# LLM wiki

*Also known as: agent knowledge base*

A knowledge base written for a language model: plain markdown entity pages linked with [[wiki-links]] that an agent builds and maintains, so knowledge compounds. Lighter than RAG.

- In depth: Give your trading agent an LLM wiki (https://tradingagent.dev/#guide-wiki)

An LLM wiki, a term popularized by Andrej Karpathy, is a set of markdown entity pages written for a model rather than a person, linked with [[wiki-links]] so they form a connected graph. An agent reads it directly and folds in new sources over time, so what it learns compounds instead of evaporating between sessions.

This site is built in that shape: every entry is an entity page, every cross-reference is a [[wiki-links|wiki link]], and each page is available as raw markdown for a model to read. For a trading agent, the same pattern can hold its strategies, markets, and [[backtesting|backtest]] results.

## Related

- [[loop-engineering]] (/wiki/loop-engineering.md)
- [[tradingagents]] (/wiki/tradingagents.md)

## Linked from

- [[loop-engineering]] (/wiki/loop-engineering.md)
- [[superior-trade]] (/wiki/superior-trade.md)
- [[tradingagents]] (/wiki/tradingagents.md)

## Categories

Concepts

## References

- Karpathy: llm-wiki gist: https://gist.github.com/karpathy/442a6bf555914893e9891c11519de94f