# Lat.md

Hacker Approved page: https://hackerapproved.com/p/lat-md/

5 people recommended Lat.md in Hacker News comments, 5 had mixed feelings and 3 criticized it, November 2025 to October 2026. It was recommended in 3 of 12 months, in 2 threads. It does not meet the Hacker Approved badge rule.

4 of the 5 people who recommend it commented in one thread, “Lat.md: Agent Lattice: a knowledge graph for your codebase, written in Markdown”.

**Verdict:** Recommended as a Markdown knowledge graph that helps AI agents search code faster than grep. Main caveat: critics want proof of better performance.

Summary written by Claude from 24 comments. It was written before the November 2026 recount, and 23 of those comments still count.

## Why people recommend it

- Faster code search for agents (5 comments in the sample): "This saves agents time on grepping but also allows you to build better workflows with tests." ([source](https://news.ycombinator.com/item?id=47564440)) "Lat short-circuits grepping significantly with `lat search` that agents happily use." ([source](https://news.ycombinator.com/item?id=47564260)) "this is where lat will start saving you time - agents will navigate code much faster" ([source](https://news.ycombinator.com/item?id=47564303))
- Better test understanding and workflows (1 comment in the sample): "Lat shifts the focus from reading test code to understanding the semantics of the test." ([source](https://news.ycombinator.com/item?id=47566200))

## What people warn about

- Doesn't cover some use cases (2 comments in the sample): "It’s a start but it wouldn’t solve my uses cases." ([source](https://news.ycombinator.com/item?id=47574416)) "Only thing is it doesn't do task constraint." ([source](https://news.ycombinator.com/item?id=47602142))
- Benefits not demonstrated (2 comments in the sample): "in theory, it's cool, but can you show me that it's actually performing better" ([source](https://news.ycombinator.com/item?id=47563747)) "it wasn't clear what the material benefits of these features were" ([source](https://news.ycombinator.com/item?id=47578929))
- Messy and too big at scale (1 comment in the sample): "One file, bad (gets too big for context" ([source](https://news.ycombinator.com/item?id=47562464))

## Other code search tools people recommend

- [ripgrep](https://hackerapproved.com/p/ripgrep/): 101 recommend, 15 mixed, 16 criticize
- [ast-grep](https://hackerapproved.com/p/ast-grep/): 20 recommend, 1 mixed, 3 criticize
- [tilth](https://hackerapproved.com/p/tilth/): 8 recommend, 1 mixed, 1 criticize
- [fff.nvim](https://hackerapproved.com/p/fff-nvim/): 8 recommend, 1 mixed, 1 criticize

## The badge

A product earns the Hacker Approved badge when at least 10 people recommend it, recommenders outnumber critics at least 2 to 1 (mixed feelings count toward neither side), it was recommended in at least 4 of the 12 months and in at least 5 different threads, and no single thread supplies more than half of the people who recommend it. Health and money products are never badged.

## Cite as

Hacker Approved, "Lat.md", https://hackerapproved.com/p/lat-md/ (5 recommend, 5 mixed, 3 criticize; Hacker News comments, November 2025 to October 2026).

Counts updated 2 Nov 2026, with data through October 31, 2026.