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.
These scores are auto-generated from public information (the agent's own listing, docs, and repository) using the canonical OWASP AIVSS formula and the MAESTRO framework — an estimate for guidance, not a penetration test, audit, or certification. See the scoring methodology. Are you the vendor? Factual corrections are free.
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.