Chromavs
Cockroach Labs
Cockroach Labs: The cloud-native distributed SQL database
Chroma
Apache 2.0 vector and full-text search engine that runs as an embedded library, a single server or a distributed cloud service.
As of 30 August 2026, Chroma is free to use. Chroma is the vector database most AI prototypes start with because it is a pip install away and needs no infrastructure. Softwr lists it under Databases.
Overview
What Chroma does
Chroma is an open source search engine for AI applications, licensed Apache 2.0. It stores documents, their embeddings and their metadata in collections and retrieves them by vector similarity, by keyword, or by both combined, with metadata filters applied alongside the search. It runs in three shapes with a consistent API: as an embedded library inside a Python, TypeScript or Rust process for prototyping; as a single server started with one command, intended for small and medium workloads, which the project characterises as fewer than about ten million records across a handful of collections; and as a distributed deployment of independent services over object storage with SSD caches and a shared system database, which is what Chroma Cloud runs. What distinguishes it is the on-ramp. Almost every competing vector database asks you to run something before you can index your first document; Chroma asks for an import statement, and the code you write against it in a notebook is the code that runs against the cloud. Commercially that has made it the default in tutorials, framework integrations and agent toolkits, which is a real advantage because it means the retrieval layer is rarely the part of a prototype that needs explaining. The permissive licence reinforces this: there is no source-available clause to review before embedding it in a product. The buyers are application teams building retrieval-augmented generation and agent memory, usually starting embedded and deciding later whether to move to the server or the cloud. The trade-off is that the easy mode has a physical ceiling. On a single node the amount of system memory bounds collection size directly, roughly a quarter of a million records per gigabyte of RAM at 1024 dimensions, and query throughput parallelises only up to the number of vCPUs before latency rises linearly with concurrency. The distributed deployment is a genuinely different architecture, with different latency and consistency behaviour, so the thing you tested locally is not the thing you eventually run. Planning for that transition early is the difference between a smooth migration and a rewrite under load.
What people use it for
- Prototyping retrieval-augmented generation where the priority is having a working index in minutes rather than choosing a permanent store
- Agent memory in a single application process, where an embedded store avoids adding a network dependency
- A departmental search application under roughly ten million records where one server is sufficient and simplicity is worth more than headroom
- Local and CI testing of retrieval code with the same client library used in production
The honest half
Where it falls short
Concrete and checkable, so you can decide whether any of them matter to you. This is the half of a review a vendor will not write about Chroma.
- On a single node, available memory sets a hard upper bound on collection size, roughly 245,000 records per gigabyte of RAM at 1024 dimensions, so capacity planning is a memory purchase and the ceiling arrives without warning.
- Single-node queries parallelise only up to the number of vCPUs, after which requests queue and latency rises linearly with concurrency, so throughput problems appear as a slow application rather than as errors.
- The distributed deployment behind Chroma Cloud is a different architecture from the embedded library, so latency, consistency and failure behaviour observed in a local prototype do not predict production behaviour.
- The open source server has no built-in authentication or multi-tenancy worth relying on, so a self-hosted deployment needs its own auth proxy and network controls before anything untrusted can reach it.
- The project has moved quickly through major internal rewrites and version changes, so upgrades have historically involved data migrations and client changes, and pinning versions is necessary rather than cautious.
Cross-shopped
What people choose instead of Chroma
Each pairing was judged by two reviewers asking whether a buyer would genuinely weigh the two against each other. The ones that failed were deleted rather than published.
- ChromavsPostgreSQL
PostgreSQL: The world's most advanced open source relational database
- ChromavsAirtable
Airtable: Create apps that perfectly fit your team's needs
- ChromavsAmazon Aurora
Amazon Aurora: MySQL and PostgreSQL-compatible relational database built for the cloud
Pricing
What Chroma costs
Taken from the vendor's own pricing page. Prices move, so check before you buy.
Starter
Free
- 10 databases
- 10 team members
- Community Slack access
- Free credits included
Team
$250 /mo
- 100 databases
- 30 team members
- $100 in included credits
- Slack support
- SOC II compliance
- Volume discounts
Enterprise
On request
- Unlimited databases
- Unlimited team members
- Dedicated support
- Single tenant clusters
- Custom SLAs
Capabilities
Features
Embedded mode
Runs in-process with persistence to a local directory, so a prototype needs no server
Single-node server
One command starts an HTTP server for small and medium production workloads
Distributed architecture
Independent services over object storage with SSD caching for large deployments and many collections
Vector search
Approximate nearest neighbour retrieval over embeddings stored per collection
Full-text search
Keyword retrieval alongside vector search so hybrid strategies do not need a second system
Metadata filtering
Predicates on document metadata evaluated as part of the query rather than as a post-filter
Consistent API across modes
The same client interface covers embedded, server and cloud deployments
Multi-language clients
Python, TypeScript and Rust clients, plus a thin HTTP-only client for constrained environments
Embedding function integrations
Pluggable embedding providers so documents can be embedded on write
Apache 2.0 licence
Permissive open source with no competing-use restriction on self-hosting
Answered, with sources
Questions people ask
Each answer names the page it came from, so you can check it rather than take our word for it.
Do I need to run a server?
No. Chroma runs embedded in your process with persistence to a local directory, which is how most projects start. The server and distributed modes exist for when multiple clients or larger collections require them.
How large can a single node get?
The project puts single-node deployments at fewer than about ten million records across a handful of collections, with collection size bounded by system memory at roughly 245,000 records per gigabyte at 1024 dimensions.
Is Chroma Cloud the same software?
It is the same API and project, but the distributed deployment is a different architecture, using independent services, object storage and SSD caches rather than a single process. Behaviour under load differs accordingly.
How does it compare with pgvector?
pgvector keeps vectors in a Postgres database you already operate, with SQL, joins and transactions. Chroma is a dedicated retrieval engine with a lower setup cost and a retrieval-shaped API. If you already run Postgres, pgvector removes a system; if you do not, Chroma removes a decision.
What licence is it under?
Apache 2.0, which permits self-hosting and embedding in commercial products without a competing-use restriction.
Keep looking
Where to go from Chroma
- Chroma alternativesEvery product people weigh against it
- Chroma pricingPlans, floors and what the tiers exclude
- Chroma badgesWhich rules it meets, and the figure behind each
- All Databases softwareThe full category
- Best Databases softwareThe shortlist, and how it was cut
Best Databases software for
Compare Chroma with
- Airtable
- PostgreSQL
- Cockroach Labs
- Amazon Aurora
- DuckDB
- turbopuffer
- Vespa
- Qdrant
- SQLite
- Timeplus
- EMQX
- LanceDB
- Firebase Realtime Database
- Memcached
- MotherDuck
- Neo4j
- OpenSearch
- Firestore
Other Databases software
Create apps that perfectly fit your team's needs
Free, then $20/month per editor11 researched notesMySQL and PostgreSQL-compatible relational database built for the cloud
Free plan12 researched notesMIT-licensed analytical SQL database that runs inside your process, with no server, no dependencies and one writer at a time.
Free plan14 researched notesClosed-source vector and full-text search service built directly on object storage, with cold queries measured in seconds rather than milliseconds.
From $16/mo14 researched notesDistributed AI search platform for retrieval, ranking, and inference
Free plan11 researched notesHigh-performance vector database for similarity search and embedding-based retrieval
Free plan13 researched notesStreaming SQL engine built on ClickHouse internals, shipping as one small binary
Free, then $199/mo12 researched notesErlang MQTT broker for large IoT fleets, relicensed to BSL with production free use limited to one node
Free, then $234/mo12 researched notesEmbedded retrieval library over the Apache 2.0 Lance columnar format, with proprietary Cloud and Enterprise tiers for serving at scale.
Pricing on request14 researched notesStore and sync data in real-time across all clients
Free plan12 researched notesOpen-source search and analytics suite forked from Elasticsearch
Open source9 researched notes
Softwr does not host reviews and shows no star rating for Chroma, because a rating we did not collect is not ours to publish. What is here is the pricing and platform detail from the vendor’s own pages, limitations we could state concretely, and alternatives a reviewer confirmed people weigh against it. Tell us if any of it is wrong.
More on Chroma
Chroma alternatives
What people switch to, and what they give up
Chroma pricing
Every tier, and where the cost actually lands
Compare Chroma
Put it head to head with anything we hold
Chroma badge
Its rating, and an embed for your own site
Best Databases software alternatives
Industrial process historian with published per-tag pricing and no client licence fees
Per tag band per year
NetApp-owned managed service for Cassandra, Kafka, OpenSearch, PostgreSQL and Cadence with a bring-your-own-cloud model
quoteErlang MQTT broker for large IoT fleets, relicensed to BSL with production free use limited to one node
Per month by connection and session volume
Attribute-based access control and masking applied inside Snowflake, Databricks and BigQuery
quote
MPP analytical database with a MySQL wire protocol and sub-second aggregation on wide tables
Open source, no licence fee
Streaming database that maintains incremental materialised views in SQL instead of Flink jobs
Per RisingWave Unit hour
Centralised data access governance from the creators of Apache Ranger, now rebranding as Trust3 AI
quote
The Meta-lineage distributed SQL query engine, distinct from the Trino fork
Open source, no licence fee