Kaelio

Active

The open-source context layer for data agents

Spring 2025Founded 20248 people

kaelio.com/ ↗LinkedIn ↗X ↗See on the Idea Map B2B momentum

About

Kaelio is the company behind ktx, the open-source context layer that makes data agents reliable. Data agents today fail because they lack structured context and determinism. Metrics are defined in five places, governed in none. Teams spend months on semantic layer projects that never finish. ktx fixes that. Connect your warehouse, BI tools, and docs. ktx builds the context layer automatically. Your team governs it. Any agent can query it. One context layer across your entire data stack.

From their website

as of Jun 7, 2026kaelio.com ↗

Open-source

Kaelio's ktx is an open-source context layer that enables analytics agents to query data warehouses more accurately by providing business context, metric definitions, and governed SQL. It builds a reviewable context layer from the data stack and serves it to agents via CLI or MCP, with an open-source engine and optional hosted cloud offering.

ktx auto-builds a context layer from your data stack, compiles accurate SQL, and provides a reviewable YAML/Markdown context that agents use to query the warehouse. It reconciles sources (warehouses, BI, modeling code, query history, docs) into executable semantics and runs read-only SQL against the warehouse. The product offers an open-source engine and a cloud-hosted option, with CLI and MCP-based access to the context and query capabilities. It supports integration with multiple data tools and agents, and maintains review loops through git-diffed updates for governance.

Who it’s for: data teams and data-focused organizations that build and deploy analytics agents requiring governed context and accurate query results

Features

context layer with business definitions and metrics
query engine that plans grain, joins, and filters
reviewable YAML/Markdown diffs for governance
integrates with MCP and CLI for agent access
runtime serving of context to agents
local open-source engine and optional cloud hosting
supports multiple data stack components (warehouse, BI, modeling code)

open-source release, cloud offering (ktx Cloud) mentioned, multiple integrations described; community and enterprise-oriented governance features implied

Founders · 2

Luca MartialCo-founder & CEO

Co-founder & CEO at Kaelio. Previously data scientist and NLP engineer, with expertise in enterprise data systems and AI safety

LinkedIn ↗

Andrey AvtomonovCo-founder & CTO

Co-founder & CTO at Kaelio. Repeat AI safety founder. Previously software & AI engineer at CERN & Dataiku

LinkedIn ↗

Launch

Launched on Y Combinator · May 2026

View launch post ↗

We give data agents the context they need to be reliable on your data stack.

Kaelio launches ktx, an open-source context engine that provides business knowledge (Markdown) and executable definitions (YAML) to data agents. Agents request a metric’s context; ktx plans joins, applies metadata, and compiles warehouse SQL to improve accuracy and consistency in data projects.