Author

Shuge Unlimited

Formerly "Ops with Skill", now officially upgraded. Fully dedicated to AI, we share both the why (fundamental insights) and the how (practical implementation). From technical operations to breakthrough thinking, we help you understand AI's transformation and master the core abilities needed to shape the future. ShugeX: boundless exploration, skillful execution.

Articles

Likes

Views

Comments

Latest from Shuge Unlimited

82 recent articles

Shuge Unlimited

Apr 30, 2026 · Databases

Milvus VTS Deep Dive: Two Write Modes, Sharding, and Migration Best Practices

The article provides a source‑code level analysis of Milvus Vector Transport Service (VTS), detailing its three‑stage architecture, partition‑aware sharding logic, two distinct sink write mechanisms (BufferBatchWriter and BulkWriter), schema conversion rules, error‑handling strategies, performance tuning parameters, and practical configuration examples for efficient vector data migration across various data sources.

BufferBatchWriterBulkWriterMilvus

0 likes · 20 min read

Milvus VTS Deep Dive: Two Write Modes, Sharding, and Migration Best Practices

Shuge Unlimited

Apr 29, 2026 · Databases

Milvus Storage Tuning in Practice: 25× Query Speedup and Three Tricks to Cut Memory Usage by Half

This article walks through Milvus 2.3‑2.6.x storage optimizations—Mmap, tiered storage, and clustering compaction—explaining their principles, configuration hierarchy, benchmark results, and concrete deployment templates that together can boost query performance up to 25‑fold while halving memory consumption.

MilvusPerformance tuningStorage Optimization

0 likes · 24 min read

Milvus Storage Tuning in Practice: 25× Query Speedup and Three Tricks to Cut Memory Usage by Half

Shuge Unlimited

Apr 27, 2026 · Operations

OpenSpec Advanced: From Core to Expanded – Unlock All Workflows with 7 Commands

This article explains how OpenSpec's Expanded Workflow adds seven new commands to the core profile, providing finer‑grained artifact control, implementation verification, parallel change management, and customizable schemas, and shows when to use fast‑forward versus stepwise execution along with best‑practice recommendations.

AI developmentCLI CommandsDevOps

0 likes · 26 min read

OpenSpec Advanced: From Core to Expanded – Unlock All Workflows with 7 Commands

Shuge Unlimited

Apr 26, 2026 · Artificial Intelligence

OpenSpec Hands‑On: 3 Commands, 4 Artifacts, 4‑Step Closed Loop for Incremental Feature Development

This tutorial walks through adding a priority field to an existing todo‑API using OpenSpec’s incremental workflow—proposing the change with /opsx:propose, reviewing the generated Delta Specs, applying the code with /opsx:apply, and archiving the change with /opsx:archive—while illustrating ADDED and MODIFIED specifications, code updates, testing, and best‑practice tips.

AI programmingCLIDelta specs

0 likes · 23 min read

OpenSpec Hands‑On: 3 Commands, 4 Artifacts, 4‑Step Closed Loop for Incremental Feature Development

Shuge Unlimited

Apr 25, 2026 · Artificial Intelligence

DeepSeek V4: Comeback? 1.6 T Params, Million‑Token Context, Open‑Source Matches Closed‑Source

DeepSeek V4, released shortly after GPT‑5.5, offers two models—V4‑Pro (1.6 T parameters) and V4‑Flash (284 B parameters)—that introduce a hybrid CSA/HCA attention architecture to enable efficient million‑token context, achieve dramatic FLOPs and KV savings, deliver competitive programming and agent benchmarks, and adopt a disruptive pricing strategy, while also exposing training‑stability tricks and highlighting both strengths and remaining gaps.

DeepSeek V4Hybrid AttentionLLM

0 likes · 25 min read

DeepSeek V4: Comeback? 1.6 T Params, Million‑Token Context, Open‑Source Matches Closed‑Source

Shuge Unlimited

Apr 23, 2026 · Artificial Intelligence

Deep Dive into Hermes Agent: Self‑Improving AI Agent Architecture with 110K+ Stars

Hermes Agent, an open‑source self‑improving AI agent framework that has amassed over 110 K GitHub stars, introduces a native closed‑learning loop, a unified single‑process agent cycle, self‑registering tools, pluggable context compression, multi‑API model support, and a scalable multi‑platform gateway, all built on Python 3.11+, SQLite + WAL, and extensive modular design.

AI agentClosed Loop LearningContext Compression

0 likes · 24 min read

Deep Dive into Hermes Agent: Self‑Improving AI Agent Architecture with 110K+ Stars

Shuge Unlimited

Apr 18, 2026 · Artificial Intelligence

From Legacy Coding to AI‑Assisted Development: A Hands‑On Guide to Using Superpowers and OpenSpec

The article presents a step‑by‑step AI‑enhanced workflow for modernising legacy systems, explaining how OpenSpec’s spec‑driven requirement layer and Superpowers’ strict execution pipeline (brainstorming, isolated worktrees, TDD, code review) together resolve inaccurate demand understanding and uncontrolled code generation, with a concrete flash‑sale implementation and practical pitfalls.

AI codingOpenSpecSpec-Driven Development

0 likes · 20 min read

From Legacy Coding to AI‑Assisted Development: A Hands‑On Guide to Using Superpowers and OpenSpec

Shuge Unlimited

Apr 17, 2026 · Artificial Intelligence

From 6.7% to 68.3%: How Harness Engineering’s Six Pillars Reshape AI Agent Development

The article shows that swapping only the harness around a fixed model can boost performance from 6.7% to 68.3%, then details a six‑layer harness architecture, context‑usage thresholds, entropy management, code‑level constraints, and practical roadmaps drawn from real‑world AI agent teams.

AI agentsArchitecture ConstraintsContext Management

0 likes · 24 min read

From 6.7% to 68.3%: How Harness Engineering’s Six Pillars Reshape AI Agent Development

Shuge Unlimited

Apr 16, 2026 · Artificial Intelligence

Hermes Agent vs Evolver: A Source‑Level Technical Investigation

The article conducts a source‑level technical investigation of the Hermes Agent and Evolver frameworks, comparing their architectures, naming conventions, core algorithms, configuration designs, Git timelines, documentation, and public evidence to assess whether the observed similarities indicate independent development or possible code reuse.

AI agentEvolverGEP

0 likes · 26 min read

Hermes Agent vs Evolver: A Source‑Level Technical Investigation

Shuge Unlimited

Apr 14, 2026 · Backend Development

Mastering SKU Inventory Deduction with Superpowers: A 7‑Stage Workflow

This article walks through a complete 7‑stage Superpowers workflow—brainstorming, isolated git worktrees, fine‑grained task planning, sub‑agent execution with two‑stage reviews, strict test‑driven development, global code review, and final branch finishing—using Python 3.11, FastAPI, SQLAlchemy and Pytest to implement robust SKU inventory deduction in an e‑commerce system.

AI programmingFastAPIGit worktrees

0 likes · 20 min read

Mastering SKU Inventory Deduction with Superpowers: A 7‑Stage Workflow