Posts on Neputer Blog

Building a Custom Agent with the Claude Agent SDK

Fri, 26 Jun 2026 00:00:00 +0000

Hands-on guide to building a custom agent with the Claude Agent SDK — define tools, wire MCP servers, and delegate to subagents, with runnable TypeScript and Python.

Claude Code with Local Models and OpenRouter: The Complete Guide

Tue, 16 Jun 2026 00:00:00 +0000

Run Anthropic's Claude Code CLI against OpenRouter, Ollama, or any custom model endpoint. Setup, model compatibility, gotchas, and a real test matrix.

AI-Assisted Development: What Actually Works in 2026

Mon, 01 Jun 2026 00:00:00 +0000

AI coding assistants have moved from novelty to necessity. But the hype cycle has settled, and we now have real data on what works and what doesn’t.

The Landscape

Tool	Best For	Limitations
GitHub Copilot	Autocomplete, boilerplate	Struggles with multi-file refactors
Cursor	Full-featured AI IDE	Context window limits on large codebases
Claude Code	Terminal-native agentic coding	Requires explicit instruction
OpenCode	Interactive CLI with subagents	Needs good task decomposition

Where AI Excels

Test Generation

AI-generated tests catch edge cases humans miss. In our codebase, AI-authored tests found 23% more boundary condition bugs than human-written equivalents:

Building a Real-Time Data Pipeline with Apache Kafka and ClickHouse

Sat, 30 May 2026 00:00:00 +0000

When your analytics queries go from “how did we do last week?” to “what’s happening right now?”, your data warehouse needs to evolve. Here’s how we built a real-time pipeline handling 500K events/second with sub-second query latency.

Architecture Overview

┌──────────┐ ┌──────────┐ ┌────────────┐ ┌──────────┐
│ Services │────▶│ Kafka │────▶│ ClickHouse │────▶│ Grafana │
│ (protobuf)│ │ (Avro) │ │ (MergeTree)│ │ Dashboards│
└──────────┘ └──────────┘ └────────────┘ └──────────┘
│
▼
┌──────────┐
│ Schema │
│ Registry │
└──────────┘

Why ClickHouse Over Traditional OLAP?

ClickHouse is a columnar database built for real-time analytics. Unlike Snowflake or BigQuery:

Rust in Production: Lessons After Two Years

Mon, 25 May 2026 00:00:00 +0000

Two years ago we rewrote a Go microservice in Rust. Here’s what we learned—the good, the ugly, and the surprising.

The Numbers

Before we get into opinions, here are the cold hard metrics comparing the Go (1.21) and Rust (1.78) versions processing 10M API requests:

Metric	Go	Rust	Delta
P99 latency	340ms	28ms	-92%
Memory (steady state)	2.1 GB	48 MB	-98%
CPU (avg)	4.2 cores	0.8 cores	-81%
Binary size	12 MB	4.8 MB	-60%
Lines of code	4,200	5,800	+38%

The latency drop isn’t just about Rust being faster—it’s about tail latency predictability. Go’s GC pauses, while short, created sporadic spikes that triggered downstream timeouts.

The Rise of Edge Computing: Why the Cloud Is Moving Closer

Wed, 20 May 2026 00:00:00 +0000

Edge computing is reshaping how we think about distributed systems. Instead of shipping every byte to a centralized data center, computation happens at the periphery—closer to where data originates.

Why Edge Computing Matters Now

Three forces are driving this shift:

5G networks provide the bandwidth and low latency edge nodes need
IoT device explosion generates terabytes of data that make no sense to transmit raw
AI inference at the edge demands real-time responses for autonomous vehicles, factory robotics, and AR applications

Architecture Patterns

Modern edge architectures typically follow a three-tier model: