The Builder

Describe a dashboard in plain English. Get one that actually works.

“I replaced two hours of weekly reporting work in fifteen minutes. The SQL generation is accurate enough that I don't second-guess it anymore, and the Slack bot means non-technical stakeholders ask it directly instead of pinging me for queries.”

Composable data skills so your AI agents always understand your business

“The MCP integration is smart — this plays well with Claude and other agentic tools that already know the MCP protocol. Auto-discovering your schema and creating Skills is the right default UX for a tool like this.”

Write a chart the same way you write a SQL query — from Hadley Wickham

“The Hadley Wickham signal alone is worth paying attention to. Grammar of graphics in SQL is the obvious next step for data stack tools, and having the person who invented ggplot2 leading the effort means the underlying design will be coherent, not bolted-on. Even in alpha, this is worth integrating into a Quarto workflow.”

GPU-accelerated OCR server hitting 1,200 pages/sec with TensorRT and PP-OCRv5

“1,200 images per second with 11ms latency on an RTX 5090, Docker-first deployment, HTTP and gRPC — this is production-grade OCR infrastructure, not a weekend project. PP-OCRv5 + TensorRT FP16 with 90.2% F1 on FUNSD is competitive with everything I've benchmarked. The layout detection that identifies 25 region classes (headers, tables, figures) is what puts it over the top for document processing pipelines.”

Natural language to live investing dashboards — backtests, macro, and models in seconds

“Natural language to working financial dashboards with real data is a workflow most analysts spend days setting up. If the data sources are solid and the backtest logic is sound, this is legitimately useful. The free tier makes it easy to evaluate before committing.”

Open-source autonomous BI agent that pulls data, builds dashboards, and takes action

“The multi-layer memory is the real innovation here — most BI agents forget everything between sessions, which means you're constantly re-explaining business context. Anton's episodic layer means it learns your data model once and applies it forever. AGPL might be a dealbreaker for some commercial use cases, but for internal tooling it's gold.”

Open-source data catalog that ships as a single binary — with MCP built in.

“Single binary, MIT license, MCP server built in — this is how OSS infrastructure tools should ship. I had it running against our Postgres and dbt setup in 20 minutes. The lineage graph actually works, which is more than I can say for most 'enterprise' catalogs I've paid for.”

Open-source AI agent that reasons, queries, charts, and acts on your data

“The three-tier memory model is the right architecture for enterprise BI — session, semantic, and long-term memory means it actually remembers your data model across projects. The AGPL license keeps it open while the cloud option gives MindsDB a business model. Self-hostable agentic BI is a real category.”

Google's 200M-param foundation model for time-series forecasting, now open-source

“Zero-shot forecasting across domains with quantile outputs and 16k context is legitimately the most useful time-series tooling I've seen released as open-source. The PyTorch + JAX dual support means I can use it in any existing ML stack. Replacing a bespoke ARIMA/Prophet pipeline with a pip install is a huge win for data teams.”

Google's zero-shot time series forecasting model, now with 16k context

“Zero-shot forecasting that competes with supervised models trained specifically on your dataset is remarkable. The BigQuery ML integration makes this accessible to data teams without ML infrastructure. 16k context is enough for 13+ years of daily data.”