Author

Code Archaeology

Learn from the past to understand the present

Articles

Likes

Views

Comments

Latest from Code Archaeology

67 recent articles

Code Archaeology

Feb 2, 2026 · Artificial Intelligence

Manus's $2B Agent Architecture: Context Engineering Strategies Revealed

The article analyzes the planning-with-files technique — three Markdown files for task planning, knowledge storage, and state tracking — and its alignment with Manus's context engineering strategies (reduce, offload, isolate context), while detailing Manus's tech stack including multi-model routing, E2B sandbox, MCP protocol, and KV cache optimization.

AI agentsE2B sandboxKV cache

0 likes · 11 min read

Manus's $2B Agent Architecture: Context Engineering Strategies Revealed

Code Archaeology

Jan 26, 2026 · Artificial Intelligence

OpenAI vs Anthropic Tool Calling APIs: Conversation vs Execution Trajectory Abstractions Compared

This article compares OpenAI's Chat Completions and Responses APIs with Anthropic's Messages API for tool calling, detailing request/response structures, abstraction differences between conversation and execution trajectory models, and Anthropic's advanced features including tool search, programmatic tool calling, and tool use examples for large-scale agent systems.

API designAnthropicChat Completions

0 likes · 19 min read

OpenAI vs Anthropic Tool Calling APIs: Conversation vs Execution Trajectory Abstractions Compared

Code Archaeology

Jan 19, 2026 · Artificial Intelligence

LLM Inference Optimization: Metrics, Model & Service Techniques

This article systematically covers LLM inference optimization across performance metrics (TTFT, TPOT, throughput, goodput, MFU, MBU), model-level techniques (quantization, distillation, pruning, speculative decoding, attention optimizations), and service-level strategies (continuous batching, prefill/decode separation, prompt caching, parallelism) to improve latency, throughput, and cost-efficiency.

KV cacheLLM inferenceTPOT

0 likes · 14 min read

LLM Inference Optimization: Metrics, Model & Service Techniques

Code Archaeology

Jan 5, 2026 · Backend Development

Netty 4.2 io_uring Configuration Options Reference

This article summarizes Netty 4.2's io_uring configuration options across system properties, IoUringIoHandlerConfig, and ChannelOptions, covering kernel requirements, ring sizing, multishot accept/recv, buffer rings, zero-copy writes, and common socket options for high-performance Linux networking.

Linux kernelNettybuffer ring

0 likes · 11 min read

Netty 4.2 io_uring Configuration Options Reference

Code Archaeology

Dec 30, 2025 · Artificial Intelligence

LLM Agent Fundamentals: ReAct Reasoning-Action Loop & Tool Calling Evolution

This article introduces the ReAct paradigm for LLM-based agents, detailing its reasoning-action-observation loop with a hands-on example, and traces the evolution of tool-use from prompt-defined tools to trained models like Toolformer and standardized APIs like OpenAI Function Calling.

AI engineeringAgent ParadigmChain of Thought

0 likes · 14 min read

LLM Agent Fundamentals: ReAct Reasoning-Action Loop & Tool Calling Evolution

Code Archaeology

Dec 22, 2025 · Artificial Intelligence

RAG Explained: Core Concepts, Architecture, and a Minimal LangChain Demo

This article introduces Retrieval-Augmented Generation (RAG), covering its origins, core components (retriever and generator), advantages like reduced hallucination and knowledge updatability, architectural challenges such as chunk sizing and vector search algorithms, and provides a step-by-step LangChain implementation using FAISS, SentenceTransformer, and DeepSeek.

FAISSKnowledge RetrievalLLM Engineering

0 likes · 15 min read

RAG Explained: Core Concepts, Architecture, and a Minimal LangChain Demo

Code Archaeology

Dec 9, 2025 · Backend Development

Inside Netty 4.2's AdaptiveByteBufAllocator: Stripe-Based Allocation & Lock-Free Strategies

This article dissects Netty 4.2's AdaptivePoolingAllocator memory allocation flow, covering request size routing, MagazineGroup's stripe mechanism with dynamic expansion, and Magazine's tryAllocate implementation with locked and lock-free paths using NEXT_IN_LINE for concurrency safety.

AdaptiveByteBufAllocatorChunkControllerMagazineGroup

0 likes · 13 min read

Inside Netty 4.2's AdaptiveByteBufAllocator: Stripe-Based Allocation & Lock-Free Strategies

Code Archaeology

Nov 28, 2025 · Backend Development

Netty 4.2 AdaptiveByteBufAllocator: MagazineGroup, Magazine & Chunk Internals

The article details the data structures behind Netty 4.2's AdaptiveByteBufAllocator, explaining how MagazineGroup, Magazine, and Chunk collaborate to manage memory pools, handle thread-local and shared allocation, and use size-classed chunks with free lists for efficient buffer pooling.

AdaptiveByteBufAllocatorByteBufChunk

0 likes · 6 min read

Netty 4.2 AdaptiveByteBufAllocator: MagazineGroup, Magazine & Chunk Internals

Code Archaeology

Nov 21, 2025 · Operations

AWS US-EAST-1 Outage: DynamoDB DNS Race Condition Triggers EC2 Congestion Collapse

This analysis of the October 2025 AWS US-EAST-1 outage details how a race condition in DynamoDB's automated DNS management system caused DNS resolution failures, triggering a 12-hour EC2 congestion collapse due to lease backlog and an NLB health-check failover driven by stale network configuration.

AWSDNSDynamoDB

0 likes · 11 min read

AWS US-EAST-1 Outage: DynamoDB DNS Race Condition Triggers EC2 Congestion Collapse

Code Archaeology

Nov 14, 2025 · Backend Development

Netty 4.2 IoUring Zero-Copy Send: Two CQEs Explained

This article explains how Netty 4.2 leverages Linux io_uring's zero-copy send (IORING_OP_SEND_ZC) to avoid user-kernel data copies, detailing the two completion queue events (CQEs) — I/O completion and buffer release notification — and Netty's handling logic with code examples.

CQEJavaLinux kernel

0 likes · 10 min read

Netty 4.2 IoUring Zero-Copy Send: Two CQEs Explained