IndexingStatus

Chroma Cloud can now automatically crawl and index websites. Users supply a starting URL and Chroma handles scraping, converting pages to markdown, chunking via Tree-sitter, and generating embeddings — no custom ingestion pipeline required. The resulting collections support hybrid search blending dense embeddings for semantic matching with BM25 sparse vectors for keyword precision. Designed for product docs, blogs, and support pages.

Nov 4, 2025

Chroma Cloud now supports collection forking, which duplicates any collection nearly instantly (100–200ms regardless of size) using a copy-on-write approach. Forks share underlying data with the parent collection, so storage costs only accumulate for new changes. Enables maintaining separate search indexes across logical versions such as different code snapshots, and is already powering production coding agents.

Aug 8, 2025

Chroma Sync is a new Chroma Cloud feature that automatically handles chunking, embedding, and indexing of external data sources. The initial launch supports GitHub, using collection forking to process only diffs between commits rather than entire repositories. Enables version-aware retrieval at specific commits or branches, designed to support background agents and automated CI/CD workflows. More data sources to follow.

Oct 22, 2025

Factory AI uses Chroma Cloud to power semantic and full-text code search for its AI software development agents (Droids). Chroma enables semantic similarity search, regex/full-text search, and collection forking to incrementally index git diffs without full re-ingestion. Serverless scalability handles unpredictable parallel workloads across many concurrent Droid instances. Factory's Droids hold the #1 score on Terminal-Bench, resolving 58.8% of tasks.

Oct 7, 2025