cat open-source.md

Answer any agent question directly on the data in your bucket.

Scalable search + analytics data infrastructure on object storage, for 10x cheaper.

Contact an engineer Get started for free

ClickBench: Infino ranks #1 among search engines for SQL analytics →

trusted by

United States Government
Pendo
Bazinga Labs

Built by the creators of OpenSearch

infino why

Getting data from your bucket to agent queries takes six jobs.

01
Get the data into shape

Export every source to files in a bucket.
02
Choose what to search

Decide which columns get keyword search and which get search by meaning.
03
Turn text into vectors

Pick an embedding model and chunk the text.
04
Make it fast at size

Tune for table design and big loads.
05
Explain the data

Write down what every column and code means, and which tables join.
06
Connect the agents

Give agents the tools and the context to query it well.

infino hydrate

Infino fully automates ingestion, retrieval and inference.

Infino

Hydrate and ingest

Chunk
Embed
Index
Table cards
Join keys
Sync

Retrieval engine

Keyword (BM25)
Vector
Graph
SQL

Supermodel

Frontier model
Infino Supermodel

Your bucket

Your data

Parquet
Iceberg
Hudi
JSON
CSV
Logs
BM25 and vector indexes
Table cards
Join keys

Your agents

Claude
Cursor
Hermes
Your apps
Your team

hydrate and ingest →

cat query.sql

Any agent question can be answered on Infino.

1An agent asks a question

How manyA count. The agent wants a number. SQL does this with COUNT. errors last nightFilters. Keep the error-level rows and the last 24 hours. mention disk fullKeyword search. Match those exact words in the log body. Today this is a call to a search engine. or look like a capacity incidentSemantic search. Match meaning even when the log never says disk full. Today this is a call to a vector database., and are tied to last week’s outageGraph search. Keep the errors linked to the outage’s record through a key they share, like a host or a service, even when they never mention it. Today this is a call to a graph database.? Which serviceA group on the same hits. SQL GROUP BY. Today a second warehouse query after the searches return. had them, and which team owns itA join. Match each service to its owner in a second table. Today the agent looks this up in another system and stitches the answers together.?

2It hides seven jobs

count
group
join
filter
keyword search
semantic search
graph search

hybrid search →

3Infino SQL runs all seven

query.sql

SELECT   o.team, h.service, count(*) AS hits
FROM     hybrid_search(
           'logs', 'body', 'disk full',
           'embedding', :q, 1000
         ) AS h
JOIN     graph_walk('logs', 'incidents', [4521], 2, 5000) AS g
           ON g._id = h._id
JOIN     owners o ON o.service = h.service
WHERE    h.level = 'error'
  AND    h.ts > now() - interval '24 hours'
GROUP BY o.team, h.service
ORDER BY hits DESC;

infino bench

Faster, cheaper and more scalable than any other engine in the world.

Keyword · 1B documents

Infino top-10 latency: 78 ms
Lucene top-10 latency: 536 ms

Vector · 10M vectors

Infino QPS at recall ≥ 0.95: 4,210
Milvus QPS at recall ≥ 0.95: 2,517
pgvecto.rs QPS at recall ≥ 0.95: 1,428
pgvector QPS at recall ≥ 0.95: 1,335
Qdrant QPS at recall ≥ 0.95: 267

SQL · 100M rows

Infino vCPU-seconds per query: 12.7
Snowflake vCPU-seconds per query: 16.6
Databricks vCPU-seconds per query: 28.0

Analytics cost · 1 PB

Infino monthly bill at list prices: $401K
Databricks monthly bill at list prices: $1.30M
Snowflake monthly bill at list prices: $1.85M

Search cost · 1 PB

Infino monthly bill at list prices: $398K
OpenSearch monthly bill at list prices: $5.74M
Elasticsearch monthly bill at list prices: $6.34M

benchmarks →

infino eval

Supermodel helps frontier models query and retrieve the correct data more accurately, faster and with fewer tokens.

Databricks' OfficeQA Pro V2 benchmark

1 Supermodel + Opus 5.5 cost per question: $0.63 answered exactly right: 73.3%
2 Mixedbread Toast + GPT-5.6 Sol cost per question: $1.15 answered exactly right: 70.0%
3 Databricks Genie + Claude Fable 5 cost per question: $4.00 answered exactly right: 60.0%
4 Claude Code + Claude Fable 5 cost per question: $37.36 answered exactly right: 45.6%
5 Codex + GPT-5.6 Sol cost per question: $4.70 answered exactly right: 33.3%
6 Claude Code + Claude Sonnet 5 cost per question: $5.01 answered exactly right: 15.6%

supermodel →

infino diff

How Infino compares.

Capability	Infino	Databricks	Snowflake	Elastic
Where your data lives	One copy, open Parquet in your bucket	Delta in your bucket, plus a vector index copy	Snowflake storage or Iceberg, plus a Cortex Search index copy	A copy in its own index
Keyword and vector search	Inside the same files	Separate Vector Search endpoints	A separate Cortex Search service	Native, on Lucene
SQL and joins	Yes, with search inside SQL	Yes	Yes	Limited, through ES\|QL
Context for agents	Table cards and join keys, built for you	Genie spaces you set up	Semantic models you write	Agent Builder over your indices
Cost	1×	8×	24×	10×
Answer accuracy	73.3%	60.0%	57.8%	n/a

infino migrate

Replace five systems with Infino and run on one copy of your data.

01
Start with search
Swap out Lucene under OpenSearch, or load an Elasticsearch snapshot. Your clients and Dashboards stay as they are.
02
Add the next workload
Vectors, graph and analytics land in the same Parquet files in your bucket.
03
Consolidate everything
Retire Pinecone, Neo4j, ClickHouse and Snowflake one at a time, until one copy serves every agent.

migrate from Elasticsearch or OpenSearch →

infino spec

Specs in the cloud or on-prem.

architecture →

search: full-text · vector · hybrid · graph · NL
index: BM25 (PFOR-delta, FST) · HNSW · OPANN + Sq16
engine: Rust + Small Language Models (SLMs)
language: SQL (Apache DataFusion) · REST · Query DSL · MCP · NL
storage: object storage, S3 · GCS · Azure Blob · on-prem
format: Apache Parquet
deploy: on-prem · self-hosted cloud · hosted cloud
core license: Apache-2.0
security: SOC 2 Type II
encryption: TLS in transit · AES-256 at rest

infino init

Queries, made simple.

Contact an engineer Get started for free

or run it yourself: pip install infino · Apache-2.0 · quickstart →

Answer any agent question directly on the data in your bucket.

Getting data from your bucket to agent queries takes six jobs.

Get the data into shape

Choose what to search

Turn text into vectors

Make it fast at size

Explain the data

Connect the agents