Ais
32 posts
Claude Code Is Not a CLI Tool, But a 'Living' System
A deep dive into Claude Code’s underlying architecture: why it’s not a traditional CLI tool but an intelligent system running in a ‘distributed state.’ From TypeScript to Bun runtime, three-tier architecture to Feature Flags, understand the core design philosophy of this AI coding assistant.
Reverse Engineering Claude Code's API Request Signing
An in-depth reverse engineering analysis of Claude Code’s API request signing mechanism, revealing how the cch hash and xxHash64 are implemented, the secrets of Bun’s runtime, and how Anthropic protects API calls with native code.
Your AI Agent Can Think, But It Can't Remember
AI agents can reason, plan, and converse—but forget everything once the session ends. The Ghost project solves this with a pure PostgreSQL-based infrastructure, turning the database into the agent’s memory palace.
Cramming a 400B Model into 48GB: The Magic Behind LLM in a Flash
An Apple paper from 2023 made it possible to run a 400 billion parameter model on an ordinary MacBook. The core technologies—MoE and quantization—hide an engineering philosophy built around on-demand loading.
90 Seconds of Waiting, Gone: How oMLX Buries Ollama on Mac
oMLX is built for Apple Silicon, using the MLX framework, SSD-backed KV cache, and continuous batching to cut TTFT from 90 seconds to 1-3 seconds in long-context scenarios, comprehensively outperforming Ollama.
Claude Code Channels: Give Your AI Coding Assistant a Phone Number
A hands-on look at Claude Code Channels, letting you control your AI coding assistant through Telegram, Discord, and more — no matter where you are.
Don't Build a Thousand Agents: How Ramp Automates Finance with One Agent
Ramp, America’s fastest-growing enterprise finance platform valued at $32B with 50,000+ customers and $100B+ in annual transaction volume, chose a ‘one Agent + a thousand skills’ architecture over building many agents. This is a deep dive into Ramp’s AI实战经验.
AI Programming Hits the 'Review Bottleneck'? Mistral Drops an Open-Source Bomb
Mistral AI releases Leanstral, the first open-source Lean 4 code agent that lets AI both write code and prove its correctness. Let’s talk about formal verification and AI programming.
AI Agents Finally Make Literate Programming Worth Trying
Literate programming has been around for 40 years but never caught on — because maintaining parallel narratives of code and prose is exhausting. AI agents change that equation entirely.
You Use AI for Coding, But Have You Ever Used One That Holds Grudges?
When AI programming tools become goldfish - discussing the context loss pain point and how to make AI remember what you’re working on
