Skip to the content
Know your tech before you buy it. Makers: get listed from $49/mo

Noveum

noveum.ai

  • Free plan
  • Linux
  • Web
  • API
  • Self-hosted
7.5 Club score Visit noveum.ai

What Noveum is

Noveum is a platform for evaluating AI agents used in production chat, voice, and workflow systems. NovaTrace records language-model calls, tool use, retrieval, and agent steps, with token use, cost, and latency attached to spans. NovaEval applies calibrated scoring across more than 15 categories, including voice and audio. For failing calls, NovaPilot can backtest proposed fixes, simulate them end to end, and prepare validated changes as pull requests for human review. Open-source tracing SDKs support Python and TypeScript, with native integrations for LangChain, LangGraph, LiveKit, Pipecat, and CrewAI, plus compatibility with OpenAI, Anthropic, and OpenTelemetry. Deployment choices include managed cloud, VPC, BYO ClickHouse, and on-premise, with Kubernetes and Helm options. The free plan includes 2.5K credits per month; Pro is $69 a month with a 7-day trial. Monthly credits reset without rollover, while purchased add-on credits do not expire. NovaGuard runtime guardrails are marked beta or coming soon.

Who it suits

Noveum suits teams operating production chatbots, voice agents, and multi-agent workflows. Its deployment options and enterprise access controls may also fit organizations with specific infrastructure and governance needs.

Good to know, and what to watch

  • Tracks calls, tools, retrieval, and agent steps.
  • Scores traces across 15+ categories.
  • Backtests candidate fixes and prepares reviewable pull requests.
  • Open-source tracing SDKs support Python and TypeScript.
  • Offers managed, VPC, self-hosted, and on-premise options.
  • Monthly credits reset and do not roll over.
  • NovaGuard runtime guardrails are beta or coming soon.
  • GDPR and SOC 2 Type II are in progress.

Enterprise

—

Free

Free

Boost

$35 one-time

Pro

$69/mo

Free plan · 7-day trial

Getting started

  1. Visit https://noveum.ai/en.
  2. Choose the free plan or a paid plan; Pro, Growth, and Max list a 7-day trial.
  3. Use the API, Linux, web, or self-hosted platform options.
  4. Select a deployment approach: managed cloud, VPC, BYO ClickHouse, or on-premise.
  5. For tracing, use the Python or TypeScript SDK and connect supported integrations.

Limits to check

The free plan includes 2.5K credits per month, 1M spans per month, 2 GB storage, 3 members, and 30-day retention. Pro at $69/mo includes 10K credits per month, 20M spans, 20 GB storage, 10 members, and 90-day retention; monthly credits do not roll over, while purchased add-on credits never expire.

The Club's review

Noveum is an evaluation platform for teams running production chatbots, voice agents, and multi-agent workflows. It is strongest for teams that want to trace agent activity, score it, and validate proposed fixes in one connected workflow. Smaller deployments can start free, but storage, retention, and monthly credits constrain how far that tier stretches.

Overview

Noveum combines observability with a path from failures to reviewed fixes. NovaTrace records LLM calls, tool use, retrieval, and agent steps, including token use, cost, and latency on spans. NovaEval scores traces across 15+ categories with calibrated scorers, including a voice and audio suite. NovaPilot backtests candidate fixes on failing calls, re-simulates them end to end, and submits validated fixes as pull requests for human review.

That combination is useful when teams need more than a record of what happened: they can evaluate behavior and put candidate corrections through a repeatable check. Teams seeking runtime guardrails should look elsewhere for now; NovaGuard is marked beta or coming soon.

Key features

Tracing and integrations

Native tracing integrations cover LangChain, LangGraph, LiveKit, Pipecat, and CrewAI, with compatibility for OpenAI, Anthropic, and OpenTelemetry also listed. Open-source tracing SDKs support Python and TypeScript. This is a practical fit for teams working across agent frameworks and voice stacks, rather than a product confined to a single framework.

Deployment and controls

Deployment choices include managed cloud, VPC, BYO ClickHouse, and on-premise, with Kubernetes and Helm options. That breadth can suit organizations with infrastructure constraints, though deployment choice alone does not establish that every operational or compliance requirement is met. GDPR and SOC 2 Type II are in progress. Enterprise deployments include encryption in transit and at rest and fine-grained access controls; SSO/SAML, RBAC, and audit logging are listed, with pricing specifying SSO/SAML from Scale upward.

Pricing

The free plan costs nothing and includes 2.5K credits/mo, 1M spans/mo, 2 GB storage, 3 members, and 30-day retention. It is a useful way for a small team to start, but the limited credits and short retention make it less suitable for sustained production histories.

Pro is $69 a month, billed $69/mo, with 10K credits/mo, 20M spans/mo, 20 GB storage, 10 members, and 90-day retention. Its 7-day trial gives a small team time to evaluate the paid tier. Growth costs $99 a month, billed $99/mo, and raises those allowances to 25K credits/mo, 50M spans/mo, 50 GB storage, 15 members, and 180-day retention; it also includes priority support. It fits teams whose longer history and higher volume justify the step up.

Max is $199 a month, billed $199/mo, with 50K credits/mo, 100M spans/mo, 100 GB storage, 25 members, and 1-year retention. Scale is $599 a month, billed $599/mo, and offers 200K credits/mo, 500M spans/mo, 500 GB storage, unlimited members, and 2-year retention, with SSO/SAML. These tiers are aimed at larger or higher-volume teams that need materially more capacity; Scale also removes the member cap. Enterprise has custom pricing and unlimited credits, spans, storage, and members, with custom retention and dedicated customer success.

Boost is a $35, paid once add-on for 5,000 credits, Accelerate is $150, paid once for 25,000 credits, and Scale (credit pack) is $500, paid once for 100,000 credits. Add-on credits never expire, unlike monthly plan credits, which reset each billing cycle without rollover. Community support is listed on the pricing page, with priority support for Growth and above. The monthly plans therefore suit predictable recurring workloads; add-on packs suit occasional extra demand, but do not replace span, storage, or retention capacity.

Platforms

Noveum supports API, Linux, self-hosted, and web. Teams can choose managed cloud or self-hosting and infrastructure options including VPC, BYO ClickHouse, and on-premise, with Kubernetes and Helm deployment options.

Who it's for

Noveum is best suited to teams operating production chat, voice, or multi-agent systems that need trace-level diagnosis alongside evaluation and a way to validate fixes before human review. It is less compelling for a team that only needs local CI evaluation or runtime protections immediately, or for a small project whose free-tier limits are already restrictive.

Pros and cons

  • Pros: Tracing, multi-category evaluation, and backtested fix proposals connect diagnosis to remediation rather than stopping at monitoring.
  • Pros: Framework, voice, and telemetry integrations plus Python and TypeScript SDKs broaden its fit across agent stacks.
  • Pros: Managed, VPC, BYO ClickHouse, and on-premise options support different deployment needs.
  • Cons: The free plan caps monthly credits, spans, storage, members, and retention, so production use may require a paid tier.
  • Cons: Monthly credits expire at the billing-cycle reset, and higher retention and team capacity require progressively more expensive plans.
  • Cons: NovaGuard is not a dependable current choice for teams requiring runtime guardrails, and GDPR and SOC 2 Type II remain in progress.

Alternatives

For a free cloud starting point with published AI application evaluation, tracing, scorers, and 1 GB/mo ingestion plus 5 GB/mo storage, consider W&B Weave. Choose Opik if running its open-source observability and evaluation feature set locally is a priority. Google Cloud Agent Evaluation is a usage-priced alternative for teams preferring per-character billing for computation-based metrics and model-based metrics.

Maxim AI is worth considering for its free Developer plan, which includes up to 3 seats, 1 workspace, up to 10k logs per month, and 3-day retention. Choose Future AGI AI Evaluation SDK if Apache 2.0 licensing and self-hosting options are central. DeepEval is an open-source local and CI/CD evaluation framework. Promptfoo offers a free Community plan with 10k red-team probes per month and local or self-hosted use. Arklex is another free option.

Compare more options in AI Agent Evaluation Tools.

Verdict

Choose Noveum if your team needs production tracing, evaluation, and a human-reviewed fix-validation workflow under one roof, particularly across chat and voice agents. Its deployment range adds flexibility, but the right plan depends on the credits, retention, and storage your workload consumes. Look elsewhere if you need mature runtime guardrails now or want an open-source local evaluation tool without a production platform subscription.

The verdict

Noveum combines tracing, evaluation, and a workflow for validating fixes in one platform. Check the credit limits, retention, and deployment terms for the plan that fits your team.

Questions people ask

Is there a free plan?

Yes. Free includes 2.5K credits per month, 1M spans per month, 2 GB storage, 3 members, and 30-day retention.

What does Noveum cost?

The Pro plan is $69/mo, and a free plan is also available. One-time add-on credit packs are listed at $35, $150, and $500.

Which platforms are supported?

Noveum lists API, Linux, self-hosted, and web platforms.

Is the tracing SDK open source?

Noveum says its open-source tracing SDKs support Python and TypeScript.

Which integrations are available?

Native tracing integrations include LangChain, LangGraph, LiveKit, Pipecat, and CrewAI. The site also lists OpenAI, Anthropic, and OpenTelemetry compatibility.

What deployment options are available?

Options include managed cloud, VPC, BYO ClickHouse, and on-premise. Kubernetes and Helm deployment options are also described.

What the maker publishes

Access controls
The homepage lists SSO/SAML, RBAC, and audit logging, while pricing specifies SSO/SAML for Scale and above. source
Deployment
Noveum offers managed cloud, VPC, BYO ClickHouse, and on-premise deployment, with Kubernetes and Helm deployment options also described on its pricing page. source
Evaluation
NovaEval scores traces with calibrated scorers across 15+ categories, including a voice and audio suite. source
Fix validation
NovaPilot backtests candidate fixes on failing calls, re-simulates them end to end, and delivers validated fixes as pull requests for human review. source
Integrations
The tracing SDK has native integrations for LangChain, LangGraph, LiveKit, Pipecat, and CrewAI, and the site also lists OpenAI, Anthropic, and OpenTelemetry compatibility. source
Intended users
Noveum describes its audience as teams operating production chatbots, voice agents, and multi-agent workflows. source
Limits
Monthly plan credits reset each billing cycle and do not roll over, while purchased add-on credits never expire. source
Product status
NovaGuard runtime guardrails are marked beta or coming soon on the maker’s site. source
Purpose
Noveum is an AI agent evaluation platform for production chat, voice, and workflow agents. source
SDKs
Noveum says its open-source tracing SDKs support Python and TypeScript. source
Security
The maker lists GDPR and SOC 2 Type II as in progress, and says enterprise deployments include encryption in transit and at rest and fine-grained access controls. source
Support
The pricing page lists community support, priority support for Growth and above, and dedicated customer success for Enterprise. source
Tracing
NovaTrace captures LLM calls, tool invocations, retrieval, and agent steps, with tokens, cost, and latency on spans. source

Checked against the maker's pages on 29 Sept 2026.