0.16.9New version of Boost released
New releasev0.16.9Oct 28, 2026

New version of Boost released— Richer insights and reliable app downloads

Download the latestRelease notes

Keep the work. Cut the context bill.

Boost saves roughly 13% of a coding-agent sessionby removing repetitive tool output before it enters the model context.

~13%

less session cost

Typical saving; actual results vary by workflow.

No workflow change

Keep your agent, model, terminal, and commands.

Nothing is lost

Every compression is local, measured, and reversible.

Read the technical paperTry Boost

Workflow proof

See the saving, task by task.

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.

Saving
51% less
Repository
minikube
Harness
Claude Code
Measured Minikube question results with and without BoostGraph
MetricWithout BoostWith BoostImprovement
Cost$0.2189$0.107151% lower
Time1m 58s37s3.2× faster
Input tokens2.3K63273% fewer
Output tokens10.7K3.3K69% fewer
Cache read689.2K180.5K74% fewer
Cache write68.8K36K48% fewer
File Compression

Web development simple UI fix.

A simple front-end fix task that uses Boost file compression feature in order to save tokens on files.

Harness
Claude Code
Loaded Unused

See what loads into context but never gets used.

Sometimes skills and MCPs are installed but not used, which might cause high token usage. Boost can help you remove the unused skills or MCPs.

Surface
boost report · Loaded Unused