The data plane for agents. Arch is a models-native proxy server that handles the plumbing work in AI: agent routing & hand off, guardrails, end-to-end logs and traces, unified access to LLMs from OpenAI, Anthropic, Ollama, etc. Build agents faster, and scale them reliably.
A curated list of Awesome-LLM-Ensemble papers for the survey "Harnessing Multiple Large Language Models: A Survey on LLM Ensemble"
Lightweight & fast AI inference proxy for self-hosted LLMs backends like Ollama, LM Studio and others. Designed for speed, simplicity and local-first deployments.
Unified interface server for various LLM providers with OpenAI API format
Compose, train and test fast LLM routers
NeurIPS 2025 paper "MESS+: Dynamically Learned Inference-Time LLM Routing in Model Zoos with Service Level Guarantees"
Add a description, image, and links to the llm-routing topic page so that developers can more easily learn about it.
To associate your repository with the llm-routing topic, visit your repo's landing page and select "manage topics."