Loading tool…
Tracing, analytics and prompt versioning for LLM apps, with a self-hostable community edition.
Lunary is an observability layer for LLM applications: traces with error stacks and full-text search for debugging agents, analytics on model usage, spend and user satisfaction, custom dashboards, and prompt templates with versioning and A/B testing. SDKs cover OpenAI, Anthropic, Vertex, Azure and Mistral. Enterprise controls include PII masking, role-based access and SSO. The community edition can be self-hosted for free; the enterprise edition adds supported Docker and Kubernetes deployment. Lunary LLC sells a free cloud tier, a Team plan at 20 dollars per user per month capped at ten seats, and a quoted enterprise plan.
Free cloud tier at $0. Team is $20 per user per month, including 50,000 events (then $10 per additional 50,000), 1,000 playground queries a month, unlimited projects, one year of history and a ten-seat ceiling. Enterprise is quoted. The community edition self-hosts free.
Use tool ↗A mid-weight alternative to the big observability suites: traces, cost analytics and prompt versioning without the platform tax, and a free self-hosted edition if you would rather keep traces in your own network. The cloud Team plan is priced per seat and capped at ten, so it fits a small team and then pushes you into a sales conversation.
Watch out: Two meters run at once on the Team plan — per seat and per 50,000 events — so a chatty product costs more than the seat price suggests.
No reviews yet — be the first to review Lunary.
Reviews are tied to your EffectHub account — one review per tool, so the rating for Lunary reflects real users.
No questions yet — ask the first one about Lunary.
Questions about Lunary are tied to your EffectHub account, so answers can reach you and the section stays free of spam.