Lunary
lunary.ai
- Free plan
- Open source
- Web
- API
- Self-hosted
What Lunary is
Lunary is an AI platform for enterprise teams and developers building chatbots or other applications powered by large language models. It monitors and debugs LLM calls and agents with traces, error views, search, and filters. Analytics cover model usage and costs, frequent topics, user satisfaction, and custom dashboards. Teams can create prompt templates together, manage versions, and run A/B tests. Human reviews and scoring are available for LLM responses. Lunary works through the web and API, and it can be self-hosted. Listed integrations include Anthropic, LangChain, OpenRouter, IBM WatsonX, Gemini, AWS Bedrock, and OpenAI. The Team plan costs $20 a month, billed monthly, with 10 seats, 50,000 events monthly, 300 AI Playground queries monthly, and one year of history. Free workspaces remain available. Lunary says cloud data is encrypted in transit and at rest, and reports SOC 2 Type 2 certification and ISO 27001:2022 compliance. Self-hosting gives customers control of their data; Lunary Cloud is not suitable for HIPAA-compliant data collection.
Who it suits
Lunary suits enterprise teams and developers operating LLM applications who need tracing, cost analytics, prompt management, evaluations, and agent monitoring. It also fits teams that need web, API, or self-hosted deployment.
Good to know, and what to watch
- Tracks LLM usage and costs
- Supports prompt versioning and A/B testing
- Offers human response reviews
- Self-hosting provides data control
- SOC 2 Type 2 and ISO 27001:2022
- Team usage overages are billed separately
- No free trial
- Cloud is unsuitable for HIPAA-compliant data collection
- Some integrations are marked coming soon
Plans
Every plan and priceEnterprise
Team
The verdict
Lunary brings observability, analytics, prompt workflows, and evaluations to LLM applications. Its Team plan has defined event and query allowances, while self-hosting and enterprise controls address organizations with specific data or access needs.
What the maker publishes
- Access controls
- Enterprise access features include RBAC and SSO. source
- Analytics
- Its analytics track model usage and costs, frequent topics, user satisfaction, and custom dashboards. source
- Analytics
- Analytics cover model usage, token and cost information, frequent topics, satisfaction and custom dashboards. source
- Automation integrations
- Email/SMTP, Slack and Zapier are listed for usage emails, alerts or workflow automation, with some marked enterprise or coming soon. source
- Chat tracking
- Lunary tracks chatbot conversations, user sessions and feedback. source
- Classification
- Topic classification groups chats to reveal conversation trends. source
- Coming soon integrations
- The integrations page marks Flowise, Ragas, Slack, Redshift, PostHog, OpenLLMetry, LlamaIndex, and Langflow as coming soon. source
- Company founding
- LinkedIn lists Lunary as founded in 2021. source
- Company headquarters
- LinkedIn lists Lunary's headquarters in San Francisco, California, at 166 Geary Street, 15th Floor. source
- Company name
- The official site footer identifies the company as Lunary LLC. source
- Company size
- LinkedIn lists Lunary's company size as 11–50 employees. source
- Company type
- LinkedIn identifies Lunary as privately held and classifies it under Software Development. source
- Compliance
- Lunary says it is SOC 2 Type 2 certified and ISO 27001:2022 compliant, and that audit reports are available to Scale and Enterprise customers upon request. source
- Deployment
- Enterprise customers can deploy Lunary in their own VPC using Kubernetes or Docker. source
- Destinations
- Enterprise destinations include MySQL, Tableau, PowerBI, Airbyte, Segment, SQL Server, Databricks, Snowflake, BigQuery and Amplitude. source
- Documentation depth
- The documentation index contains installation guides, provider integrations, feature guides, security material, self-hosting instructions and a large API reference. source
- Evaluation checks
- Lunary advertises AI-powered assertors and evaluations that do not require customers to provide inference API keys. source
- Evaluations
- The evaluation product compares models, settings and prompts against datasets and can run from a dashboard or CI pipeline. source
- Free workspaces
- The pricing page says existing plans, including Free workspaces, stay the same. source
- Headquarters
- San Francisco, California, United States source
- Human reviews
- Teams can manually judge LLM responses through human-review workflows. source
- Independent description
- TakeAI describes Lunary as the successor to LLMonitor and identifies observability, prompt management, chatbot analytics, feedback and debugging as its focus. source
- Integrations
- The integrations page lists sources including Anthropic, LangChain, OpenRouter, IBM WatsonX, Gemini, AWS Bedrock, and OpenAI, plus destinations and automation tools. source
- Integrations
- The integrations directory lists Anthropic, Flowise, LangChain, OpenRouter, IBM WatsonX, Mistral, Grok, Fireworks AI, Ragas, Gemini, AWS Bedrock, OpenAI, Azure OpenAI, LiteLLM and other sources. source
Checked against the maker's pages on 15 Oct 2026.