Eduardo Romero

Excited to announce that Lance is now a 𝗰𝗼𝗿𝗲 𝗲𝘅𝘁𝗲𝗻𝘀𝗶𝗼𝗻 of @duckdb! 🦆🚀 The Lance core extension allows DuckDB users to read and write Lance tables, enabling advanced operations directly within DuckDB, including vector similarity search, full-text search, and hybrid search across local or S3-based datasets.

Starlette 1.0 is here!🎉 After nearly eight years, Starlette has reached its first stable release. Downloaded almost 10 million times a day, it serves as the foundation for FastAPI and the Python MCP SDK. Blog post: marcelotryle.com/blog/2026/03/2… Release notes: #100-march-22-2026" target="_blank" rel="nofollow noopener">starlette.io/release-notes/…

We're excited to announce duckdb-skills, a DuckDB plugin for Claude Code! We think the embedded nature of DuckDB makes it a perfect companion for Claude in your local workflows. The skills supported include: + read-file and query – uses DuckDB's CLI to query data locally, unlocking easy access to any file that DuckDB can read. + read-memories – a clever idea to store your Claude memories in DuckDB and query them at blazing speed. These are powered by two additional skills: + attach-db – gives Claude a mechanism to manage DuckDB state through a .sql file linked to your project. + duckdb-docs – uses a remote DuckDB full-text search database to query the DuckDB docs and answer all of your (and Claude's own) questions. github.com/duckdb/duckdb-…

Prediction: Clay Christensen is best known for his theory of “Disruptive Innovation,” but the business transformations AI is forcing will eventually show that his most impactful work is his theory of “Jobs to be Done.”

Introducing the "C4 model and Structurizr DSL pattern catalog"! 📢 This pattern catalog presents a number of minimal examples of how to use the C4 model and the Structurizr DSL to model common patterns found in software architecture. Link: docs.structurizr.com/dsl/patterns/

We just open-sourced LiteParse 🎉 A lightweight, local document parser in the shape of an easy-to-use CLI. No API calls, no external service, no cloud dependency. Just fast text extraction from common file formats, right from your terminal. It's built for developers who want parsing that stays on their own infrastructure and gets out of their way. Clean PDFs, DOCX, HTML: run it, get your text, move on. The output is designed to be fed straight into agents so they can read parsed text and reason over screenshots without any extra wrangling. When you hit more complex territory like scanned docs, dense tables, or multi-column layouts, that's where LlamaParse picks up. Same philosophy, more horsepower for the hard stuff. 📖 Announcement post: llamaindex.ai/blog/liteparse… 🔗 GitHub: github.com/run-llama/lite… 🎬 Walkthrough: youtu.be/_gcqMGUWN-E

Introducing LiteParse - the best model-free document parsing tool for AI agents 💫 ✅ It’s completely open-source and free. ✅ No GPU required, will process ~500 pages in 2 seconds on commodity hardware ✅ More accurate than PyPDF, PyMuPDF, Markdown. Also way more readable - see below for how we parse tables!! ✅ Supports 50+ file formats, from PDFs to Office docs to images ✅ Is designed to plug and play with Claude Code, OpenClaw, and any other AI agent with a one-line skills install. Supports native screenshotting capabilities. We spent years building up LlamaParse by orchestrating state-of-the-art VLMs over the most complex documents. Along the way we realized that you could get quite far on most docs through fast and cheap text parsing. Take a look at the video below. For really complex tables within PDFs, we output them in a spatial grid that’s both AI and human-interpretable. Any other free/light parser light PyPDF will destroy the representation of this table and output a sequential list. This is not a replacement for a VLM-based OCR tool (it requires 0 GPUs and doesn’t use models), but it is shocking how good it is to parse most documents. Huge shoutout to @LoganMarkewich and @itsclelia for all the work here. Come check it out: llamaindex.ai/blog/liteparse… Repo: github.com/run-llama/lite…

We've entered into an agreement to join OpenAI as part of the Codex team. I'm incredibly proud of the work we've done so far, incredibly grateful to everyone that's supported us, and incredibly excited to keep building tools that make programming feel different.

Rippling launched its AI analyst today. I'm not just the CEO - I'm also the Rippling admin for our co, and I run payroll for our ~ 5K global employees. Here are 5 specific ways Rippling AI has changed my job, and why I believe this is the future of G&A software. 🧵 1/n

We benchmarked TanStack Start, React Router, and Next.js running the exact same eCommerce app at 1,000 req/s on AWS EKS. The results were eye-opening.

.@nodejs has always been about I/O. Streams, buffers, sockets, files. But there's a gap that has bugged me for years: you can't virtualize the filesystem. You can't import a module that only exists in memory. You can't bundle assets into a Single Executable without patching half the standard library. That changes now 👇

We doubled Claude usage on weekends, and outside 5–11am PT on weekdays for the next 2 weeks.

“Hollow Knight Symphonic Orchestra Concert” announced! A full orchestra concert featuring the music of “Hollow Knight” and “Hollow Knight: Silksong.” Featuring vocalist: Amelia Jones @ameliajvocals 📍Yokohama & Osaka, Japan June 2026 Day concert “Hollow Knight” Evening concert “Hollow Knight: Silksong” Official website hollowknightconcert2026.com Ticket application for overseas visiters will start in April. Stay tuned!

json-render now supports YAML as a wire format JSONL needs a full element before rendering YAML is valid at every prefix, going from element-level to property-level 💨 YAML looks like source code to LLMs And we use 3 standards they know: JSON Patch, Merge Patch, Unified diff

We've released Python Polars 1.39. Some of the highlights: • Streaming AsOf join join_asof() is now supported in the streaming engine, enabling memory-efficient time-series joins. • sink_iceberg() for writing to Iceberg tables A new LazyFrame sink that writes directly to Apache Iceberg tables. Combined with the existing scan_iceberg(), Polars now supports full read/write workflows for Iceberg-based data lakehouses. • Streaming cloud downloads scan_csv(), scan_ndjson(), and scan_lines() can now stream data directly from cloud storage instead of downloading the full file first. Link to the complete changelog: github.com/pola-rs/polars…

My own reflections when I realized AI is good enough to write all my code in January of this year (and many experienced engineers came to the same realization) And what this means for the industry - amusingly, there could be more demand for devs! newsletter.pragmaticengineer.com/p/when-ai-writ…

@jpabluz Brave new world when you live in the bleeding edge 😂

@foxteck Lol, so we are going to see bot vs bot PR fights? Excited for this timeline.

Claude's definitely NOT into Jules: ⏺ Jules did it again. You'll probably want to disable Jules on this PR — it keeps pushing "acknowledge PR comments" commits that silently revert your changes. It's done it 3 times now.

Meet KARL: a faster agent for enterprise knowledge, powered by custom reinforcement learning (now in preview). Enterprise knowledge work isn’t just Q&A. Agents need to search for documents, find facts, cross-reference information, and reason over dozens or hundreds of steps. KARL (Knowledge Agent via Reinforcement Learning) was built to handle this full spectrum of grounded reasoning tasks. The result: frontier-level performance on complex knowledge workloads at a fraction of the cost and latency of leading proprietary models. These advances are already making their way into Agent Bricks, improving how knowledge agents reason over enterprise data. And Databricks customers can apply the same reinforcement learning techniques used to train KARL to build custom agents for their own enterprise use cases. Read the research → databricks.com/sites/default/… Blog: databricks.com/blog/meet-karl…