New releasev0.12.6Aug 24, 2026

New version of Boost releasedHomepage demos and cleaner uninstall

$ token-savings

Token Savings

Compress noisy command output at the source, so agents spend context on signal instead of terminal spam.

The anatomy of abloated context window

Repetitive terminal noise balloons the loop. Here is how Boost trims it.

terminal
acme-app git:(main) claude
Claude Code v2.1.195
Opus 4.8 (1M context) · Claude Enterprise
~/projects/acme-app
Fix the failing build
⎿ ⊞ Read src/api.ts, tsconfig.json
I'll run the build and read the errors.
Bash(npm run build)
✓ build ran — noise stripped, 1 error kept
ERROR ./src/api.ts:42:18 — TS2345
Argument of type 'string' is not assignable to 'number'.
→ exact stack trace preserved · boilerplate dropped
Found it — patching src/api.ts on the first pass.
Update(src/api.ts) +1 -1
Brewed for 6s
✓ Boost saved 409,100 tokens in this session
? for shortcuts · ← for agents high · /effort
context window742,900 tok · 62%

This is your session with Boost on. Toggle it to see the raw, context-flooding output it just hid.


What Boost keeps

Boost preserves the signal: failures, summaries, counts, and next clues. The repetitive stream gets compressed before it spends context. If a filter hid too much, run boost retrieve <id> — Boost monitors those retrieve events and can disable the filter locally. Prefer retrieve over bypassing Boost.

Where it helps most

The noisiest commands your agent runs (tests, builds, and logs) shrink the most.

boost — noisy commands
# noisy test runs
pytest -q
go test ./...
npm test

# build & lint logs
npm run build
npx tsc --noEmit
ruff check .

# diffs, logs & debug output
git diff
docker logs app
kubectl logs deploy/api

Measure what you saved

Boost tracks raw versus filtered size and estimates saved tokens per command. Run boost report for aggregate savings, or add a TOML filter for custom tools.


# sustainability

Emission Savings

Every saved token is energy you didn't burn. Boost translates raw token savings into an estimated emissions impact, so the work your agents skip becomes a number you can share with your team.

boost — emissions
$ boost report

Saved 1.7M tokens of terminal noise.

You avoided 359 g CO2e. ≈ 0.21 kg CO2e / 1M saved tokens.

Less noise → less compute → less AI exhaust in the atmosphere.

emissions estimated CO2e avoided

The estimate uses a configurable kg-CO2e-per-million-saved-tokens heuristic. It's a directional sustainability signal, not audited carbon accounting, but it turns context saved into a concrete reminder that less AI exhaust reaches the atmosphere.


Next steps