Lunary
Open-source platform for building and testing LLM chatbots and agents
- Status
- Not yet determined
- Last checked
- Checked · Oct 12, 2026
- License
- Open source
- Pricing
- Free tier · from $0
What it is
Lunary is an open-source platform designed to help developers manage, test, and deploy large language model (LLM) chatbots and agents. It provides tools for observability, prompt management, and comprehensive testing.
Lunary stands out by offering an open-source solution for the full lifecycle of LLM chatbots and agents, from prompt management to testing and monitoring, all while allowing developers to maintain control over their infrastructure.
When it fits — and when it doesn’t
A good fit for
Teams building complex, data-intensive chatbot applications that require extensive testing and monitoring
Developers who need a self-hosted solution to manage their own infrastructure and data privacy requirements
Projects focused on prompt engineering for LLMs where systematic management and testing of prompts are critical
Look elsewhere if
Teams requiring real-time analytics or immediate feedback from chatbot interactions, as Lunary focuses more on post-deployment observability
Small projects with limited resources that prefer a fully managed service over self-hosting
Known weaknesses
Each one links to the public issue, changelog or docs page it came from, where we have one.
- 01
New cloud workspaces require a paid subscription, eliminating free access for new users.
The platform mandates payment before workspace access for new users, which creates a barrier to entry for individuals or small teams testing the tool.
Source: lunary.ai/pricing ↗ - 02
Exceeding the event limit for two consecutive days results in account limitation.
Users who consistently exceed their included event allowance face restricted access to their account, requiring an upgrade or usage reduction to regain full functionality.
Source: lunary.ai/pricing ↗ - 03
Data hosting is restricted to Europe for cloud users, limiting regional flexibility.
The cloud service hosts data exclusively in Europe, which may not comply with data residency requirements for teams operating in other regions without opting for on-premises hosting.
Source: lunary.ai/pricing ↗ - 04
The OpenAI integration requires manual configuration for template tracking.
Unlike automatic detection in other contexts, users must manually pass the template_id when tracking runs with the OpenAI integration to see data in the template column.
Source: lunary.ai/faq ↗
What it does well
Observability tools for monitoring chatbot performance
Prompt management system to streamline the creation and testing of prompts
Comprehensive testing framework for LLM agents
Self-hosted deployment options for flexibility
Pricing
- Free tier
- YesOpen source — free to use
- Paid from
- $0
- Model
- Flat rate
- Enterprise plan
- No
Pricing not independently confirmed — check the vendor’s page.
Performance benchmarks
How Fast Is It?
Set up Lunary
Setup steps, common gotchas and what to check after 30 days.
Get the badge
A small badge for Lunary’s README or site: its name, “Tracked on AI Navigator”, and the availability status and check month from this page. It updates as the catalog does.
Markdown
[](https://navigateaitools.com/explorer/tool/lunary)HTML
<a href="https://navigateaitools.com/explorer/tool/lunary"><img src="https://navigateaitools.com/badge/lunary.svg" alt="Lunary — tracked on AI Navigator" height="58"></a>