Lat.md
Ranked 5 of 15 code search tools by recommenders
Recommended as a Markdown knowledge graph that helps AI agents search code faster than grep. Main caveat: critics want proof of better performance.
Recommended as a Markdown knowledge graph that helps AI agents search code faster than grep. Main caveat: critics want proof of better performance.
14 people gave an opinion
- recommend it
- 11
- criticize it
- 3
- approval share
- 79%
Recommended in 3 of 13 months
- November 2025: not recommended
- December 2025: not recommended
- January 2026: not recommended
- February 2026: not recommended
- March 2026: recommended
- April 2026: recommended
- May 2026: not recommended
- June 2026: not recommended
- July 2026: not recommended
- August 2026: not recommended
- September 2026: recommended
- October 2026: not recommended
- November 2026: not recommended (month in progress)
Why it doesn’t carry the badge
- 11 people recommend itNeeds 10 or more, met.
- 3.7 recommenders for every criticNeeds 2 to 1 or better, met.
- Recommended in 3 of 13 monthsNeeds 4 or more, not met.
The same three rules apply to every product, and the badge can’t be bought. How the badge works
What people say about it
The reasons people give, with the number of comments that give each one. Open a reason to read what they said.
Why people recommend it
Each mark is one comment
Faster code search for agents
“This saves agents time on grepping but also allows you to build better workflows with tests.”
Comment from 29 Mar 2026 in “Lat.md: Agent Lattice: a knowledge graph for your codebase, written in Markdown” “Lat short-circuits grepping significantly with `lat search` that agents happily use.”
Comment from 29 Mar 2026 in “Lat.md: Agent Lattice: a knowledge graph for your codebase, written in Markdown” “this is where lat will start saving you time - agents will navigate code much faster”
Comment from 29 Mar 2026 in “Lat.md: Agent Lattice: a knowledge graph for your codebase, written in Markdown” - Comment from 30 Mar 2026 in “Lat.md: Agent Lattice: a knowledge graph for your codebase, written in Markdown”
- Comment from 29 Mar 2026 in “Lat.md: Agent Lattice: a knowledge graph for your codebase, written in Markdown”
Better test understanding and workflows
“This saves agents time on grepping but also allows you to build better workflows with tests.”
Comment from 29 Mar 2026 in “Lat.md: Agent Lattice: a knowledge graph for your codebase, written in Markdown” “Lat shifts the focus from reading test code to understanding the semantics of the test.”
Comment from 29 Mar 2026 in “Lat.md: Agent Lattice: a knowledge graph for your codebase, written in Markdown”
What people warn about
Each mark is one comment
Doesn't cover some use cases
“It’s a start but it wouldn’t solve my uses cases.”
Comment from 30 Mar 2026 in “Lat.md: Agent Lattice: a knowledge graph for your codebase, written in Markdown” “Only thing is it doesn't do task constraint.”
Comment from 1 Apr 2026 in “Claude Code Unpacked : A visual guide” Benefits not demonstrated
“in theory, it's cool, but can you show me that it's actually performing better”
Comment from 29 Mar 2026 in “Lat.md: Agent Lattice: a knowledge graph for your codebase, written in Markdown” “it wasn't clear what the material benefits of these features were”
Comment from 30 Mar 2026 in “Lat.md: Agent Lattice: a knowledge graph for your codebase, written in Markdown” Messy and too big at scale
“My concern is scale though. Once you have thousands of nodes the Markdown files themselves become a mess to navigate”
Comment from 29 Mar 2026 in “Lat.md: Agent Lattice: a knowledge graph for your codebase, written in Markdown” “One file, bad (gets too big for context)”
Comment from 29 Mar 2026 in “Lat.md: Agent Lattice: a knowledge graph for your codebase, written in Markdown”
Other code search tools people recommend
The four most recommended other code search tools, with the same counts for each, so you can compare like for like. The tick on each bar marks the 2 to 1 line the badge needs.
| Product | Recommend | Criticize | Approval | Months | Owned | Badge |
|---|---|---|---|---|---|---|
| ripgrep | 122 | 18 | 87% | 12 | — | Approved |
| ast-grep | 21 | 3 | 88% | 9 | — | Approved |
| Semble | 20 | 7 | 74% | 4 | — | Approved |
| Graft (Claude Code hooks) | 13 | 4 | 76% | 4 | — | Approved |
| Lat.mdThis page | 11 | 3 | 79% | 3 | — | — |
What people said
24 of the 25 comments that mention it, newest first. Each links to the original comment.
“For me it strikes the right balance between structure and flexibility.”
“it replaced manual work I was already doing, more reliably than I was doing it.”
“Markdown is still just text an LLM can hallucinate over or ignore.”
“Only thing is it doesn't do task constraint.”
“it wasn't clear what the material benefits of these features were”
“It’s a start but it wouldn’t solve my uses cases.”
“gives agent tools to search and traverse the graph, better than they can with grep”
“seems like it could be useful to cross-reference company-wide projects”
“Lat shifts the focus from reading test code to understanding the semantics of the test.”
“lat focuses on both public and private impl detail”
“imo that's still too hand-wavy compared to enforcement through generative tests”
“was able to get an answer in 12 seconds vs 2 minutes without lat”
“I can see sometimes lat allowing for up to 2x faster coding sessions.”
“it might make it even nicer”
“I think it's a great idea and I'm considering building this in lat too.”
“This saves agents time on grepping but also allows you to build better workflows with tests.”
“this is where lat will start saving you time - agents will navigate code much faster”
“Lat short-circuits grepping significantly with `lat search` that agents happily use.”
“Yes, it does work and I continue improving it.”
“in theory, it's cool, but can you show me that it's actually performing better”
“It's a useful idea: the agents.md torrent of info gets replaced with a thinner shim”
“One file, bad (gets too big for context)”
“I think this is a good idea just don't really get why would you need a tool around it”
“My concern is scale though. Once you have thousands of nodes the Markdown files themselves become a mess to navigate”
Counts come from 1,795,640 Hacker News comments, November 2025 to November 2026. How we count. Report a mistake.