Data

• scikit-learnby scikit-learnPython machine learning library for classification, regression, clustering, and preprocessing.FreeWatch
• LlamaIndexby LlamaIndexOpen-source Python toolkit for building RAG pipelines and LLM agents over your own data.FreeWatch
• Vannaby Vanna AILet users ask questions across databases through an AI SQL agentFreemiumWatch
• LanceDBby LanceDBYC W22AI-native multimodal lakehouse for training data, features, and retrievalFreemiumWatch
• Milvusby ZillizOpen-source vector database for large-scale AI search and retrievalFreemiumWatch
• Bespoke Curatorby Bespoke LabsPython library for bulk synthetic data generation and structured extractionFreeWatch
• Towheeby ZillizOpen-source framework for building embedding pipelines over unstructured dataFreeWatch
• ASReviewby ASReviewOpen-source AI software for systematic text screening and review.FreeWatch
• Elysiaby WeaviateOpen-source agentic platform that routes queries through a decision tree of tools.FreeWatch

That’s all 9 tools.