trove Install

Updated November 2026 · study launch-3, Claude Code 2.1.319

Measured results.

How much of a coding-agent bill Trove saves, and what it costs in quality. Every figure is labeled measured or estimated.

Install
brew install usetrove/trove/trove

Free and open source. Sends nothing anywhere by default. Run trove on your own sessions and see your own numbers.

The headline numbers

Cost change with model routing

−25%estimated

Cost per session went down by a quarter, and every task still passed. Needs an API key.

likely range: 21% to 29% lower

Tasks passed

30 of 30measured

Every task passed, with and without Trove.

in every version of the test

30 long Python sessions in Claude Code with an API key. One model, one agent version, easy tasks: not a forecast of your bill.

Does it cost quality?

Every task passed in every arm (above). The other checks, all measured, not estimated:

Extra time with routing

+9.4 smeasured

Extra time per session with routing on. The plugin alone added 0.3 s.

median · likely range +1.8 s to +12.7 s

Error lines kept

698 of 698measured

Error lines still visible to the model after trimming.

scripted sessions · v0.4.0

Cache kept intact

400 of 400measured

Requests that kept the cached prefix byte-identical.

scripted sessions · v0.4.0

You don't have to take our word for it

Benchmarks show what Trove does on these sessions. Yours are what matter. Every fix starts in shadow on a copy of your requests, turns on only from that evidence, and rolls back if it stops paying off.

Real-task studies

Study launch-3 compares long Claude Code sessions with and without Trove:

Cost is estimated: list price on the gateway's usage records, the same source for every arm. Pass or fail is measured.

MeasurePlugin + gateway + model routingPlugin alone
Studylaunch-3, 30 long-session taskslaunch-3, 30 long-session tasks
Model, agentclaude-sonnet-5-5, tool turns routed to claude-haiku-5-5; Claude Code 2.1.319claude-sonnet-5-5; Claude Code 2.1.319
Runs30 pairs (90 runs in the study)30 pairs (90 runs in the study)
Total cost change, 98% interval (estimated)−25.3% (−29.2% to −21.4%)+3.5% (−0.6% to +7.7%)
Median paired cost change (estimated)−26.2% (−29.8% to −21.0%)+4.2% (−1.6% to +8.5%)
Success (measured)30 of 30 vs 30 of 3030 of 30 vs 30 of 30
Mean cost per run (estimated)$0.089 vs $0.119 without Trove$0.124 vs $0.119 without Trove
VerdictSHIPDON'T SHIP: even the best case saves under 1%

What the numbers mean

Full launch-3 report

Scripted sessions, replayed through the real engine

Hand-scripted sessions replayed offline with trove bench workflows: no API calls, no spend.

They show what the optimizers do on these patterns, not what your bill will be. Sonnet list prices as of 2026-11-08; results from v0.4.0.

Kind of sessionMedian saving (range)Label
Everyday: fix a failing test, rename across a codebase, debug with logs, explore a repo, a ~90-turn feature session (7 workflows)3.7% (0.0% to 8.6%)estimated
Output-heavy: a verbose test loop, a failing container build, incident logs (3 workflows). A ceiling for that kind of work, not a typical day19.3% (2.5% to 50.7%)estimated
A custom agent or script that sends no cache markers (the 7 everyday workflows again). Zero for an agent that already caches, such as Claude Code72.0% (51.6% to 79.8%)estimated

How it was measured

The question, the arms, the decision rule and the budget were locked before the first run.

Decision rule

A comparison ships only if all of these hold:

The study stopped after its first look because both comparisons were decided. Each look is tested at the stricter level, so stopping early doesn't make a result easier to reach.

Where things stand. With an API key and model routing on, estimated cost fell 25% (98% interval 21% to 29%) with no drop in tasks passed. That's the only confirmed saving, and routing never runs on a subscription. Trove promises nothing beyond what a study shows.

Caveats

Reproduce

Needs an Ubuntu 24.04 VM (4+ vCPUs, 16 GB RAM) and your own pay-per-use API key.

The pilot costs about $5–15. The study is capped at $40.

bash bench/scripts/launch/00_vm_setup.sh
export ANTHROPIC_API_KEY=...   # your own pay-per-use key
bash bench/scripts/launch/01_check.sh
bash bench/scripts/launch/02_pilot.sh
bash bench/scripts/launch/03_run.sh
bash bench/scripts/launch/04_report.sh

Read the methodology. Earlier results are in the v0.4.0 archive.

Open source. Runs on your machine. trove uninstall puts everything back.