| Description |
| Summary |
Open-source evaluation and testing framework for LLM applications, especially RAG systems, with metrics, synthetic test data and evaluation workflows.
|
|
|
|
| Description |
Ragas provides metrics, synthetic test data generation and workflows for systematically evaluating LLM applications and RAG pipelines for faithfulness, context quality and answer relevance.
|
|
|
|
| Positioning |
Open-source evaluation framework for RAG and LLM applications
|
|
|
|
| Key facts |
| HQ location |
San Francisco, CA, USA
|
|
|
|
| Founded |
2023
|
|
|
|
| Company type |
Private
|
|
|
|
| Pricing model |
licensing open source
|
|
|
|
| Last updated |
Jun 21, 2026
|
|
|
|
| Financials |
| Revenue estimate |
Unknown
|
|
|
|
| Valuation estimate |
Unknown
|
|
|
|
| Investments |
~$500K funding reported by third-party startup databases; source confidence low
|
|
|
|
| Relationships |
| Target customers |
Developers and AI teams building RAG and LLM applications
|
|
|
|
| Key competitors |
TruLens, LangSmith, DeepEval, PromptLayer, Braintrust
|
|
|
|
| Known customers |
Open-source community; LangSmith integration/reference
|
|
|
|
| Segments & Industries |
| Segments |
AI Workflows, AI Developer Tools, Knowledge & RAG, Document AI, AI Quality & Observability, AI Governance & Risk, Chatbots, Analytics & BI
|
|
|
|
