Lunary

What is Lunary?

Lunary is a platform for teams building LLM chatbots and agents, combining observability, prompt management and evaluation in one dashboard. A lightweight SDK, with a one-line monitor call for OpenAI and support for LangChain and other frameworks, records prompts and results, shows traces and error stack traces, and lets you search, filter and label logged data for fine-tuning. Analytics cover model usage, cost, frequent topics and user satisfaction, with custom dashboards, human reviews and alerts for agents that are not behaving as expected. Prompt templates support versioning and A/B testing so non-technical teammates can collaborate, and evaluations compare models and prompts, can run in CI/CD pipelines and need no inference API keys. On security, the vendor states that it holds SOC 2 Type II and ISO 27001 certifications and that you can self-host it. The Team plan costs $20 per user a month with 50,000 events included, and Enterprise pricing is custom.

Use cases

• Log and trace LLM calls
• Debug production agents
• Version and test prompts
• Run LLM evaluations in CI
• Track model cost and usage
• Review chatbot responses by hand
• Mask personal data in logs

Who it's for

• AI engineers
• Product teams
• Enterprise AI teams
• Prompt engineers

Why use Lunary

• Recording prompts, results and traces in one place makes it faster to find why an agent failed in production.
• Cost, usage and satisfaction analytics help teams spot expensive or underperforming LLM features.
• Prompt versioning and a playground let non-technical teammates edit prompts without touching source code.
• Evaluations that run in CI catch regressions before a prompt or model change ships.
• Self-hosting and PII masking keep user data inside your own infrastructure.

Lunary features

• Logging of LLM calls with traces and error stack traces
• Instant search, filters and data labeling
• Analytics on model usage, costs, topics and satisfaction
• Custom dashboards and alerts
• Prompt templates with versioning and A/B testing
• AI Playground covering 20+ models
• Evaluations with CI/CD integration and AI-powered assertors
• Human reviews of LLM responses
• PII masking, RBAC and SSO
• Self-hosting with Kubernetes or Docker

Lunary integrations

• OpenAI
• LangChain

How to get started with Lunary

1. Create a workspace and add the Lunary SDK to your app, for example with the one-line monitor call for an OpenAI client.
2. Run your app so prompts, results, users and traces are recorded in the dashboard.
3. Search and filter logs, label data, and set alerts or custom dashboards for key metrics.
4. Move prompts into templates, test them in the playground and compare models with evaluations.
5. Trigger evaluations from CI/CD or the dashboard, and review responses with your team.

Lunary limitations

• Team plan includes 50k events a month, then $10 per extra 50k events
• Team plan caps seats at 10
• AI Playground includes 300 queries a month, then $0.05 per query
• Payment is required before workspace access on new accounts
• Self-hosting, SSO and PII masking are Enterprise features

Lunary pricing

Lunary has no free plan. Plans start at $20 per month, according to the official pricing page on 24 Oct 2026.

Lunary plans

• Team

  $20 per user /month

  Billed monthly

  • 50,000 events per month included
  • 300 AI Playground queries per month
  • Unlimited projects
  • 1 year history
  • Prompt management and human reviews

• Enterprise

  Custom

  • Self-hosted
  • SSO
  • Granular access control
  • PII masking
  • SLA and white labeling

Plans as listed on the official pricing page on 24 Oct 2026. Prices can change and may vary by country or exclude tax. Check the official pricing page.

Lunary alternatives

The main Lunary alternatives listed on Debuly are Langfuse, Helicone, Arize Phoenix, Braintrust, Weights & Biases and VoltAgent. The table compares pricing and platforms; order is A–Z.

1. 

   Arize Phoenix

   Open-source tool for tracing, evaluating and experimenting on LLM apps and agents, free to self-host or run locally.

   Developer platformsAutomation and agents
   Open sourceVisit Arize Phoenix (official site)
2. 

   Braintrust

   AI observability and evaluation platform for tracing LLM apps and agents, scoring outputs and catching regressions before release.

   Developer platformsCoding
   FreemiumVisit Braintrust (official site)
3. 

   Helicone

   Open-source LLM observability and AI gateway that logs requests, tracks cost and latency, and routes to 100+ models through one API.

   Developer platformsCoding
   FreemiumVisit Helicone (official site)
4. 

   Langfuse

   Open-source LLM observability and evaluation platform for tracing agents, managing prompts and scoring outputs.

   Developer platformsAutomation and agentsCoding
   FreemiumVisit Langfuse (official site)
5. 

   VoltAgent

   Open-source TypeScript framework for building AI agents, paired with the VoltOps console for tracing, evals and deployment.

   Developer platformsAutomation and agentsCoding
   FreemiumVisit VoltAgent (official site)
6. 

   Weights & Biases

   Platform for tracking ML experiments and tracing, evaluating and monitoring LLM apps and agents with W&B Weave.

   Developer platformsCodingAutomation and agents
   FreemiumVisit Weights & Biases (official site)

Lunary FAQ

Sources & verification

Facts on this page come from the official sources below, each with the date we read it. Written by Debuly; the vendor did not review this page.

Image credits

• Logo: from lunary.ai · fetched 24 Oct 2026 · Vendor trademark, used only to identify the product; removed on request
• Cover: none collected yet, so a generated tile is shown.

Spot an error? Report an issue with this listing. We also remove a logo or image on the owner's request.