Built by an AI agent, for AI agents

Plausible for AI Agents

Simple, affordable observability for your AI agents. Drop in the SDK. See your traces. Get alerts when agents fail. No self-hosting, no enterprise contracts.

Free forever up to 1,000 traces/month

🔍

See every trace

Full waterfall view of your agent's steps — LLM calls, tool uses, sub-agent invocations. Know exactly what happened and when.

🚨

Alerts when agents fail

Email alerts the moment a trace errors or times out. With rate limiting to prevent alert fatigue. Know before your users do.

One SDK, 10 lines

Open-source TypeScript SDK. Drop it into any agent — Claude, GPT-4, LangChain, custom. Start seeing traces in under 5 minutes.

Simple pricing

No enterprise tiers. No seats. No surprises.

Free
$0 / month
  • 1 agent
  • 1,000 traces / month
  • 30-day retention
  • Trace viewer
  • Community support
Get started
Most popular
Pro
$9 / month
  • Unlimited agents
  • 50,000 traces / month
  • 90-day retention
  • Email alerts on failure
  • Team access (up to 5)
  • Priority support
Start free, upgrade anytime

Feature comparison

Feature Free Pro
Trace viewer
Span waterfall
Dashboard & metrics
Data retention 30 days 90 days
Agents 1 Unlimited
Monthly traces 1,000 50,000
Email alerts on failure
Team access Up to 5
Support Community Priority
🤖

Built by an AI agent, for AI agents

Nexus was designed and built by Ralph, an autonomous AI agent employed by Keylight Digital LLC. Ralph needed a way to monitor his own agent runs — so he built the tool he wished existed.

Every feature in Nexus was motivated by a real problem Ralph encountered managing AI workflows: knowing when a trace failed, understanding why an agent stalled, tracking performance over time. If you're building with AI agents, you have the same problems. Nexus is for you.

Ready to see inside your agents?

Start free. No credit card. Under 5 minutes to first trace.