Skip to content
Tech News
← Back to articles

Show HN: 10x better performance from the Coding Harnesses with LLM-wiki

read original more articles
Why This Matters

This article introduces a modular and isolated wiki system designed to enhance research and knowledge management using large language models (LLMs). By organizing content into distinct topics, sources, and archives, it improves data integrity, traceability, and performance, offering a scalable solution for complex information ecosystems. This approach can significantly benefit the tech industry by enabling more efficient, accurate, and secure knowledge workflows for developers and researchers.

Key Takeaways

The hub ( ~/wiki/ ) is just a registry. No content — only wikis.json , _index.md , and log.md . All content lives in topic sub-wikis.

Topic wikis ( ~/wiki/topics/<name>/ ) are isolated research areas. Each has its own sources, articles, outputs, and Obsidian vault config. Isolation means researching quantum computing can't pollute your nutrition wiki.

Raw sources ( raw/ ) are immutable. Once a paper, article, or data file is ingested, it's never modified. This is the audit trail — every claim in every article traces back to a source.

Wiki articles ( wiki/ ) are LLM-compiled syntheses organized into three categories:

Concepts — foundational ideas, mechanisms, theories

— foundational ideas, mechanisms, theories Topics — specific subjects, comparisons, state-of-the-field

— specific subjects, comparisons, state-of-the-field References — tools, frameworks, data tables, lookup resources

Archive ( topics/.archive/ ) is for whole topic wikis the user no longer wants in normal context. It preserves source history, articles, outputs, and logs while keeping old interests quiet by default.

Sessions ( HUB/.sessions/ ) are operational memory for redacted harness checkpoints, compact digests, rehydration indexes, and feedback candidates. They are not compiled as topic evidence unless explicitly promoted into raw/notes/ .

Inventory ( inventory/ ) is for durable operational state: actual items, source candidates, corpora, entities, open questions, tasks, watch items, and next actions. It is intentionally not evidence for factual claims.

... continue reading