# www.trychroma.com

> AI-optimized mirror of www.trychroma.com containing 43 pages totalling 43,706 words of clean markdown content, structured data, and semantic HTML. Original source: https://www.trychroma.com/. Last updated: 2026-04-17T00:54:37.416Z.

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

## Homepage

- [Chroma - open-source search infrastructure for AI](/site-root.html): Read case study → (1,026 words)

## Articles & Blog Posts

- [ChromaDB - the open-source search infrastructure for AI](/products/chromadb/index.html): The open-source search infrastructure for AI. Fast, serverless, and scalable. Supporting vector, full-text, regex, and metadata search. Built on object storage and trusted by millions of developers. (550 words)
- [Chroma v0.4 | Chroma](/blog/chroma_0-4-0.html) (1,123 words)
- [The Embedding Revolution | Chroma](/blog/podcast-cogrev/index.html): March, 2, 2023 (255 words)
- [Interviews - Chroma](/interviews/index.html) (45 words)
- [Chroma - open-source search infrastructure for AI](/package-search/registry/package.html) (4 words)
- [Discussing Attention is All You Need | Chroma](/blog/podcast-notboring-1/index.html): November 7, 2022 (192 words)
- [Chroma Server in Production | Chroma](/project/server-in-prod/index.html): Chroma has quickly become the leading retrieval system for developers building with AI. From the first week of our launch back in 2023, we've seen a steady stream of developers deploying Chroma in ... (392 words)
- [Enterprise - Chroma](/enterprise/index.html): # Why Chroma ## Fast Experimentation Chroma's run-anywhere architecture lets you get started in minutes. No complex setup or infrastructure needed. Your time to demo is minutes, not days. ## De... (393 words)
- [Google PaLM + Chroma | Chroma](/blog/palm/index.html) (199 words)
- [Product Engineering - Careers at Chroma](/careers/product-engineering/index.html): Developer experience has been a key element of Chroma's success from the beginning. Chroma is the leading retrieval system for AI developers because we focus on every detail of the user experience,... (207 words)
- [Chroma Context-1 - Agentic search at the Pareto frontier](/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)
- [Product Designer - Careers at Chroma](/careers/product-designer/index.html): At Chroma, we build software that millions of developers use to create AI applications. We focus on the memory layer of AI—what AI systems know and remember. This new frontier requires new user int... (345 words)
- [Chroma Sync - Serverless Data Ingestion](/products/sync/index.html): Serverless data ingestion for Chroma Cloud. Connect your S3 buckets, GitHub repositories, and websites. Chroma handles parsing, chunking, and embedding so you can start searching in minutes. (428 words)
- [Announcing our Hacker in Residence Program | Chroma](/blog/hir-2023/index.html) (435 words)
- [Company Updates - Chroma](/company/index.html) (6 words)
- [Package Search MCP for AI Agents - Chroma](/package-search/index.html): ▗▄▄▖ ▗▄▖ ▗▄▄▖▗▖ ▗▖ ▗▄▖ ▗▄▄▖▗▄▄▄▖ ▐▌ ▐▌▐▌ ▐▌▐▌ ▐▌▗▞▘▐▌ ▐▌▐▌ ▐▌ ▐▛▀▘ ▐▛▀▜▌▐▌ ▐▛▚▖ ▐▛▀▜▌▐▌▝▜▌▐▛▀▀▘ ▐▌ ▐▌ ▐▌▝▚▄▄▖▐▌ ▐▌▐▌ ▐▌▝▚▄▞▘▐▙▄▄▖ ▗▄▄▖▗▄▄▄▖ ▗▄▖ ▗▄▄▖ ▗▄▄▖▗▖ ▗▖ ▐▌ ▐▌ ▐▌ ▐▌▐▌ ▐▌▐▌ ... (293 words)
- [Changelog - Chroma](/changelog/index.html): └─ Latest updates and releases (51 words)
- [Retrieval powered by object storage | Chroma](/engineering/serverless/index.html): Retrieval has emerged as an important component in the AI application stack. Input prompts to a large language model (LLM) can be augmented with relevant information stored in a retrieval system, a... (926 words)
- [Pricing - Chroma](/pricing/index.html): Chroma Cloud enables fast, scalable, & serverless vector, full-text, and metadata search across terabytes of data. The open-source search infrastructure for AI. (321 words)
- [Engineering - Chroma](/engineering/index.html) (24 words)
- [Propel uses Chroma to power code review agents | Chroma](/customers/propel-ai-case-study/index.html): “Chroma is the obvious choice for Propel, enabling our agents to reason across entire repositories and dependencies. The result is more accurate reviews and a higher standard of feedback.” (397 words)
- [Sparse vector support is here! | Chroma](/project/sparse-vector-search/index.html): Chroma now supports sparse vector search. We’re shipping first class support for BM25 and SPLADE embeddings. Sparse vectors capture lexical signals like term frequency and rarity. Combine with dens... (700 words)
- [Chroma v0.4 | Chroma](/project/0-4-0.html) (1,133 words)
- [Chroma raises $18M seed round | Chroma](/blog/seed/index.html): April 7, 2023 (750 words)
- [Designing a query execution engine | Chroma](/engineering/execution-engine/index.html): Authored by Hammad Bashir Sanket Kedia Sicheng Pan (1,232 words)
- [Updates - Chroma](/updates/filter.html) (113 words)
- [Discussing Stable Attribution | Chroma](/blog/podcast-notboring-2/index.html): February 10, 2023 (133 words)
- [Platform - Careers at Chroma](/careers/platform/index.html): Millions of AI developers will rely on Chroma's cloud service for their applications. We can't afford to deliver something that's just 'good enough'. The AI ecosystem is developing rapidly, and Chr... (222 words)
- [Chroma raises $18M seed round | Chroma](/company/seed/index.html): April 7, 2023 (760 words)
- [Careers at Chroma | Jobs & Open Positions](/careers/index.html): └─ Build the data & search infrastructure for AI (97 words)
- [Replit + Chroma | Chroma](/blog/replit/index.html) (498 words)
- [How Factory powers code search with Chroma Cloud | Chroma](/customers/factory-ai-case-study/index.html): “Switching to Chroma unlocked core functionality for us, fast, effortless, and accurate code search.” (706 words)
- [Making Celebrity Voice | Chroma](/blog/voice/index.html): March 6, 2023 (483 words)
- [ScienceIO + Chroma | Chroma](/blog/scienceio/index.html) (343 words)
- [Chroma is now 4x faster | Chroma](/project/1-0-0.html): Two years ago, we set out to make AI retrieval effortless for developers. 30+ million downloads later, that vision is becoming reality with widespread adoption across hackathon projects, fast-growi... (358 words)
- [Mintlify powers search with Chroma Cloud | Chroma](/customers/mintlify-case-study/index.html): “Migrating to Chroma removed the pain. No one’s getting woken up on call anymore. We all get to sleep through the night.” (465 words)
- [Evaluating Chunking Strategies for Retrieval | Chroma](/research/evaluating-chunking/index.html): Chunking is a commonly used pre-processing step when ingesting documents for retrieval in the context of AI applications. Chunking serves to divide documents into units of information, with semanti... (9,790 words)
- [Chroma - open-source search infrastructure for AI](/ai-engine/index.html): Continue with GithubContinue with GoogleContinue with SSOContinue with emailBy clicking continue, you agree to our terms of service, privacy policy, and data processing addendum. (29 words)
- [Distributed Systems - Careers at Chroma](/careers/distributed-systems/index.html): Scaling retrieval systems is a challenging engineering problem. Chroma's distributed data plane must support workloads appropriate to serving AI applications at scale, which involves scaling vector... (229 words)
- [Chroma Context-1: Training a Self-Editing Search Agent | Chroma](/research/context-1/index.html): Using search systems in conjunction with a large language model (LLM) is a common paradigm for enabling language models to access data beyond their training corpus. This approach, broadly known as ... (11,630 words)
- [Database Storage - Careers at Chroma](/careers/database-storage/index.html): Chroma is about data. Chroma's retrieval system is built on top of a distributed storage engine that is designed to be scalable, reliable, and serverless. (179 words)
- [Why an Open-Source Embedding Database? | Chroma](/blog/podcast-sedaily/index.html): April 20, 2023 (5,953 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](/content/sitemap.xml): Machine-readable sitemap for crawler discovery
- [Robots.txt](/content/robots.txt): Crawler directives