← All comparisons
Atelier vs fff (fff-mcp)
What fff (fff-mcp) says, vs. what it scored.
In-memory, frecency-ranked file and content search with a background watcher -- fast file discovery, not symbol-level code search.
What fff (fff-mcp) says about itself
“A file search toolkit for humans and AI agents. Really fast... Way faster than CLIs like ripgrep and fzf in any long-running process that searches more than once.”
“On a 500k-file Chromium checkout, FFF achieves sub-10ms per query compared to 3-9 seconds per ripgrep spawn.”
Publishes some numbers ...never against another search tool ~9.6k stars
What it actually scored — same 14 repos, same 7,213 queries as every other tool
| Tool | MRR | p95 | p100 |
|---|---|---|---|
| ★ Atelier +semantic (BGE) | 0.727 | 390ms | 1057ms |
| ★ Atelier lexical (default) | 0.676 | 134ms | 319ms |
| fff (fff-mcp) | 0.430 | 46ms | 207ms |
The speed claim is real and it shows -- 46ms p95 here, among the fastest tools in the set. It's a file-finder with no semantic layer, though, so on "where does X happen" queries it tops out at 0.430 MRR: fast answers to the wrong question about a third of the time.
The true story
Every tool in this comparison, fff (fff-mcp) included, has been through the exact same 14 repositories and 7,213 query/gold pairs that score Atelier — no cherry-picked queries, no separate corpus. Full methodology, every raw number, and the other 9 tools →