# www.trychroma.com

> AI-optimized mirror of www.trychroma.com containing 50 pages totalling 23,675 words of clean markdown content, structured data, and semantic HTML. Original source: https://www.trychroma.com/. Last updated: 2026-06-09T04:57:14.951Z.

Each page is available as HTML (with JSON-LD structured data) and Markdown (text-only, ideal for LLMs and RAG).

## Homepage

- [site-root.html](/content/site-root.html) (1 words)

## Articles & Blog Posts

- [Agentic search at the Pareto frontier](/content/products/agent/index.html): Context-1, an open-weights model from Chroma, is trained with SFT and RL, and is competitive with frontier models at search, while being 10x faster and 25x cheaper. (291 words)
- [home/index.html](/content/home/index.html) (1 words)
- [research/generative-benchmarking/index.html](/content/research/generative-benchmarking/index.html) (1 words)
- [research/context-rot/index.html](/content/research/context-rot/index.html) (1 words)
- [blog/voice/index.html](/content/blog/voice/index.html) (1 words)
- [interviews/alex-on-minion/index.html](/content/interviews/alex-on-minion/index.html) (1 words)
- [interviews/flo-on-lindy/index.html](/content/interviews/flo-on-lindy/index.html) (1 words)
- [privacy/index.html](/content/privacy/index.html) (1 words)
- [Distributed Chroma: Bring Your Own Cloud](/content/engineering/distributed-chroma-byoc/index.html): Chroma BYOC lets customers run Chroma inside their own cloud to meet strict security and compliance requirements, while still relying on Chroma’s team to operate and support the database in production. (1,813 words)
- [interviews/bryan-on-zapier/index.html](/content/interviews/bryan-on-zapier/index.html) (1 words)
- [Chroma Cloud Security](/content/security/index.html) (773 words)
- [Chroma raises $18M seed round](/content/company/seed/index.html) (760 words)
- [Retrieval powered by object storage](/content/engineering/serverless/index.html): The design of Chroma's distributed and serverless architecture (926 words)
- [List of Subprocessors](/content/subprocessors/index.html) (191 words)
- [Loved by Developers, Trusted by Enterprises](/content/enterprise/index.html): Open-source search infrastructure for AI (393 words)
- [Announcing our Hacker in Residence Program](/content/blog/hir-2023/index.html): Get paid to make open source AI apps with us (435 words)
- [Chroma Server in Production](/content/project/server-in-prod/index.html): Deploying and running Chroma server in production. (392 words)
- [Chroma v0.4](/content/blog/chroma_0-4-0.html) (1,123 words)
- [ChromaDB](/content/products/chromadb/index.html): The open-source search infrastructure for AI. Fast, serverless, and scalable — supporting vector, full-text, regex, and metadata search. (550 words)
- [Multi-label tagging and categorization](/content/changelog/metadata-arrays/index.html): Chroma now supports storing arrays of strings, numbers, and booleans in metadata fields, one of our [most requested features](https://github.com/chroma-core/chr... (255 words)
- [Chroma raises $18M seed round](/content/blog/seed/index.html) (750 words)
- [The Embedding Revolution](/content/blog/podcast-cogrev/index.html): Anton appears on the CogRev podcast (255 words)
- [Key Responsibilities](/content/careers/account-executive/index.html): Build revenue from the ground up as our first dedicated seller, working directly with the founders. (456 words)
- [Distributed indexing](/content/changelog/introducing-chroma-cloud/index.html): Chroma Cloud is a hosted, production-grade deployment of Chroma built from everything we learned shipping the single-node engine, re-architected into a distribu... (561 words)
- [Research](/content/research/index.html): Basic and applied research for search, retrieval, agents, and context engineering. (206 words)
- [Propel chose Chroma to power agent search.](/content/customers/propel-ai-case-study/index.html): Case study: How Propel's AI code reviewer uses Chroma Cloud for repository wide code context during code review. (397 words)
- [The Challenge](/content/customers/mintlify-case-study/index.html): Case study: Chroma Cloud powers Mintlify's agent and human search (465 words)
- [Product](/content/changelog/package-search-mcp/index.html): We indexed thousands of open-source repos in Chroma, and exposed query support through an MCP server. 

Add to your coding agent or LLM *(Cursor, Claude, Open..., We indexed thousands of open-source repos in Chroma, and exposed query support through an MCP server. 

Add to your coding agent or LLM *(Cursor, Claude, Open... (40 words)
- [Changelog](/content/changelog/index.html): Stay up to date with the latest updates and releases from Chroma (51 words)
- [Chroma, now 4x faster](/content/project/1-0-0.html) (358 words)
- [Chroma Sync](/content/products/sync/index.html): Serverless data ingestion for Chroma Cloud. Connect your S3 buckets, GitHub repositories, and websites. Chroma handles parsing, chunking, and embedding. (428 words)
- [What you'll do](/content/careers/distributed-systems/index.html): Build reliable, scalable, and performant distributed systems for Chroma's data plane. (229 words)
- [Interviews](/content/updates/interviews/index.html): Open-source search infrastructure for AI (45 words)
- [Company Updates](/content/company/index.html): Open-source search infrastructure for AI (6 words)
- [Sparse Vector Search in Chroma](/content/updates/project/index.html): Open-source search infrastructure for AI (13 words)
- [Technical Report: Context-1](/content/updates/index.html): Open-source search infrastructure for AI (113 words)
- [IndexingStatus - Chroma Changelog](/content/changelog/indexingstatus/index.html): When data is written to Chroma, it's first committed to our write-ahead log ([Wal3](https://www.trychroma.com/engineering/wal3)), then indexed and persisted to ... (166 words)
- [Customer-Managed Encryption Keys - Chroma Changelog](/content/changelog/cmek/index.html): Customer-Managed Encryption Keys (CMEK) is now Generally Available (GA) and already powering production workloads for our enterprise customers on GCP and AWS. C... (174 words)
- [Terms](/content/website-terms/index.html) (451 words)
- [How it works](/content/changelog/groupby/index.html): **Group By & Aggregation** is now available on Chroma Cloud. 

GroupBy is useful when the unit of results you want to return is not the chunk, but instead an ..., **Group By & Aggregation** is now available on Chroma Cloud. 

GroupBy is useful when the unit of results you want to return is not the chunk, but instead an ... (379 words)
- [Engineering](/content/engineering/index.html): Open-source search infrastructure for AI (24 words)
- [Scraping Challenges](/content/changelog/chroma-web-sync/index.html): Chroma Sync now supports web pages. Automatically crawl, scrape, chunk and embed web pages directly into Chroma Cloud.

![Chroma Web Sync](/img/web-sync.jpg)
..., Chroma Sync now supports web pages. Automatically crawl, scrape, chunk and embed web pages directly into Chroma Cloud.

![Chroma Web Sync](/img/web-sync.jpg)
... (270 words)
- [Project Updates](/content/project/index.html): Open-source search infrastructure for AI (14 words)
- [Product](/content/talk-with-us/index.html): Open-source search infrastructure for AI (38 words)
- [Updates - Chroma](/content/updates/engineering/index.html): Open-source search infrastructure for AI (24 words)
- [Log in to Chroma](/content/login/index.html): Open-source search infrastructure for AI (27 words)
- [Introduction\#](/content/research/evaluating-chunking/index.html): Despite document chunking being virtually ubiquitous as a pre-processing step, little work has been done to investigate its impact on retrieval performance. This is partially due to the structure of commonly used information retrieval benchmarks, which are aimed at whole-document retrieval tasks. 

In this work we present an evaluation approach which takes token-level relevance into account, and allows for the evaluation of several popular document chunking strategies. We demonstrate that the choice of chunking strategy can have a significant impact on retrieval performance, with some strategies outperforming others by up to 9% in recall. 
 (9,790 words)
- [Seed Round](/content/updates/company/index.html): Open-source search infrastructure for AI (5 words)
- [Retrieval for AI.](/content/signup/index.html): Open-source search infrastructure for AI (29 words)

## Resources

- [Full Page Index](/index.html): Browse all cached pages with rich metadata
- [About This Cache](/content/about.html): Methodology, technical details, and usage guidelines
- [XML Sitemap](/sitemap.xml): Machine-readable sitemap for crawler discovery
- [Robots.txt](/robots.txt): Crawler directives