US$0/month
- 10,000 requests/month
- 25 Clyvel AI credits/month
- 7 days of retention
- Traces, tokens, latency and costs
- No automatic overages
Your AI agents, under control.Clear insights. Better decisions.
Connect existing agents. Understand performance and costs, discover savings opportunities and make better decisions with Clyvel AI.
Connect what you already use.
OpenAI
Anthropic
Gemini
LangChain
n8n
Start with one application. Grow with your team.
Top up Clyvel AI when you need more credits
250 credits · US$ 9500 credits · US$ 161,000 credits · US$ 29
One-time payment. No expiration. Available after Paddle setup.
Everything you need to run your AI agents.
Bring every agent into view.
Connect existing agents through SDK, frameworks, OpenTelemetry or Gateway—on your terms.
Every request, explained.
See requests, traces, performance and tokens. Explore trends, evaluations and reports.
Turn AI spend into clarity.
Understand costs by agent, provider and model, with token insights and budgets in one place.
Stay ahead of every signal.
Follow latency, reliability, incidents and Watchtower alerts as your agents run.
Meet Clyvel AI. Your operation, explained.
Ask about costs, agents and performance. Get insights, priorities and opportunities to optimize.
Operate with confidence.
Bring roles, policies, approvals and audit history together for confident decisions.
GET STARTED
Connect your agents. See the bigger picture.
Four ways to connect your existing tools and turn every received request or trace into useful insights.
01
Choose how to connect
Connect through SDK, a framework, OpenTelemetry or AI Gateway, depending on your application.
02
Set up your chosen connection
Instrument your agent, connect its exporter or use Gateway to centralize model requests.
03
See your agents in action
Explore usage, costs, performance and traces to find actionable optimization insights.
Common questions.
Read the documentation →How do I connect my AI agents?
Choose the path that fits your stack: Python/JavaScript instrumentation, frameworks and automation, OpenTelemetry OTLP/HTTP or AI Gateway. Your agent stays in your infrastructure. Gateway is the option for routing model calls through Clyvel.
What can I see in Clyvel?
Bring requests, traces, tokens, models, P95 latency, incidents, estimated provider spend and budgets into one operational view. Explore analytics, evaluations, Watchtower alerts, reports and exports.
How does Clyvel AI help my team?
Ask questions about costs, performance, agents and incidents. Clyvel AI combines your workspace data to explain changes, highlight priorities and propose ways to improve. Supported actions can be reviewed and approved by your team when enabled.
How can I find savings opportunities?
Analyze costs by agent, model and provider, identify workloads worth optimizing and review potential model or routing savings. Clyvel helps you evaluate recommendations with operational evidence before applying them.
What's included in a Clyvel plan?
Plans provide monitoring and management capacity, monthly request allowances and Clyvel AI credits according to the selected tier. Model-provider usage remains billed by your provider. Connection behavior and service limits depend on the integration and plan.
Can I manage my agents with my team?
Use shared operational views, budgets, roles, policies, approvals and audit history to coordinate decisions. Clyvel helps your team understand activity and keep sensitive actions under human control.
A clearer view of your AI starts today.
Connect your agents and discover what Clyvel can show you.