Skip to content
SPECIFICTION
Get listed

Metarank

metarank.ai

WindowsmacOSLinuxAPISelf-hosted
Visit metarank.ai
Spec score 7.4 #10 of 20 in Feature Store Software

What it is

Metarank is an open-source ranking service for personalized semantic search and recommendations. It uses customer activity, including clicks and purchases, to adjust ranking and personalize results in real time. Capabilities include recommendations, LambdaMART reranking, automatic feature generation and retraining, and serving multiple models for A/B testing. It can use large language models in bi-encoder and cross-encoder modes for semantic search and reranking. Events can arrive through Apache Kafka, Apache Pulsar, AWS Kinesis Streams, a REST API, or files; files are supported for import, not inference. Persistence options include local memory, a local directory, Redis, and S3. It runs as a Docker container or JAR on Linux, Windows, and macOS, and provides APIs for feedback ingestion, training, ranking, recommendations, LLM inference, and Prometheus metrics. Production guidance recommends Redis persistence, while multiple API instances require an external load balancer because clustering is not provided out of the box.

Spec sheet

Product
Metarank is an open-source ranking service for personalized semantic search and recommendations.Read 8 Oct 2026 · docs.metarank.ai
Deployment
Metarank can run as a JAR or Docker container, and the docs also describe Kubernetes deployment.Read 8 Oct 2026 · docs.metarank.ai
API
Its API includes feedback, training, ranking, recommendations, LLM inference, and Prometheus metrics endpoints.Read 8 Oct 2026 · docs.metarank.ai
Privacy
The docs say default anonymous usage analytics does not track IP addresses, collected data is not shared, and data is stored for one year before removal.Read 7 Oct 2026 · docs.metarank.ai
Support
The docs invite users with questions to join the Metarank Slack community.Read 7 Oct 2026 · docs.metarank.ai
Headquarters
United StatesRead 28 Sep 2026 · metarank.ai
Data integrations
Supported event sources include Apache Kafka, Apache Pulsar, AWS Kinesis Streams, REST API, and files; files are supported for import but not inference.Read 8 Oct 2026 · docs.metarank.ai
Deployment limit
The production guide says standalone mode cannot be scaled across instances that share a database and recommends serve mode for production.Read 8 Oct 2026 · docs.metarank.ai
Error reporting
Error reporting uses Sentry by default, with breadcrumbs and personally identifiable information tracking disabled; tracking can be disabled in configuration or with METARANK_TRACKING=false.Read 7 Oct 2026 · docs.metarank.ai
Event sources
Supported event sources include Apache Kafka, Apache Pulsar, AWS Kinesis Streams, a REST API, and files.Read 7 Oct 2026 · docs.metarank.ai
Maker support
Metarank Labs describes itself as providing professional services and integration support for Metarank.Read 8 Oct 2026 · linkedin.com
Models
The product overview lists LambdaMART reranking, collaborative filtering recommendations, automatic feature generation, model retraining, and A/B testing among its features.Read 8 Oct 2026 · docs.metarank.ai
Performance
The performance guide lists typical reranking latency of 10–30 ms, Redis memory use of 1–10 GiB, and data import throughput of 1,000–3,000 events per second.Read 7 Oct 2026 · docs.metarank.ai
Personalization
It uses customer signals such as clicks and purchases to personalize ranking in real time.Read 8 Oct 2026 · docs.metarank.ai
Production requirement
For production, the docs recommend Redis persistence and say multiple API instances require an external load balancer because clustering is not provided out of the box.Read 7 Oct 2026 · docs.metarank.ai
Production requirements
The Kubernetes deployment guide lists Helm, Redis, and an event bus as prerequisites for distributed deployment.Read 8 Oct 2026 · docs.metarank.ai
Ranking
It uses customer signals such as clicks and purchases to improve ranking and support real-time personalization.Read 7 Oct 2026 · docs.metarank.ai
Ranking features
It computes ranking signals including click-through rate, referrer, user agent, and time.Read 8 Oct 2026 · docs.metarank.ai
Search
The docs describe using LLMs in bi-encoder and cross-encoder modes for semantic search and reranking.Read 7 Oct 2026 · docs.metarank.ai
Search integrations
The docs describe Metarank as a secondary reranking service that can work with search systems including Elasticsearch, OpenSearch, and SOLR.Read 8 Oct 2026 · docs.metarank.ai
Signals
Built-in feature extractors include interaction counts and rates, item age, local time, user-agent details, referer medium, ranking position, and diversity.Read 7 Oct 2026 · docs.metarank.ai
Storage
Documented persistence options include local memory, a local directory, Redis, and S3.Read 7 Oct 2026 · docs.metarank.ai
Supported systems
The JAR supports Linux x86_64/AArch64, Windows x86_64, and macOS x86_64/AArch64, with JVM 11 or newer.Read 8 Oct 2026 · docs.metarank.ai
Use cases
The docs describe semantic search, recommendations, and learning-to-rank as use cases.Read 8 Oct 2026 · docs.metarank.ai

Strong points and limits

Strong points

  • Open-source and self-hosted.
  • Supports real-time personalization from clicks and purchases.
  • Offers multiple models for A/B testing.
  • Supports Kafka, Pulsar, Kinesis, REST, and file event sources.
  • Includes online and offline stores and point-in-time joins.

Limits

  • Files are supported for import, not inference.
  • Multiple API instances require an external load balancer.
  • Production guidance recommends Redis persistence.
  • Standalone mode cannot scale across instances sharing a database.

Who it suits

Metarank suits teams building personalized search, recommendations, or learning-to-rank into their systems. It is for teams able to deploy and operate a self-hosted service, including production infrastructure such as Redis and an external load balancer for multiple API instances.

Verdict

Metarank provides ranking, recommendations, and semantic-search reranking as a self-hosted, open-source service. Production deployment requires attention to persistence and scaling constraints.

Where Specifiction places it

Alternatives to MetarankAll alternatives →