Guides for production LLM systems

Implementation patterns, technical comparisons, and decision rules for engineers building with language models and agents.

All guides

A long token stream splitting into full-length and bounded rolling cache paths

·LLM Infrastructure

Sliding-Window Prefix Caches Need Physical Proof

Hybrid attention turns prefix caching into a memory-consistency problem across KV pools with different lifetimes.

Branching speculative paths meeting a luminous commit boundary

·AI Agents

Speculative Agents Need a Commit Boundary

Speculative execution cuts agent latency only when prediction and commitment are separate operations.

Abstract interlocking loops for harness engineering

·AI Agents

Loop / Harness Engineering

Agent loops turn prompts into one part of a production harness: tools, state, checks, approvals, and exit conditions.

Plain-Text Context Files for LLMs

·AI Agents

Plain-Text Context Files for LLMs

Plain-text context files are the git-native, zero-ops way to steer AI agents.

How to Build an MCP Server

·AI Agents

How to Build an MCP Server

A guide to building an MCP server for Markdown note taking

Structuring tools for AI Agents

·AI Agents

Structuring tools for AI Agents

A short conceptual guide to organising tools in agentic workflows

The Modern Document Processing Stack

·LLM Infrastructure

The Modern Document Processing Stack

A simple engine for converting any file type to Markdown.

Decoding Methods for LLMs

·LLM Infrastructure

Decoding Methods for LLMs

A verbose explanation of common auto-regressive decoding methods: temperature, top k and top p.

Structured Generation Shoot-out

·Structured Generation

Structured Generation Shoot-out

A comparison of some of the most popular libraries that constrain LLM generation.

Compare open-source AI frameworks

Filter projects by language, age, funding, size, and GitHub stars.

Open the leaderboard