> ## Documentation Index > Fetch the complete documentation index at: https://docs.slng.ai/llms.txt > Use this file to discover all available pages before exploring further. # Improve an existing agent Keep your agent where it runs and connect the layers your integration supports. Choose your framework or voice platform below for its setup steps. ## In your own code For LiveKit and Pipecat, you can connect speech models and the context router. The custom LLM guide covers OpenAI-compatible clients. Use SLNG speech models and the context router in a LiveKit agent. Use SLNG speech models and the context router in a Pipecat pipeline. Route your existing OpenAI-compatible LLM calls through the context router. ## On a voice platform These integrations route the language model through the context router. Speech to text and text to speech stay on your platform. Route your ElevenLabs agent's language model through the context router. Route your Vapi assistant's language model through the context router. Route your Deepgram Voice Agent's language model through the context router.