Strata – an expressive semantic layer that can say no to your LLM
15 minutes from setup to insights, on your own machine. One command starts the server, the CLI connects your warehouse, and your coding agent builds the semantic model.
Strata – an expressive semantic layer that can say no to your LLM launched on September 30, 2026 with 25 votes, #765 of 8,093 launches that month and more than 90% of that year's launches.
In plain words
Strata is a semantic layer that runs locally on your machine to connect data warehouses and generate insights. Users can get started in 15 minutes using a single command to start the server and a CLI to connect their warehouse, with a coding agent automatically building the semantic model. It runs in Docker with no configuration needed, includes a free plan without credit card requirement, and comes pre-loaded with a sample retail model for exploration.
written from the facts on this page · September 2026
From the sources
15 minutes from setup to insights. Free plan, no credit card, everything runs locally. You need Docker, Ruby 3.4.4 or newer, Git, and read access to a warehouse. A coding agent such as Claude Code or Codex does the modeling for you. Strata Server runs in Docker with its own bundled database, so there is nothing to configure. Need Docker? Get Docker Desktop . It checks Docker, pulls the image, starts the container, and waits until it is healthy. Then open http://localhost:8080 and create your admin account. Your free trial activates on its own, and a TPC-DS retail sample model is already loaded, so you can explore before connecting anything. Give it 30 to 60 seconds on first boot, then open…from strata.do
Does a similar job
all alternatives →
Mitzu2024 · mitzu.io · ▲491Ask funnel, retention, and cohort questions in plain language. Mitzu auto-builds a governed semantic layer and answers with deterministic, reviewable SQL.
ViberiaMay 2026 · getviberia.com · ▲146Hey HN, This is my take on the agent harness. Everything on an isometric map. Agents are grouped into "buildings" that run in a sequence or a loop; e.g., the CodeForge has an agent that writes a PRD, another one that implements, and a third that reviews. Everything is customizable, you build your own buildings/teams however you want. It's a Tauri app, really light (about 8x less energy than the closest competitor I benchmarked, so it actually runs from a coffee shop on battery). It's macOS only for now, but ping me if you are willing to test the Windows or Linux version. I've been…
Metabase Data StudioMar 2026 · metabase.com · ▲153Build the semantic layer that makes AI analytics trustworthy

Trilogy – A Reusable, Composable SQL Experiment2024 · trilogydata.dev · ▲78Recipe: Add a semantic layer to SQL; use it drop the requirement for joins/group_by; add in type-checking and a lightweight python-esque import syntax to enable reuse and hierarchical querying. Trilogy is intended to provide an accessible but deep alternative to raw SQL. It offers a new-but-inspired-by-SQL syntax that compiles to various dialects of SQL (with DuckDB as the default). The target audience is people that really like SQL for analytics and data engineering, but want less boilerplate and sharp edges and looser coupling to the DB. Semantic models can be easily shared, composed…
More ai this month
the category →



Paintings by AI models: programs run through a simulation of oil paint.
AI · 23d ago · stillwet.art

FastRouter.ai▲364Route requests to the right LLM for cost, latency & quality
AI · 24d ago · fastrouter.ai
Launched alongside, September 2026
the whole month →
E-ink bird frame for Raspberry Pi - real-time bird detection by audio, fully local AI, rendered as real, hand-cut 1800s bird illustrations. - arnegiacomo/fugleramme
AI · Sep 2026 · github.com
- WI
Special relativity simulator in which light crawls along at a human speed, so Lorentz contraction, aberration and Doppler shift happen at walking pace.
Life & fun · Sep 2026 · rivendell.dmitrybrant.com



Start coding agents, control sessions, review PRs. Anywhere.
Dev tools · Sep 2026 · kilo.ai
