Open-source search infrastructure for AI, with vector, full-text, regex, and metadata search.
Chroma is open-source search infrastructure for AI. Its site describes fast, serverless, scalable infrastructure for vector, full-text, regex, and metadata search, built on object storage and released under the Apache 2.0 license. Listed capabilities include sparse vector search (BM25 and SPLADE), semantic vector search, trigram and regex full-text search, metadata filtering, collection forking, and a command-line interface, with Python, TypeScript, and Rust clients.
The homepage also describes enterprise options such as bring-your-own-cloud in your VPC. On October 23, 2026, Chroma announced that it has signed a definitive agreement to join Replit. ChromaDB and Foundation, its enterprise context product, will continue there.
The hosted Chroma Cloud service is winding down over the next 60 days, and open-source Chroma stays under Apache 2.0.
Pricing: Open-source Chroma is Apache 2.0. The pricing page lists usage-based Chroma Cloud plans: Starter at $0 per month plus usage, with $5 in free credits; Team at $250 per month plus usage, with $100 in credits; and Enterprise at a custom price. The October 23, 2026 announcement says the hosted Chroma Cloud service is winding down over the next 60 days.
Pricing model: Freemium
Common questions about Chroma
Chroma has signed a definitive agreement to join Replit. ChromaDB and Foundation, its enterprise context product, will continue there as the companies work on a context layer for agents.
Chroma Cloud is winding down over the next 60 days from the October 23 announcement. Open-source Chroma stays under Apache 2.0.
Chroma makes ChromaDB, the open-source vector database it says gets about 6 million downloads a month, and Foundation, its newer product for self-improving enterprise context.…
Other products to explore and follow.
The people behind Chroma
CEO
AI coding platform that turns text prompts into full-stack websites and apps — with built-in databases, auth, hosting, and analytics.
Free Apache-2.0 CLI from Vercel Labs. Coding agents read and operate desktop apps through the OS accessibility tree.
Turn a codebase into a knowledge graph your AI assistant can trace — answers come back as graph paths with real file:line citations.
The open home of machine learning: 3 million models, 500,000 datasets and 1 million apps, with hosted inference, Spaces and the Transformers libraries.
Open-source framework for rendering HTML compositions into MP4 videos, built for AI agents and automated pipelines.
Multimodal vector database for RAG, AI agents, and hybrid search with native versioning and S3-compatible storage.
