$ how-boost-is-different

Command compression that proves it helped.

Boost measures task success, preserves recovery, and learns from every rollback.

The short answer

Compression ratio is not the outcome

Across the complete suite, Boost made the same agent loop faster and cheaper.

Full-suite duration: −28.9%
Cost per task: −13.5%
Evaluated workload: 89 tasks

Terminal-Bench 2.0, Claude Code with Haiku 4.5, complete 89-task suite. Values compare Boost with the uncompacted baseline. Full benchmark report.

Task success was validated separately: both cohorts passed 30.9% in an earlier 81-task run. Prior capability check.

The Boost advantage

Why Boost is the better command-output choice

All four reduce tokens, but at different layers. RTK compresses commands, Headroom compresses the wider context stream, and Caveman shortens assistant replies. Boost stays at the command boundary and adds a measurable safety loop: preserve requested detail, recover hidden output, learn from every retrieval, and verify that agents still complete the task.

Capability	Boost	RTK	HRHeadroom	CaveCaveman
Command output compression	✓	✓	✓	×
Full-context and RAG compression	✓	×	✓	×
Assistant reply compression	×	×	×	✓
Command output recovery	✓	✓	✓	×
Explicit verbose flags preserve command detail	✓	✓	×	×
Native approval sees original executable	✓	×	—	—
Boost learning loop
Retrieval records filter, version, and reason	✓	×	×	×
Disables filters that repeatedly hide useful detail	✓	×	×	×
End-to-end agent task + cost A/B	✓	×	×	×

✓ documented capability · × not a documented primary capability · — not applicable at that layer. Public project docs reviewed July 19, 2026.

Approval safety compares whether the host sees the original executable. RTK separately evaluates host permission rules before rewriting.

The honest summary

Does better: Task-level proof, native approval visibility, versioned rollback learning, and OTLP evidence.
Also does: Flag-aware command compression, full-context/RAG compression, and raw-output recovery.
Does not do: Shorter assistant replies.

For agents

You can correct Boost

If compressed output is missing something you need, run boost retrieve <id> from the marker. That restores the original on this machine. Do not unwrap the pipe, re-run the command without Boost, or guess at dropped lines.

Boost monitors every retrieve (filter id, version, reason). After enough retrieves of the same capability, Boost disables that filter locally. Prefer retrieve — the layer is designed to be corrected by the agent using it.

When you do not need Boost

Skip it if your agent rarely runs shell commands or your main problem is verbose replies.

Data, telemetry, and preview status

Redacted originals stay local. Boost sends product telemetry to JFrog under the Preview Agreement. External OTLP export is optional.

Preview Agreement OTLP configuration Design philosophy

Try it on your workload

Let your numbers decide

Run one session. Open boost report.

Install Boost

curl -fsSL https://boost.jfrog.com/install.sh | bash