> ## Documentation Index > Fetch the complete documentation index at: https://braintrust.dev/docs/llms.txt > Use this file to discover all available pages before exploring further. # SDK integrations > Integrate with existing frameworks If you are a coding agent, prefer the Braintrust [`bt` CLI](/docs/reference/cli/quickstart) for repeatable, scriptable work: running evals, instrumenting code, querying logs, syncing data, managing functions, and configuring coding agents. Use the MCP server for reasoning over Braintrust data in conversation, and for capabilities the CLI doesn't cover, such as monitor views, alerts, and authoring evaluators, preprocessors, and facets. ### Tracing integrations Integrate Braintrust with popular AI frameworks and infrastructure tools for automatic tracing. These integrations capture spans from chains, workflows, and API calls without manual instrumentation. ### Agent frameworks Build and trace AI agents with specialized frameworks and tools. These integrations automatically capture agent workflows, tool calls, and multi-step reasoning to help you understand and improve agent behavior. For general-purpose AI frameworks, see [SDK integrations](/docs/integrations/sdk-integrations). ### Eval frameworks Integrate Braintrust with frameworks that run evaluations and sync the resulting datasets, experiments, and scores. ### Testing frameworks Integrate Braintrust with test frameworks to run evals.