Author

Architecture Digest

Focusing on Java backend development, covering application architecture from top-tier internet companies (high availability, high performance, high stability), big data, machine learning, Java architecture, and other popular fields.

2.4k

Articles

Likes

13.6k

Views

Comments

Latest from Architecture Digest

100 recent articles max

Architecture Digest

Sep 21, 2026 · Artificial Intelligence

3 AI Open-Source Projects: DeepSeek Agent Runtime, Verified Diagrams, 744B MoE on 25GB RAM

This article reviews three cutting-edge AI open-source projects: DeepSeek's plugin-based Agent runtime framework (deepseek-harness), archify for generating verifiable architecture diagrams directly in coding agents, and colibri, a pure C inference engine enabling 744B MoE models to run on 25GB RAM via disk streaming.

DeepSeekMoEPure C

0 likes · 8 min read

3 AI Open-Source Projects: DeepSeek Agent Runtime, Verified Diagrams, 744B MoE on 25GB RAM

Architecture Digest

Sep 20, 2026 · Artificial Intelligence

BrowserSkill: AI Agents Borrow Your Logged-In Browser Without Test Accounts

Tencent's open-source BrowserSkill lets AI agents like Cursor and Claude Code operate within your authenticated Chrome or Edge window, inheriting login state, borrowing tabs via explicit leases, and handing off CAPTCHAs to humans, all through a local daemon and browser extension with no external servers.

AI AgentsBrowserSkillCLI

0 likes · 8 min read

BrowserSkill: AI Agents Borrow Your Logged-In Browser Without Test Accounts

Architecture Digest

Sep 19, 2026 · Artificial Intelligence

Alibaba's Open Code Review: Deterministic Pipelines Slash Token Costs 9x

Alibaba open-sourced Open Code Review, an AI code review tool used internally for two years, which combines a deterministic rule engine for file selection and line positioning with LLMs for judgment only, achieving higher precision and 9x lower token consumption than Claude Code on a benchmark of 200 real PRs.

AACR-BenchAI code reviewAlibaba

0 likes · 8 min read

Alibaba's Open Code Review: Deterministic Pipelines Slash Token Costs 9x

Architecture Digest

Sep 18, 2026 · Backend Development

LangChain4j: Java-Native LLM Integration with Unified API, RAG, and Agents

LangChain4j provides a Java-native framework for integrating 20+ LLM providers and 30+ vector stores via a unified API, declarative AiServices, RAG pipelines, tool calling, and MCP support, enabling Spring Boot teams to add AI capabilities without Python dependencies.

AI servicesJavaLLM Integration

0 likes · 9 min read

LangChain4j: Java-Native LLM Integration with Unified API, RAG, and Agents

Architecture Digest

Sep 17, 2026 · Backend Development

Graphify: One-Click Code Architecture Graphs for Legacy Java & Microservices

Graphify uses tree-sitter AST parsing to generate queryable code knowledge graphs with confidence-labeled edges, community detection, and God node identification, enabling offline architecture governance for legacy Java and microservices without vector databases or LLM tokens.

AST parsingGraphifyJava

0 likes · 10 min read

Graphify: One-Click Code Architecture Graphs for Legacy Java & Microservices

Architecture Digest

Sep 16, 2026 · Artificial Intelligence

Superpowers: Forcing AI Coding Agents to Write Testable Code via TDD & Sub-Agents

Superpowers is an open-source skill library that injects mandatory TDD, sub-agent delegation, and two-phase code review into AI coding agents like Claude Code and Cursor, preventing 'works-on-my-machine' code by enforcing engineering discipline through workflow hooks rather than model upgrades.

AI coding agentsClaude CodeCursor

0 likes · 10 min read

Superpowers: Forcing AI Coding Agents to Write Testable Code via TDD & Sub-Agents

Architecture Digest

Sep 15, 2026 · Artificial Intelligence

Running 744B GLM-5.2 on 25GB RAM: colibri's Disk-Streaming MoE Inference Engine

colibri, a zero-dependency C inference engine, runs Zhipu's 744B-parameter GLM-5.2 MoE model on a 25GB RAM laptop by keeping dense weights in memory and streaming routed experts from NVMe, achieving ~1 token/s after cache warm-up with router-lookahead prefetching and learned caching.

AVX2CPU inferenceColibri

0 likes · 11 min read

Running 744B GLM-5.2 on 25GB RAM: colibri's Disk-Streaming MoE Inference Engine

Architecture Digest

Sep 14, 2026 · Artificial Intelligence

Microsoft's markitdown: One-Command RAG Document Preprocessing & Java Integration

Microsoft's open-source markitdown tool (18k GitHub stars) converts PDFs, Office files, and more into clean Markdown for RAG knowledge bases, preserving tables and structure; the article covers CLI/Python batch processing, three Java backend integration patterns (CLI, Docker service, MCP), security considerations, and comparisons with Tika and pdfplumber.

Java integrationLLM knowledge baseMarkdown conversion

0 likes · 9 min read

Microsoft's markitdown: One-Command RAG Document Preprocessing & Java Integration

Architecture Digest

Sep 13, 2026 · Artificial Intelligence

Running 2.78T-Parameter Kimi K3 on 8GB RAM: Pure C Inference Engine Explained

A pure C inference engine runs the 2.78 trillion parameter Kimi K3 model on just 8GB RAM by streaming weights from disk, leveraging MoE sparsity (only 3.7% active per token) and computing directly on compressed formats, achieving correct output at 32.69 seconds per token on consumer hardware.

BenchmarkingC languageKimi K3

0 likes · 11 min read

Running 2.78T-Parameter Kimi K3 on 8GB RAM: Pure C Inference Engine Explained

Architecture Digest

Sep 12, 2026 · Artificial Intelligence

CrewAI: 57k-Star Multi-Agent Framework for Complex Task Automation

CrewAI is a 57k-star open-source multi-agent framework that orchestrates role-based AI agents (researcher, writer, reviewer) via sequential or hierarchical processes, adds tooling, memory, human-in-the-loop, observability, and introduces Flows for deterministic control alongside autonomous Crews.

AI AgentsCrewAIFlows

0 likes · 14 min read