LakeSail

Skip to main content The AgenticHumanAdaptive ERA Extract meaning. Reason at scale. Activate decisions. Get Access Talk To Us → Built for both Humans and Agents RUST-NATIVE · STATELESS · YOUR CLOUD One engine for every workload. One layer for every agent. One Rust-native runtime for batch, stream, ad hoc, & AI. One platform to orchestrate every workload & agent around your data. UNIFIED Batch, Stream, Ad Hoc, AI RUST-NATIVE Zero JVM overhead SPARK COMPATIBLE No rewrite required MULTIMODAL LAKEHOUSE Any modality · PDFs, images, videos, and more The Platform All Your Data, One Platform Your CloudComputeSQL & Python JobsAgents Your Cloud, Fully Managed Deploys in your AWS account. Your cloud, your data. BYOC: runs inside your AWS account Your IAM roles, your encryption keys Sovereignty built in from day one Zero ops overhead Fully Managed We handle the infrastructure so you can focus on your workloads. Governance & Access Control SSO, role-based access, and granular permissions out of the box. Agentic Infrastructure How agents operate on LakeSail LakeSail gives agents a governed system for execution, validation, and adaptive branching so they can operate reliably at scale. Agent-Driven Execution LakeSail gives agents a governed execution layer for queries, Python, and runtime tooling on data. Built for agents Dynamic Tooling at Runtime Agents can define custom Python data sources and UDFs at runtime, so execution adapts as work unfolds. Custom Python tools Automatic Lakehouse Branching Create isolated lakehouse branches automatically so agents can explore, validate, and recover without touching production data directly. Safe by default Elastic Compute per Workload Compute provisions on demand for each workload, scales with execution, and releases when the work is done. Scale to zero Governed, Auditable Operation Every run is auditable, controlled, and built for human oversight so agents can operate reliably in production. Human-governed Performance Powered By Sail Rust-native, Spark compatible, zero JVM overhead. Up to 8x Faster on average than Spark 16x More Data Processed 94% Lower Cost ClickBench TPC-H ClickBench, c6a.4xlarge, lower is faster LakeSail ×1.76 Gluten‑on‑Velox ×5.78 Spark+Comet ×6.04 Spark+Auron ×6.54 Apache Spark ×7.80 Getting Started Running In Minutes Connect Your Data Any source and any sink Your Infrastructure Deploy in your AWS or on-prem Zero Rewrites Existing Spark code just works See The Difference Rust-powered performance The agentic data layer is here. Get Access Talk to us → --- Skip to main content Everything your data needsin one platform. Rust-native SQL, PySpark, and AI workloads. Your AWS account, built-in scheduling, scale-to-zero compute. Get Access Talk to us → The Platform All Your Data, One Platform Your CloudComputeSQL & Python JobsAgents Your Cloud, Fully Managed Deploys in your AWS account. Your cloud, your data. BYOC: runs inside your AWS account Your IAM roles, your encryption keys Sovereignty built in from day one Zero ops overhead Fully Managed We handle the infrastructure so you can focus on your workloads. Governance & Access Control SSO, role-based access, and granular permissions out of the box. Solutions What can you do with LakeSail? Data Engineering SQL, Python, and Spark pipelines with built-in scheduling. Agentic Infrastructure Agents provision compute and create tools at runtime. Features What powers it Spark Connect Compatible Drop-in Spark SQL and PySpark compatibility on a faster engine. Python Workloads Write Python, execute on Rust. Zero-copy UDFs via PyO3. Ready to try it? Get Access Talk to us → --- Skip to main content DATA ENGINEERING Because your pipelines shouldn’t have to suffer Upgrading your workloads to a faster, more cost-efficient engine has never been easier. Get Access Talk to us → Data Pipeline on LakeSail SQL / Py Write or upload Sail Engine Rust-native Delta / Iceberg Open formats Your S3 Your VPC Spark SQL Parquet CSV JSON Avro Platform Built for data engineers A Rust-native engine, Spark compatibility, and the day-to-day tooling you need. Rust-Native Engine Zero-copy Arrow execution with no JVM. Up to 8x faster on average than Spark. Drop-in Compatibility Run existing Spark Connect workloads without rewrites. Same API, faster engine. Proven at Scale Arrow Flight data exchange, pipelined shuffles, and automatic failure recovery keep jobs scaling without reconfiguration. On-Demand Provisioning and Autoscaling Nodes are provisioned automatically per job, and scale down after completion. Pay only for the compute you're actively using. Job Orchestration Dependencies, cron schedules, and automatic retries built in. Connects with Airflow, Dagster, and the orchestration tools you already use. Open Formats Read and write with Rust-native Delta Lake and Iceberg support. Ingest from any modality. Python and SQL Jobs Write, run, and schedule jobs from a single workspace. One place for ad hoc analysis and production pipelines alike. Runs in Your Cloud Deploys inside your AWS account. Retain full control over security, networking, and data residency. Performance at a Glance Up to 8x Faster on average across TPC Benchmarks94% Lower compute cost on same workloads2-8x Faster execution on same workloads0 Code changes to switch from Spark Advantages How LakeSail takes your workloads to the next level The engineering advantages that save you time and money every day. 01 Seconds to Ready Lightweight native processes replace heavyweight startup, so your jobs begin processing immediately. No more minutes of delay before any real work begins. 02 Native-Speed Python UDFs Sail embeds a Python interpreter directly in the engine process. No data serialization or copying between built-in operations and your Python UDFs. 03 Compile-Time Safety Sail is built in Rust, which guarantees memory safety and prevents data races at compile time. No garbage collector, no GC overhead, and fewer bugs in production. 04 Lower Infrastructure Costs LakeSail finishes the same workloads on smaller instances. No more paying for capacity you don't need. Ingestion & Open Formats Bring your data in. Keep it open. Connect any source or sink. Land in open lakehouse tables with no lock-in. Native format support Read and write any data modality natively. No external connectors or conversion steps needed. First-class lakehouse tables Read and write with Rust-native Delta Lake and Iceberg support. Python Data Sources Can't find your data source? Define custom readers and writers in Python to connect to any system. Migration Zero rewrites required LakeSail drops into your existing stack: same APIs, same data, faster engine. Spark Connect compatibility: same API, faster engine, zero rewrites Run existing jobs faster on smaller instances Keep your data where it is: your S3, your VPC Existing orchestrators work as-is Getting Started Simple to get started LakeSail runs in your AWS account, so there are a few setup steps. Here’s what to expect. 1 Create Account Sign up with email, verify via code, and set up mandatory 2FA.2 Connect AWS Launch a CloudFormation template in your account. Requires admin access.3 Create Cluster Set up a VPC with your CIDR block, then create a cluster.✓ Run Your First Query Open the SQL editor, point to your data, and go. Faster Pipelines Start Here Get Access Talk to us → --- Skip to main content AGENTIC INFRASTRUCTURE The data layer for AI agents LakeSail gives agents a governed system for execution, validation, and adaptive branching. Run Python and SQL, define tools dynamically, and operate safely on your data at scale. Get Access Talk to us → Capabilities Built for agentic workloads The core infrastructure agents need to execute, validate, and operate safely on data at scale. Elastic Agent Compute Provision compute on demand for each agent workload, scale with execution, and release resources when the work is done. Dynamic Tool Creation Agents can define custom Python data sources and UDFs at runtime, giving them a flexible execution layer that adapts as work unfolds. Governed Execution Every workload runs with auditable controls, clear isolation boundaries, and human oversight built in from the start. A Shared Data Layer Agents operate on structured, queryable data instead of scattered context and files, making execution more reliable, observable, and governable. Automatic Lakehouse Branching Create isolated lakehouse branches automatically so agents can explore, validate, and recover safely without touching production data directly. Native Python Execution Python executes directly inside the engine via PyO3, with zero-copy access to shared Arrow buffers for high-performance agent workloads. Why LakeSail Legacy data engines weren’t built for agents Agents need fast startup, dynamic Python execution, safe branching, and governed access to data. Traditional JVM-based systems were built for a different model of work. Traditional JVM Platforms Startup Model Heavier runtime overhead JVM startup, warm-up, and executor overhead before work begins Python Execution Cross-process execution Python runs outside the engine process, adding serialization and IPC overhead Branching and Validation Not built for agent workflows Agent-style validation, recovery, and adaptive execution require additional systems Execution Model Cluster-oriented Long-lived infrastructure designed for traditional batch and ETL workloads Cost Model More idle overhead Keeping infrastructure warm can add cost even when workloads are intermittent LakeSail Startup Model Fast, lightweight startup Rust-native engine with no JVM or VM warm-up path Python Execution In-process, zero-copy execution Python runs inside the engine via PyO3 with zero-copy access to shared Arrow buffers Branching and Validation Built for agent workflows Automatic lakehouse branching supports exploration, validation, and safe recovery Execution Model Elastic and workload-driven Compute provisions per workload, scales with execution, and releases when work is done Cost Model Scale-to-zero economics You pay for active compute instead of keeping idle clusters running Agents need a governed execution layer for data. LakeSail is built to make agent workloads operational, auditable, and safe at scale. Getting Started Simple to get started From signup to running agent workloads in four steps. 1 Create Account Sign up with email, verify via code, and set up mandatory 2FA.2 Connect AWS Launch a CloudFormation template in your account. Requires admin access.3 Connect Your Agent Connect your agent workflows to LakeSail and start running governed workloads on your data.✓ Run Agent Workloads Agents run SQL and Python, define tools dynamically, and operate safely on governed data. Native Python Runs in-process on the Rust engine0 Cross-process Python serialization overheadElastic Compute provisions per workload and scales to zero Give your agents a data layer built for production Get Access Talk to us →