Unified TypeScript library for streaming, structured outputs, and agent loops across AI providers
Full evaluationGlossary · Updated Sep 2, 2026
Vector database
A datastore optimised for storing embeddings and finding the nearest ones to a query quickly.
Definition
Vector databases index embeddings so similarity search over millions of items stays fast, often combining approximate nearest-neighbour algorithms with metadata filtering. They are used in RAG pipelines, recommendation systems, and semantic search, and they range from dedicated services to extensions of existing databases.
Why it matters when choosing a tool
If you build an agent or knowledge assistant, the vector store determines retrieval speed, cost, and how well filters and permissions can be enforced.
Where you will meet it
AI Agent & Chatbot Builders, AI Coding & Development
Related terms
Embedding · Retrieval-augmented generation (RAG) · Self-hosting
Tools where this matters
Reviewed products in the related categories
Prototyping environment and developer API platform for Google's Gemini models
Full evaluation
A source-available workflow automation platform with native AI agent nodes, self-hostable or cloud.
Full evaluation
A thoughtful AI collaborator for writing, analysis, coding, and long-form work.
Full evaluation
An AI-native code editor for repository-aware agents, edits, review, and automation.
Full evaluation
Anthropic's agentic coding tool that works in the terminal, IDE, desktop app, and browser to plan and execute multi-step changes.
Full evaluation