{
  "slug": "chroma",
  "name": "Chroma",
  "url": "https://www.trychroma.com",
  "cat": "search",
  "group": "back",
  "tagline": "Embedded vector DB + cloud",
  "price": "OSS free (Apache 2.0). Chroma Cloud Starter: $0/mo base with $5 free credits, then usage. Team $250/mo + usage with $100 credits. Rates: $2.50 per GiB written, $0.33 per GiB-month stored, $0.0075 per TiB queried, $0.09 per GiB returned.",
  "tier": "mixed",
  "pick": false,
  "what": "The vector store that runs in-process. <code>pip install chromadb</code> gives a persistent local database with no server to run, and the same client points at Chroma Cloud when you deploy. Cloud adds serverless vector, hybrid and full-text search on a Rust core.",
  "why": "Fastest possible RAG prototype: three lines to a collection, and it embeds your documents with a sensible default model. You get working retrieval before choosing an embedding provider.",
  "warn": "Embedded mode is single-process and not safe under a concurrent web server — run <code>chroma run</code> as a server for that. Collections sometimes need migration across major versions.",
  "install": "pip install chromadb",
  "category": {
    "key": "search",
    "name": "Search, vector & RAG",
    "desc": "Keyword search, vector stores, and web-search APIs for agents — three different things.",
    "group": "back",
    "groupName": "Give it a backend"
  },
  "freshness": null,
  "health": {
    "ok": true,
    "status_code": 200,
    "final_url": "https://www.trychroma.com/",
    "checked_at": "2026-08-18T17:12:38.21+00:00"
  },
  "corrected_at": null,
  "upstream_changed_at": null
}