# Noveum.ai

> Noveum is an AI-native reliability platform for production AI agents and LLM apps. It traces instrumented runs, applies selected compatible checks from a library of 112 published scorers, tests configured voice and chat scenarios, and turns evaluated failures into ranked recommendations. The Python SDK is open source; REST ingest, managed cloud, and scoped enterprise deployment options are available. SOC 2 Type II is in progress, and GDPR requirements can be reviewed for the selected deployment.

## Products
- [Tracing - noveum-trace](https://noveum.ai/novatrace): Open-source Python SDK that records instrumented LLM calls, tool invocations, retrievals, and agent steps as structured traces. Add custom spans and attributes for application-specific work; supported integrations include LangChain, LangGraph, LiveKit, Pipecat, and CrewAI.
- [Chatbot Evaluation - NovaEval](https://noveum.ai/novaeval): Applies selected compatible checks to dataset items from a library of 112 published scorers across 15 categories: 82 Premium, 30 Free, 76 model-backed, and 36 dedicated voice and audio scorers. Model-backed results can include reasoning.
- [Analysis & Recommendations - NovaPilot](https://noveum.ai/novapilot): Analyzes evaluated dataset items, groups recurring failures, and produces ranked prompt, model, parameter, and tool recommendations for engineers to review and verify.
- [Voice AI Agent Evaluation & Testing - NovaSynth](https://noveum.ai/novasynth): Runs reusable personas and scenarios against configured LiveKit, phone, and HTTP chat agents, then records available transcripts, audio, timing, scorer results, and analytics.
- [Guardrails - NovaGuard (Beta)](https://noveum.ai/novaguard): Configures organization- and project-scoped model-spend caps plus request or token limits. Blocking requires enforcement in your application or gateway data plane, which reports usage events back to Noveum.

## Solutions
- [AI Agent Monitoring](https://noveum.ai/solutions/ai-agent-monitoring)
- [LLM Observability](https://noveum.ai/solutions/llm-observability)
- [Agent Evaluation](https://noveum.ai/solutions/agent-evaluation)
- [Debugging & Tracing](https://noveum.ai/solutions/debugging)
- [Scorer Library - 112 published scorers](https://noveum.ai/solutions/scorers)

## Comparisons
- [Noveum vs Langfuse](https://noveum.ai/comparison/noveum-vs-langfuse)
- [Noveum vs Arize & Braintrust](https://noveum.ai/comparison/noveum-vs-arize-braintrust)
- [Noveum vs Arize Phoenix](https://noveum.ai/comparison/noveum-vs-arize)
- [Platform comparison hub](https://noveum.ai/comparison)

## Developers
- [Agent instructions](https://noveum.ai/agents.md): Connection setup, SDK integration, trace verification, evaluations, NovaPilot diagnosis, and validated fixes, with links to the Noveum Agent Skill recipes and scripts.
- [MCP server for AI agents](https://noveum.ai/mcp): Connect an MCP client to https://noveum.ai/api/mcp over OAuth 2.1 sign-in or a Bearer API key. Search the current documentation with search_noveum_docs, read workflow resources, and use guided prompts and tools generated from the current OpenAPI contract for supported tracing, evaluation, NovaPilot analysis, and NovaSynth workflows.
- [MCP server reference](https://noveum.ai/docs/platform/mcp-server-reference): Documentation search, resource and prompt inventory, generated-tool behavior, OAuth connector mode, scopes, and per-client install snippets.
- [Noveum Agent Skill](https://github.com/Noveum/noveum-skill): Open-source integration instructions for SDK setup, trace verification, datasets, evaluations, NovaPilot diagnosis, and validated fixes in your own environment.

## Company & resources
- [About Noveum](https://noveum.ai/about): Why we built an AI-native reliability layer.
- [Enterprise](https://noveum.ai/enterprise): Scope in-VPC, on-premise, self-hosted, or BYO ClickHouse options with deployment-specific security, support, data-flow, and GDPR requirements. SOC 2 Type II is in progress.
- [Pricing](https://noveum.ai/pricing)
- [Documentation](https://noveum.ai/docs)
- [Blog](https://noveum.ai/blog)
- [Changelog](https://noveum.ai/changelog)
- [Case study: MyOperator](https://noveum.ai/case-studies/myoperator): Voice-agent call success from 84% to 95%+ with 200× faster iteration.
- [GitHub - noveum-trace SDK](https://github.com/Noveum/noveum-trace)