Sold by: Lunary AI
Observability, prompt management and evaluation for LLM applications.
Overview
Lunary is an open-source platform that assists AI developers in monitoring, improving, and securing their LLM applications. Key features include:
- Observability: Track metrics like cost, token usage, and latency. Log and debug with detailed traces.
- Prompt Management: Collaborate on, template, and version prompts. Perform A/B testing.
- Guardrails: Ensure your AI answers do not contain toxic content, respond to prompt injections, or leak PII data.
- Evaluation Suite: Test prompts and models to ensure optimal performance and integrate evaluations into your CI pipeline.
- Chat Tracking: Record user interactions and collect feedback to refine AI responses.
- Security and Compliance: Deploy on your own servers or use GDPR-compliant cloud hosting. Ensure data security with PII removal and anomaly detection.
- Integration and Tools: Support for popular AI libraries, APIs, and SDKs for easy integration such as LangChain, OpenAI or Anthropic.
For more information, visit Lunary.ai.
Highlights
- Observability: Track metrics like cost, token usage, and latency. Log and debug your LLM calls and agents with detailed traces.
- Prompt Management: Collaborate on and version prompts. Perform A/B testing and improve your LLM prompts.
- Evaluation Suite: Test prompts and models to ensure optimal performance and integrate evaluations into your CI pipeline. Protect users from toxic content with Guardrails.
Details
New
Introducing multi-product solutions
You can now purchase comprehensive solutions tailored to use cases and industries.
Features and programs
Financing for AWS Marketplace purchases
AWS Marketplace now accepts line of credit payments through the PNC Vendor Finance program. This program is available to select AWS customers in the US, excluding NV, NC, ND, TN, & VT.
Pricing
Pricing is based on the duration and terms of your contract with the vendor. This entitles you to a specified quantity of use for the contract duration. If you choose not to renew or replace your contract before it ends, access to these entitlements will expire.
Additional AWS infrastructure costs may apply. Use the AWS Pricing Calculator to estimate your infrastructure costs.
Dimension | Description | Cost/12 months |
|---|---|---|
Seats | Number of seats | $1,000.00 |
Vendor refund policy
Refunds can be requested within 30 days of purchase under specific conditions via our customer portal or support email (hello@lunary.ai ). A refund is available if unresolved technical issues persist that our support team cannot fix within 30 days. The software must be uninstalled, and all licenses deactivated. Our support team will attempt to resolve issues within 30 days; if unresolved, refunds are processed within 10 business days. No refunds for incorrect installation or custom solutions.
Legal
Vendor terms and conditions
Upon subscribing to this product, you must acknowledge and agree to the terms and conditions outlined in the vendor's End User License Agreement (EULA) .
Content disclaimer
Vendors are responsible for their product descriptions and other product content. AWS does not warrant that vendors' product descriptions or other product content are accurate, complete, reliable, current, or error-free.
Delivery details
Software as a Service (SaaS)
SaaS delivers cloud-based software applications directly to customers over the internet. You can access these applications through a subscription model. You will pay recurring monthly usage fees through your AWS bill, while AWS handles deployment and infrastructure management, ensuring scalability, reliability, and seamless integration with other AWS services.
Support
Vendor support
Personalized support with dedicated technical account manager.
Email: support@lunary.ai
Phone: +1 (415) 425 8539
Website:
AWS infrastructure support
AWS Support is a one-on-one, fast-response support channel that is staffed 24x7x365 with experienced and technical support engineers. The service helps customers of all sizes and technical abilities to successfully utilize the products and features provided by Amazon Web Services.
Updated weekly
By Lunary AI
By Portkey AI
By NeuralSeek
Sentiment is AI generated from actual customer reviews on AWS and G2
Functionality
Ease of use
Customer service
Cost effectiveness
Positive reviews
Mixed reviews
Negative reviews
AI generated from product descriptions
Observability and Monitoring
Track metrics including cost, token usage, and latency with detailed traces for logging and debugging LLM calls and agents.
Prompt Management and Versioning
Collaborate on prompts with versioning capabilities and perform A/B testing to improve LLM prompt performance.
Evaluation and Testing Integration
Test prompts and models for optimal performance with evaluation suite integration into CI pipeline.
Content Safety and Guardrails
Implement guardrails to prevent toxic content, detect prompt injections, and prevent PII data leakage in AI responses.
Security and Compliance Features
Support for on-premises deployment and GDPR-compliant cloud hosting with PII removal and anomaly detection capabilities.
AI Gateway and Request Routing
AI Gateway with load balancing capabilities between multiple language models and fallback mechanisms for production reliability
Observability and Monitoring
Full visibility and observability over AI applications with comprehensive logging and monitoring through a centralized dashboard
Prompt Management
Centralized prompt management system for versioning, organization, and control of prompts across AI applications
Security and Compliance
Enterprise-grade security with ISO, SOC2, HIPAA, and GDPR compliance certifications and security policy enforcement
Guardrails and A/B Testing
Built-in guardrails for output validation and A/B testing capabilities for comparing model performance and behavior
Multi-Agent Orchestration
Build and manage multiple agentic generative AI solutions from a single platform with ability to assign Large Language Models to agents and switch between LLMs for optimization and cost savings
Retrieval Augmented Generation with Governance
Point and click governance and guardrails for Retrieval Augmented Generation outputs with Provenance, Coverage and Confidence Scores, and Semantic Analytics visibility
Hallucination and PII Mitigation
Enterprise observability and control mechanisms to mitigate risks of Large Language Model hallucination, misinformation, and Personal Identifiable Information loss
Dynamic Prompt Generation
Fully customized Retrieval Augmented Generation prompt generation capability to create and run dynamic generative AI prompts against proprietary data without code
LLM Performance Monitoring
Real-time monitoring of Large Language Model token usage, operational costs, and cost comparison capabilities across multiple Large Language Models
Standard contract
Customer reviews
No customer reviews yet
Be the first to review this product . We've partnered with PeerSpot to gather customer feedback. You can share your experience by writing or recording a review, or scheduling a call with a PeerSpot analyst.