Lunary
by Lunary
Observability platform to understand, test and improve AI applications, with agent tracing, analytics and prompt templates.
About
Observability platform to understand, test and improve AI applications, with agent tracing, analytics and prompt templates.
Lunary is an observability platform for LLM apps that helps teams understand, test and improve their AI products. It captures logs and events, replays chats, traces agents and classifies topics so teams can see how users actually interact with the application.
Features include prompt templates, an AI playground, human reviews, feedback tracking, custom dashboards and CSV and JSONL exports. The Community Edition can be self-hosted for free, and the Enterprise edition adds SSO and SAML, PII masking, SOC2 and ISO27001 reports and an SLA.
Key features
Product details
Vendor
Lunary
Category
AI Agent Observability & Evals
Pricing model
subscription
Starting price
Team $20/user/mo; Enterprise custom
Free trial
No
Deployment
Self-hosted Community Edition (free); Enterprise self-hosting via Docker, Kubernetes or on-premises
Pricing
Pricing model: subscription
Plans
- Team: $20 per user per month; Enterprise: custom pricing; self-hosted Community Edition free
Similar software
AgentOps
by AgentOps
Agent monitoring, replay and evaluation platform.
Arize AX
by Arize AI
Arize AX is an AI engineering platform for agent observability, evaluation, tracing and experimentation.
Arize Phoenix
by Arize AI
Open-source AI observability and evaluation platform.
Braintrust
by Braintrust
Evaluation and observability platform for AI products.
Comet Opik
by Comet
Open-source evaluation, testing and monitoring platform for LLM applications.
Confident AI
by Confident AI
LLM evaluation, testing, tracing and monitoring platform with regression testing, online evals and real-time alerting.