51.6B
Tokens saved stripped from LLM context
Community Metrics
The LeanCTX community.
Every developer running LeanCTX trims the tokens their AI reads, saving money and real energy. This is our shared scoreboard: live, opt-in, and summed from tamper-evident local ledgers. Add yours and push the numbers higher.
Collective impact, measured.
Updated on every visit: real tokens, real dollars, and the energy that compute never had to burn. Every figure reconciles to the opt-in ledgers below, and grows each time someone new joins.
$129,053
Money saved at published model rates
5.7 MWh
Energy saved ≈ 477,975 phone charges
Fewer tokens means less compute — and less energy burned. Every name on this board is a small, verifiable dent in AI’s footprint, multiplied by everyone who joins.
Energy is an estimate — tokens saved × ≈0.4 J/token (modern optimized LLM inference, e.g. Llama-3-70B FP8 on H100); real figures vary by model and hardware. Sources: Epoch AI, John Snow Labs.
Measured. Not estimated.
Top realized savings.
These developers have compressed the most context, and saved the most energy doing it. Figures are self-reported from each user’s local ledger (not server-verified), so entries that look statistically implausible are flagged unverified and ranked last. Claim your spot with a single command.
| # | Developer | Tokens saved | Compression | Energy saved | Saved | Last sync |
|---|---|---|---|---|---|---|
| 1 | frpboy Leader | 5.1B | 71% | 562.5 kWh | $12,656 est. | 1d ago |
| 2 | anonymous | 2.2B | 85% | 247.6 kWh | $5,570 est. | 18h ago |
| 3 | anonymous | 1.7B | 69% | 188.9 kWh | $4,249 est. | 8h ago |
| 4 | anonymous | 1.4B | 58% | 158.5 kWh | $3,565 est. | 15h ago |
| 5 | anonymous | 1.3B | 75% | 147.6 kWh | $3,320 est. | 21m ago |
| 6 | anonymous | 1.2B | 92% | 136.9 kWh | $3,080 est. | 12h ago |
| 7 | anonymous | 1.1B | 62% | 124.1 kWh | $2,793 est. | 17h ago |
| 8 | yvgude | 1.0B | 79% | 115.3 kWh | $2,595 est. | 1d ago |
| 9 | Shutaru | 715.2M | 89% | 79.5 kWh | $1,788 est. | 11h ago |
| 10 | anonymous | 700.5M | 74% | 77.8 kWh | $1,751 est. | 18h ago |
| 11 | anonymous | 685.0M | 97% | 76.1 kWh | $1,712 est. | 1d ago |
| 12 | anonymous | 680.5M | 75% | 75.6 kWh | $1,701 est. | 15h ago |
| 13 | anonymous | 673.3M | 84% | 74.8 kWh | $1,683 est. | 16h ago |
| 14 | anonymous | 670.3M | 77% | 74.5 kWh | $1,676 est. | 16h ago |
| 15 | anonymous | 637.1M | 85% | 70.8 kWh | $1,593 est. | 5h ago |
| 16 | anonymous | 591.2M | 67% | 65.7 kWh | $1,478 est. | 16h ago |
| 17 | anonymous | 560.8M | 45% | 62.3 kWh | $1,402 est. | 14h ago |
| 18 | albinekb | 556.3M | 84% | 61.8 kWh | $1,391 est. | 1d ago |
| 19 | anonymous | 546.8M | 74% | 60.8 kWh | $1,367 est. | 18h ago |
| 20 | anonymous | 492.3M | 83% | 54.7 kWh | $1,231 est. | 9h ago |
| 21 | tmk | 472.6M | 75% | 52.5 kWh | $1,181 est. | 18h ago |
| 22 | anonymous | 452.0M | 51% | 50.2 kWh | $1,130 est. | 21h ago |
| 23 | anonymous | 410.8M | 96% | 45.6 kWh | $1,027 est. | 3h ago |
| 24 | anonymous | 410.2M | 96% | 45.6 kWh | $1,025 est. | 1d ago |
| 25 | anonymous | 406.0M | 74% | 45.1 kWh | $1,015 est. | 3h ago |
| 26 | anonymous | 385.7M | 80% | 42.9 kWh | $964 est. | 17h ago |
| 27 | anonymous | 362.9M | 78% | 40.3 kWh | $907 est. | 17h ago |
| 28 | anonymous | 347.1M | 86% | 38.6 kWh | $868 est. | 4h ago |
| 29 | anonymous | 324.5M | 49% | 36.1 kWh | $811 est. | 36m ago |
| 30 | anonymous | 321.8M | 60% | 35.8 kWh | $804 est. | 9h ago |
| 31 | CleanTest-Real-v2 | 307.5M | 50% | 34.2 kWh | $769 est. | 15h ago |
| 32 | Natha | 297.0M | 88% | 33.0 kWh | $743 est. | 16h ago |
| 33 | anonymous | 277.5M | 97% | 30.8 kWh | $694 est. | 16h ago |
| 34 | anonymous | 271.6M | 54% | 30.2 kWh | $679 est. | 1d ago |
| 35 | anonymous | 268.9M | 74% | 29.9 kWh | $672 est. | 1d ago |
| 36 | anonymous | 267.9M | 88% | 29.8 kWh | $670 est. | 5h ago |
| 37 | Naoray | 234.5M | 48% | 26.1 kWh | $586 est. | 1d ago |
| 38 | anonymous | 209.0M | 74% | 23.2 kWh | $522 est. | 4h ago |
| 39 | anonymous | 207.5M | 53% | 23.1 kWh | $519 est. | 18h ago |
| 40 | anonymous | 206.6M | 73% | 23.0 kWh | $517 est. | 4h ago |
| 41 | anonymous | 201.6M | 55% | 22.4 kWh | $504 est. | 1d ago |
| 42 | ibte | 193.8M | 67% | 21.5 kWh | $484 est. | 1d ago |
| 43 | anonymous | 183.9M | 79% | 20.4 kWh | $460 est. | 1d ago |
| 44 | anonymous | 169.5M | 68% | 18.8 kWh | $424 est. | 6h ago |
| 45 | Wadaw | 166.8M | 80% | 18.5 kWh | $417 est. | 1d ago |
| 46 | anonymous | 162.7M | 81% | 18.1 kWh | $407 est. | 13h ago |
| 47 | anonymous | 153.7M | 77% | 17.1 kWh | $384 est. | 18h ago |
| 48 | mate.travel | 151.1M | 84% | 16.8 kWh | $378 est. | 1d ago |
| 49 | anonymous | 147.6M | 64% | 16.4 kWh | $369 est. | 16h ago |
| 50 | anonymous | 133.3M | 39% | 14.8 kWh | $333 est. | 9h ago |
Want in? Once LeanCTX has been compressing your
context for a while, run lean-ctx gain --publish --leaderboard, then watch
your name climb.
- Pick your name. Add
--name="your handle"the first time; it sticks for every future push. - No account, ever. Your entry is signed by a key that lives only on your machine. That key is your identity: no login, no email, nothing to leak.
- Push as often as you like. Re-publishing refreshes your one entry in place (same link), so it never piles up duplicates.
- Stay on the board on autopilot.
lean-ctx config set gain.auto_publish truekeeps your numbers fresh as you save more energy.
What's shared: only four aggregate numbers — tokens saved, compression rate, energy and dollars saved — plus the name you pick. Never your code, file paths, repo names or prompts. It's all open source — see the publish contract.
See your ownsavings.
Install LeanCTX and track your compression metrics from day one.
curl -fsSL https://leanctx.com/install.sh | sh