Interlinked.

85 microseconds.
Five tools. Six orders of magnitude.

We typed iron man into five file search tools on the same machine, against 4.47 million files, and measured wall-clock time to first result.

Interlinked85 µsVS Code35 sec, 412,000×Claude Code3:13, 2,276,000×INDEXEDWALKING

TL;DR

The takeaways in five lines.

01

85 microseconds to find one file among 4.47M, a single indexed lookup, where VS Code is 412,000× slower and Windows Search takes 67 seconds (~480,000×).

02

Content search lands in 7 to 9 ms where ripgrep needs 93.8 seconds cold, 16 ms warm, up to 58,625× faster on the same query.

03

An AI agent's file hunt collapsed from 6m57s across 71 tool calls to 16 ms in one, roughly 7,200,000× faster, and that step fell from ~58% of the context window to ~0%.

04

It's an index, not a faster walk. The work happens once, in the background: idle footprint ~44 MB, and an edited file is searchable again within ~1 ms.

05

Everything local is free forever, no card. Hosting starts at $5.99/mo.

Interlinked Files

85 µs

Indexed lookup, one pipe round trip

Claude Code (Opus 4.6)

3:13

~71 shell calls until it found the file

2,276,000×
the gap between the fastest and slowest tool.

Same machine. Same drive. Same query. Same file.

The ranking

Five tools, one question, ranked.

Each tool was timed from the moment the query was submitted to the moment the first matching result was on screen. All returned the same file.

ToolWall clockvs InterlinkedHow it answered
Interlinked Files85 µsIndexed lookup, one pipe round trip to daemon
VS Code Ctrl+P35 sec412,000×Recursive filesystem walk + fuzzy scorer
Windows Search67 sec480,000×Indexer service, slow to wake, slow to rank
grep -r71 sec832,000×Full recursive walk, reads every byte of every file
Claude Code (Opus 4.6)3 min 13 sec2,276,000×~71 shell tool calls, running grep/find in a loop

The shape of the gap

Two clusters, one chasm.

The tools sort themselves into two groups with nothing in between. Indexed engines answer in microseconds. Walkers spend tens of seconds to minutes doing filesystem bookkeeping.

Nothing on this list takes between 10 ms and 10 seconds. There is no mildly-slow file search engine. You are either indexed and fast, or you are walking and hopelessly slow.

Cluster 1: Indexed

< 10 ms

Interlinked Files (85 µs)

Cluster 2: Walkers

35 to 193 sec

VS Code, Windows Search, grep, Claude Code

Indexed or walking. There is no in-between.

The gap is six orders of magnitude.

The index

Microseconds, because it never walks.

Interlinked answers from a prebuilt index that already lives in memory. The query never touches the disk: it's a lookup in a table that already knows where every one of the 4.47 million files sits. The work happened once, in the background. By the time you press a key, there is nothing left to compute but the answer.

Getting a lookup down to 85 µs doesn't come from writing tighter C. It comes from different data structures: a lookup table cache-friendly enough to fit its hot set in L2, a query path that avoids branch mispredictions, a background daemon that amortizes the memory materialization cost across every call, and a hardware generation that gives you DDR5, AVX-512, and sixteen cores.

A walker cannot reach this number no matter how tight its code is. grep reading every byte, VS Code's recursive scan, Windows Search waking its indexer: each pays the full filesystem tax on every query. The index pays it once, offline. That is not a faster walk. It is the absence of a walk.

Architecture comparison

Walking the disk

35 to 71 sec

Recursive scan · every entry · no index · every query

Interlinked (indexed)

85 µs

L2-friendly index · NTFS journal · Zig · zero-copy

Same problem. Same OS API. One walks the whole filesystem on every call. The other never walks at all.

The walkers

Every walker is bad in its own way.

Claude Code193 seconds
2,276,000×

Not a search tool. An agent that fires grep and find in a loop (71 shell calls) until something sticks. The AI is guessing where your file is.

grep -r71 seconds
832,000×

Reads every byte of every file on the drive. Honest about what it is: a brute-force text scanner. No index, no shortcuts.

Windows Search67 seconds
480,000×

Has an index, but the indexer wakes up slowly and ranks with an aggressive scoring model that isn't built for speed. The worst of both worlds.

VS Code Ctrl+P35 seconds
412,000×

“Only” 35 seconds because it restricts itself to the open workspace. Ask it to search the whole drive and it joins grep in the minutes bracket.

None of it matters to the user. From their side, the question “is this file on my machine?” took somewhere between 35 seconds and three minutes. During that window they started composing the “I'll do it myself” response in their head.

Latency budget

What fits inside a human blink.

A human blink takes 150 to 400 ms. A keystroke-to-result loop that feels “instant” must complete in under 100 ms. Here's what each tool spends of that budget.

100 ms PERCEPTION BUDGETFull bar = 100 ms
99.915 ms free
INTERLINKED 85µs
VS CODE 35,000ms, 350× OVER BUDGET
CLAUDE CODE 193,500ms, 1,935× OVER BUDGET

Only one tool fits inside the perception budget. Everyone else overflows it by hundreds to thousands of times.

The bigger picture

Why this gap will only widen.

AI agents call file search hundreds of times per session. The cost of walking compounds. The cost of an index stays constant.

Files on drive

4.47M

Real developer workstation

Code files indexed

446K

Content-searchable in memory

Test query

“iron man”

Same query, every tool

Claude Code without Interlinked Files spent 71 tool calls guessing where a file lives. With Interlinked, the answer comes back in 85 microseconds, before the model even finishes reading its own system prompt.

The model ceiling is reachable. The next frontier is retrieval, and that's where Interlinked Files lives.

Common questions

The questions everyone asks.

Q

Why is it so much faster than grep, ripgrep, or VS Code search?

A

Because it answers from a prebuilt index that already lives in memory: it never walks the filesystem. A filename lookup is 85 microseconds; the walkers pay the full disk-scan tax on every query, which is why the same search costs them tens of seconds to minutes.

Q

Does the index go stale between searches?

A

No. It stays synced to the NTFS change journal, so a newly created or edited file becomes searchable again within about 1 millisecond. The always-on index sits at roughly 44 MB of memory while idle.

Q

Can it search inside files, or only filenames?

A

Both. Full-text content search returns in 7 to 9 ms, versus ripgrep's 93.8 seconds cold (16 ms warm), up to 58,625× faster on the same query. Word, PDF, Excel, and PowerPoint text is indexed too.

Q

How much does this actually help an AI coding agent?

A

A lot, because agents call file search hundreds of times per session. In one measured task an agent's file hunt went from 6m57s across 71 tool calls to 16 ms in a single call (about 7,200,000× faster), dropping that step from roughly 58% of the context window to nearly 0%.

Q

What does it cost?

A

Everything local is free, forever: the app, whole-machine search, MCP. Hosting starts at $5.99/mo.

Test machine: Ryzen 9 9950X3D · 64 GB DDR5 · 2 TB NVMe · Windows 11 Home · 4,470,000 files. Comparison numbers measured April 2026; engine validated July 2026: crash-free, correct ranking, zero errors across ~1,500 queries.