Bring your AI app
to production.

The platform to monitor, manage and improve your LLM apps.

Integrate now — it's free

free up to 1k events / day

Log & debug LLM agents

Log all your prompts and results, see how agents are performing in production.

Traces & error stack traces
Instant search & filters
Live tail
Label data for fine-tuning

Stay on top of costs

Monitor requests and costs segmented by user and model.

Auto cost & token calculations
Optimize costs
Costs by user, prompts & agents

Debug complex agents

Replay agent executions with traces and find out what went wrong and where.

Trace agent executions
Error stack traces
Filter & instant search

Run Benchmarks

Experiment with prompts and models to find the best performing ones.

Fully no-code
AI-powered assertions & tests
Test open-source models

Replay user chats

Record user conversations and identify gaps in your chatbot's knowledge.

Capture user feedback
React hooks
Dev-friendly frontend integration

Iterate on prompts

Create templates and collaborate on prompts with non-technical teammates.

Clean your source-code
Versioning
A/B testing

1500+ AI developers at leading companies build better LLM apps

Lunary is easy to integrate

Python

import lunary
from openai import OpenAI

client = OpenAI()
lunary.monitor(client)

chat_completion = client.chat.completions.create(
  messages=[{"role": "user", "content": "Hello"}],
)

Secure hosting for your data

Self-host on your servers

Keep the data within your company for maximum security. Learn more →

Inspect our source code

Our source code is completely open source and available on GitHub. Learn more →

Data hosted in the EU

Our Cloud offering's servers are located in Europe to comply with GDPR.

SOC 2 and ISO 27001

Lunary will obtain SOC 2 Type 2 and ISO 27001 certification by June 2024. Learn more →

Join our Open Source community.

Everything we build is 100% open-source. Check out the source-code or our ship logs.

lunary: 841

What our users say

Developers also love these

Live TailNew logs and runs are shown in real time.

Instant SearchSearch across all your data in milliseconds.

Label dataTag your data to easily filter and fine-tune.

Self HostSet up on your own servers for maximum data security.

PromptsStore, version, and collaborate on prompts.

APIExtend your LLM workflow with our complete API.

AlertsSet up alerts to be notified of outlier results and errors.

Frontend SDKTrack chats and feedback directly in your frontend.

PlaygroundTest your prompts on 20+ models.

Get started in minutes.

Run it on your own or get started in minutes with our hosted version.

Get Started (it's free)

Browse the docs

Open Source

Self Hostable

Evaluations

Alerts

Public API

Exports

Prompt Templates

Chat Replays

Agent Tracing

Metrics

Feedback Tracking

LangChain Support