Proof
Performance you can check yourself.
These numbers come from a real local run across five production repos — reproducible from a single command, not hand-picked figures.
Honest by default
Every number ties back to a command.
Each benchmark is generated by the binary on a local run — repo size, symbols, edges and re-index speed, with nothing massaged by hand.
Measured proofcold -> warm -> context
| Project | Files | Tokens saved | Query |
|---|---|---|---|
| matchr | 253 | 87% | 41 ms |
| crates | 70 | 83% | 14 ms |
| poisson | 1,380 | 81% | 73 ms |
| monsite | 192 | 78% | 2 ms |
| MyRoadTrip | 1,110 | 65% | 81 ms |
| salecast | 1,951 | 54% | 10 ms |
| Total | 4,956 | 81% | — |
Token reduction = AIndex's focused context capsule vs reading the files that contain the search hits in full, measured over each repo's most central symbols at a 32k budget. Counts are estimated, so the ratio is tokenizer-independent.
Honest by default
Every number ties back to a command.
Each benchmark is generated by the binary on a local run — repo size, symbols, edges and re-index speed, with nothing massaged by hand.
ai-indexer-mcp bench --repo ~/Documents/matchr --jsonLatest run
The exact JSON, straight from the tool.
Loading benchmark data…Honest limits
What these numbers do and don't say.
These are local indexing and re-index timings on a single machine, not a hosted benchmark. Your figures depend on repo size, language mix and disk speed — run the command on your own code to see real numbers.