Show HN: VernLLM – LLM fallback without a gateway
VernLLM is a TypeScript/Node library that replaces external LLM gateway services by handling rate limiting, multi-provider fallback, and circuit breaking inside the application process. It targets TypeScript developers who want to avoid deploying and trusting a separate network-hop service with their API keys.
VernLLM is a TypeScript/Node library that replaces external LLM gateway services by handling rate limiting, multi-provider fallback, and circuit breaking inside the application process. It targets TypeScript developers who want to avoid deploying and trusting a separate network-hop service with their API keys.
VernLLM is a TypeScript library that provides retry, timeout, circuit-breaking, and caching for LLM API calls across multiple providers. It solves the problem of inconsistent error handling and reliability in production LLM integrations.
VernLLM is a TypeScript library that provides retry, timeout, circuit-breaking, and caching for LLM API calls across multiple providers. It solves the problem of inconsistent error handling and reliability in production LLM integrations.
Atom is an open-source multi-agent platform with an LLM Gateway module that acts as a unified local proxy for routing and failover between local Ollama models and cloud APIs. It solves the problem of managing API switching, failover logic, and context limits for developers using local models alongside cloud endpoints in agent workflows, Cursor/Windsurf, or custom scripts.
Atom is an open-source multi-agent platform with an LLM Gateway module that acts as a unified local proxy for routing and failover between local Ollama models and cloud APIs. It solves the problem of managing API switching, failover logic, and context limits for developers using local models alongside cloud endpoints in agent workflows, Cursor/Windsurf, or custom scripts.
A developer is asking for an open-source, self-hosted AI/LLM gateway that supports dynamic runtime routing and model management, to sit between agent frameworks and multiple LLM providers. They need to add/remove models, enable/disable them, and change routing weights without restarting, plus features like load balancing, fallbacks, retries, timeouts, health checks, and an OpenAI-compatible API. They've looked at LiteLLM and Portkey but find them lacking for simple self-hosting.
A developer is asking for an open-source, self-hosted AI/LLM gateway that supports dynamic runtime routing and model management, to sit between agent frameworks and multiple LLM providers. They need to add/remove models, enable/disable them, and change routing weights without restarting, plus features like load balancing, fallbacks, retries, timeouts, health checks, and an OpenAI-compatible API. They've looked at LiteLLM and Portkey but find them lacking for simple self-hosting.
Llmbridge is an LLM gateway/proxy written in C++ that routes requests to LLM providers with sub-millisecond added latency. It targets developers and teams serving LLM traffic who find existing gateways too slow or heavyweight. Posts show launch only; no features beyond latency claims are documented.
Llmbridge is an LLM gateway/proxy written in C++ that routes requests to LLM providers with sub-millisecond added latency. It targets developers and teams serving LLM traffic who find existing gateways too slow or heavyweight. Posts show launch only; no features beyond latency claims are documented.