> ## Documentation Index > Fetch the complete documentation index at: https://docs.inference.net/llms.txt > Use this file to discover all available pages before exploring further. # Catalyst by Inference.net Catalyst is a platform for understanding, evaluating, and improving the AI systems you ship. [Create an account](https://inference.net/register) to get started with Catalyst. ## The Catalyst platform Catalyst is built around two products. Use them on their own or together. Capture full traces of every LLM call, tool call, and agent step. Then let Halo, our open-source agent-loop optimizer, read your traces and tell you what to fix in prompts, tools, and the harness itself. Route LLM traffic through Catalyst Gateway to capture every request, watch usage and cost, build datasets, run evals, and fine-tune and deploy task-specific models on dedicated GPUs. Tracing is for agent improvement. Gateway is for inference observability and training task-specific models from your captured traffic. Most teams start with one and add the other later. They also compose: when your agent calls LLMs through Gateway, trace spans line up with the same requests Gateway is recording. ## Quick Start ### Tracing Install the tracing SDK and capture LLM calls, tool calls, and agent steps in minutes. Inspect trace trees in the dashboard and run Halo to find what to improve. ### Gateway Route traffic through the Catalyst gateway to capture LLM calls and view metrics. Define quality, measure it, and compare models side by side. The full loop: data, training, and a production endpoint. Call open-source and custom models running on Inference.net. ## Catalyst Platform Collect OpenInference-shaped traces from LLM SDKs, agent frameworks, and custom application code. Capture your LLM traffic and get metrics and visibility into your production usage. Create and manage datasets for evaluation and training. Evaluate models to measure quality across model candidates. Train a custom model on your production data to improve performance, lower latency and cost. Deploy a model to a dedicated GPU to use in production.