others via adapters.

NakshGuard is a self-hosted reverse proxy for OpenAI and Anthropic chat APIs that detects and blocks runaway AI agent loops before they waste tokens or API spend. It includes per-agent session tracking, configurable thresholds, shadow mode, and hot config reload.

Aquifer is a self-hosted MCP gateway runtime for buffering spiky agent and API traffic. It queues requests durably in SQLite, dispatches them at a configurable rate, and supports both MCP and HTTP adapters with webhook delivery.