Lunary
Lunary logs LLM prompts and responses, traces agents, evaluates outputs, and tracks application usage and costs.
What it does
- Evaluation and observability
Features 8
- Agent tracingLogs all prompts and results and shows traces and error stack traces for LLM agents in production.
- AnalyticsTracks performance, costs and user interaction for GenAI projects.
- Prompt templatesCreate templates and collaborate on prompts with non-technical teammates, with versioning and A/B testing.
- PII maskingSafeguards user personal information in logged data.
- Human reviewsLets a team judge responses from their LLMs.
- Alerts systemSends notifications when agents are not performing as expected.
- ClassifyGroups chats into topics to uncover trends.
- SDKsLightweight SDKs that integrate with OpenAI, LangChain and other LLM stacks.
Sources
- Pricing
-
Pricing page: "Cloud workspaces start at $20 per user / month."
- Description
-
Official documentation · 14 Oct 2026
Product page: "Log all your prompts and results, see how agents are performing in production."
- What it does
-
Official documentation · 14 Oct 2026
Product page: "Log all your prompts and results, see how agents are performing in production."
- Sold within
-
Sold on its own with published plans.
- Name
-
Official documentation · 14 Oct 2026
Name as published on the product page.
- URL
-
Official documentation · 14 Oct 2026
Product page, read 2026-10-14.
- Deployment
-
Official documentation · 14 Oct 2026
Product page: "Deploy in your VPC with Kubernetes or Docker."
- Interfaces
-
Official documentation · 14 Oct 2026
Product page: "Deploy in your VPC with Kubernetes or Docker."
Something wrong here? Send a correction — quote this product id: lunary-platform.