Changkun Ou changkun

Agent harness design: trade-off analysis

An agent harness is the runtime that sits between a language model and the world — it manages the conversation loop, dispatches tool calls, enforces context and trust boundaries, persists session state, and shepherds work across failures. "Agent harness" is not a single pattern; it is a design space with several largely independent axes. Choices on one axis constrain others, and the sharpest failures in production come from the interactions rather than from any single dimension in isolation.

A harness also does not exist in isolation. It depends on — and is co-designed with — a broader ecosystem: identity and delegation systems, storage substrates, proxies and gateways, network policy enforcement, observability pipelines, evaluation infrastructure, model lifecycle tooling, supply-chain controls, policy engines and approval flows, cost and quota systems, long-term memory stores, and compliance mechanisms. A harness that wins on its internal axes but has no eval su

LLM Wiki v2

A pattern for building personal knowledge bases using LLMs. Extended with lessons from building agentmemory, a persistent memory engine for AI coding agents.

This builds on Andrej Karpathy's original LLM Wiki idea file. Everything in the original still applies. This document adds what we learned running the pattern in production: what breaks at scale, what's missing, and what separates a wiki that stays useful from one that rots.

What the original gets right

The core insight is correct: stop re-deriving, start compiling. RAG retrieves and forgets. A wiki accumulates and compounds. The three-layer architecture (raw sources, wiki, schema) works. The operations (ingest, query, lint) cover the basics. If you haven't read the original, start there.

LLM Wiki

A pattern for building personal knowledge bases using LLMs.

This is an idea file, it is designed to be copy pasted to your own LLM Agent (e.g. OpenAI Codex, Claude Code, OpenCode / Pi, or etc.). Its goal is to communicate the high level idea, but your agent will build out the specifics in collaboration with you.

The core idea

Most people's experience with LLMs and documents looks like RAG: you upload a collection of files, the LLM retrieves relevant chunks at query time, and generates an answer. This works, but the LLM is rediscovering knowledge from scratch on every question. There's no accumulation. Ask a subtle question that requires synthesizing five documents, and the LLM has to find and piece together the relevant fragments every time. Nothing is built up. NotebookLM, ChatGPT file uploads, and most RAG systems work this way.

Claude Code 配置与工作流完全指南

一、核心概念

1. Skills（技能）与 Commands（命令）

用途：预设工作流的快捷方式，可链式调用（如 /refactor-clean、/tdd、/e2e）
存储位置：
- Skills：~/.claude/skills/ — 更广泛的工作流定义
- Commands：~/.claude/commands/ — 快速执行的提示词

See also, http://libraryofalexandria.io/cgo/

Using Go `cgo`

cgo has a lot of trap.
but Not "C" pkg also directory in $GOROOT/src. IDE's(vim) Goto command not works.

So, Here collect materials.

	package main

	import (
	"runtime"
	"fmt"
	"time"
	)

	func main() {
	// Print our starting memory usage (should be around 0mb)

	You will now act as a prompt generator.
	I will describe an image to you, and you will create a prompt that could be used for image-generation.
	Once i described the image, give a 5 word summary and then include the following (markdown)
	![Image](https://image.pollinations.ai/prompt/{description}), where {description} = {sceneDetailed},%20{adjective1},%20{charactersDetailed},%20{adjective2},%20{visualStyle1},%20{visualStyle2},%20{visualStyle3},%20{genre},%20{artistReference}

	-- show running queries (pre 9.2)
	SELECT procpid, age(clock_timestamp(), query_start), usename, current_query
	FROM pg_stat_activity
	WHERE current_query != '<IDLE>' AND current_query NOT ILIKE '%pg_stat_activity%'
	ORDER BY query_start desc;

	-- show running queries (9.2)
	SELECT pid, age(clock_timestamp(), query_start), usename, query
	FROM pg_stat_activity
	WHERE query != '<IDLE>' AND query NOT ILIKE '%pg_stat_activity%'

	# post_loc.txt contains the json you want to post
	# -p means to POST it
	# -H adds an Auth header (could be Basic or Token)
	# -T sets the Content-Type
	# -c is concurrent clients
	# -n is the number of requests to run in the test

	ab -p post_loc.txt -T application/json -H 'Authorization: Token abcd1234' -c 10 -n 2000 http://example.com/api/v1/locations/