Waxell

A closer look at Waxell

Waxell is an AI agent governance and observability platform that gives engineering and security teams complete visibility into every AI agent, model call, and agentic workflow, before something goes wrong. It instruments agents with a 2-line setup across 200+ libraries, is OpenTelemetry-native, governs MCP servers, and offers US or EU data residency, with SOC 2 compliance and ISO/IEC 27001:2022 certification. Pricing runs from a free tier with 10,000 observed executions per month up through team and business tiers, with token costs billed by the user's own provider, not by Waxell.

Editorial guidance based on published documentation. The workflow below is a suggested starting point, not a measured product result.

When to choose Waxell

• Engineering and security teams running many AI agents, since Waxell gives one governance plane with visibility into every agent, model call, and agentic workflow.
• Teams that need governed agent deployment, since Waxell offers governance policy categories, MCP gateway governance, and managed runtime on higher tiers.

When to choose something else

• Teams that need more than 10,000 observed executions per month on a free account, since the Free tier caps observation at 10,000 executions per month.
• Teams that need runtime included without an add-on on the middle tier, since runtime is an add-on at $99 per month on the $49 tier.

A practical starting workflow

1. Instrument agents with the 2-line setup across 200+ auto-instrumented libraries, OpenTelemetry-native.
2. Connect provider accounts directly with the team's own LLM keys, so token costs go to the provider, not to Waxell.
3. Observe every agent, model call, and agentic workflow from one governance plane, with MCP gateway governance.
4. Govern with policy categories, coordinate the team, and add managed runtime where needed, scaling seats, executions, and retention by tier.

Check before committing

• Token costs go to the user's own provider, not to Waxell, since users connect provider accounts directly with their own LLM keys, so model spend sits outside Waxell pricing.
• Runtime on the middle tier is an add-on at $99 per month, while it is included on the $499 per month business tier, so runtime costs depend on the tier chosen.
• Data retention differs by tier, from 14 days on Free to 30 days on the $49 tier and 90 days on the $499 tier.

Common questions

Compare approaches for this task

• Watcher — Engineering and security teams running fleets of coding agents, since Watcher monitors agent tokens at scale and gives one set of policies with visibility across the team's agents.; Teams that need risky actions stopped before they run, since Watcher checks agent actions before they run and blocks those crossing a risk threshold, including prompt injection and privilege escalation.
• Claude — Working through source material, developing structured drafts, and iterating on code or documents.