Each demo runs the same task with and without Boost, then publishes the complete token, time, and cost result.
Codebase exploration
Asking a question costs 50% less with Boost.
An agent traced Minikube’s missing-container-runtime preflight flow. BoostGraph replaced the long grep-and-read loop with structural code search, returning the same answer with fewer calls and less context.
Measured Minikube question results with and without BoostGraph
Metric
Without Boost
With Boost
Improvement
Cost
$0.2189
$0.1071
51% lower
Time
1m 58s
37s
3.2× faster
Input tokens
2.3K
632
73% fewer
Output tokens
10.7K
3.3K
69% fewer
Cache read
689.2K
180.5K
74% fewer
Cache write
68.8K
36K
48% fewer
File upload
Uploading a file costs 52% less with Boost.
An agent attached a large source file to work through a change. Boost compacted the surrounding tool output so the upload and follow-up reads carried the same workflow with less context.
Saving
52% less
Harness
Claude Code
Next in the lab
More real workflows, no mock data.
Videos and full telemetry in progress
Developing a feature
Benchmark pending
Fixing a bug
Benchmark pending
Debugging CI
Benchmark pending
This site uses Google Analytics cookies to understand what content is useful. Do you accept?