Tôi là Duyệt

I landed 1000+ PRs this week, and this is how I use Herdr these days to achieve that.

It's been a year or two.

I am on SuperGrok Heavy because of Grok Bot and I am super impressed.

I am building AnyRouter to solve my problem of collecting free LLM tokens from everywhere and unifying the MCP Gateway.

I'm building Open Managed Agents (OMA) in the open — a self-hosted control plane on Cloudflare that drives agents on any sandbox backend from one UI and one API, and stays compatible with the Claude Managed Agents API.

I run Claude inside agent sandboxes on a home Kubernetes cluster.

You've probably heard of the agent loop by now.

Using Claude Cowork as vision planner and market research

A quick snapshot of where coding agents are in 2026: you can hand one a real, multi-part task, walk away, and come back to merged PRs, a live deploy, and a few issues it worked around on its own.

The second ultrawork run: I asked Claude Code to migrate chmonitor.dev from Next.js to TanStack Start and went to sleep.

Cloudflare's Agents SDK runs stateful TypeScript agents on Durable Objects, with Workers AI, AI Gateway, AI Search, Vectorize, Browser Run, Queues, Workflows, Email, Dynamic Workers, and Sandboxes around it.

OpenClaw, NanoBot, PicoClaw, ZeroClaw, NullClaw, NemoClaw, ...

Wrapper scripts to use Claude Code with alternative providers

Plan mode performs significantly better than just prompting directly

Lead a team of parallel agents with leader delegation to senior and junior roles

A coding agent with nice UI/UX that consolidates all your subscriptions

Build a long-running autonomous coding agent that runs 24/7

Ask clarifying questions before planning complex tasks

A collection of plugins, skills, MCPs, commands, and hooks I use for Claude Code

Reflect on what I'm thinking and doing in this LLM era

Keep your coding agent's project instructions consistent across sessions

Claude Design reads your codebase and builds a design system from your colors and typography

How I configure Claude Code - auto-compact, permissions, MCPs, and skills

Why Claude Code is still the king among coding agents I've tried

In Data Platform System with ClickHouse, rather than extracting data from ClickHouse for processing in external systems, we can perform transformations directly within ClickHouse itself.

Learn how to set up and manage ReplicatedReplacingMergeTree in ClickHouse on Kubernetes.

My favorite ClickHouse table engine is `ReplacingMergeTree`.

After starting this series ClickHouse on Kubernetes, you can now configure your first single-node ClickHouse server.

Complete guide to monitoring ClickHouse on Kubernetes.

Dynamic column selection (also known as a `COLUMNS` expression) allows you to match some columns in a result with a re2 regular expression.

Complete guide to deploying ClickHouse on Kubernetes using the Altinity ClickHouse Operator.

So, I hadn't really planned on writing a summary post for this year, as lazy as I am, but somehow, here we are.

Serialize and deserialize JSON in Rust using serde and serde_json — derive macros, field attributes, enum representations, file I/O, dynamic values, and error handling.

OpenDAL is a data access layer that allows users to easily and efficiently retrieve data from various storage services in a unified way such as S3, FTP, FS, Google Drive, HDFS, etc.

It's been years since I first started using neovim and I've been updating it regularly ever since.

In this post, I want to explore the features and capabilities of DuckDB, an open-source, in-process SQL OLAP database management system written in C++11 that has been gaining popularity recently.

How to control parallelism and concurrency

My data engineering team at Fossil recently released some of Rust-based components of our Data Platform after faced performance and maintenance challenges of the old Python codebase.

This post provides a quick and easy guide on how to run Apache Spark in GitHub Actions for testing purposes

I've been using Gatsby since 2019 and while it's great that I can write my blogs in NeoVim, commit and push to Github, and have Cloudflare Pages build and publish to CDN, but I was becoming frustrated with the slow building times and the overall maintenan…

Why does Helm Charts interpret 0777 to 511?

The field of Natural Language Processing (NLP) has seen remarkable advancements in recent years, and the emergence of the Generative Pre-trained Transformer (GPT) has revolutionized the way NLP models operate.

I asked ChatGPT to explain 20 important concepts of Apache Spark.

If you're interested in data engineering with Rust, you might want to check out Polars, a Rust DataFrame library with Pandas-like API.

This blog post will provide an overview of the data engineering tools available in Rust, their advantages and benefits, as well as a discussion on why Rust is a great choice for data engineering.

Recently, I was working on building a new Logs dashboard at Fossil to serve our internal team for log retrieval, and I found ClickHouse to be a very interesting and fast engine for this purpose.

Airflow since 2.4, in addition to scheduling DAGs based upon time, they can also be scheduled based upon a task updating a dataset.

In Rust, the question mark (?)

Since 1.64.0, Cargo now supports workspace inheritance, so you can avoid duplicating similar field values between crates while working within a workspace.

There are several scenarios when you will need to override or patch upstream dependencies.