Chroma
An open‑source vector database and embeddings engine for building retrieval‑augmented AI applications.
🛡️ AgentReady threat assessment
MAESTRO 7-layer threat model + OWASP AIVSS risk score for Chroma, derived from its capabilities.
AIVSS 7.6 · High
View MAESTRO 7-layer threat model →Overview
Chroma is an open-source, AI-native vector database built for storing and querying embeddings alongside metadata. It supports full‑text and multimodal search, scalable retrieval, and powers retrieval‑augmented generation workflows. Available as both a local SDK and a private‑preview managed cloud, Chroma offers strong developer ergonomics and extensible integrations for building production‑grade LLM applications.
Key features
- vector database
- embeddings
- retrieval augmented generation
- open-source
- multimodal search
- Python SDK
- JavaScript SDK
Use cases
- Building retrieval‑augmented LLM applications with custom memory.
- Storing and querying vector embeddings with metadata filtering.
- Rapid prototyping with Python/JavaScript SDKs and local deployment.
- Scaling from a local database to a managed cloud solution.