╭──────────────────────────────────────────╮ ╭──────────────────────────────────────────╮ │ >>>>>>>>>>>>>>> ctx_read >>>>>>>>>>>> │ │ >>>>>>>>>>>>>>> ctx_read >>>>>>>>>>>> │ ┌─────────────┐ │ >>>>>>>>>>>>>>> compress >>>>>>>>>>>> │ ┌──────────┐ ┌─────────────┐ │ >>>>>>>>>>>>>>> compress >>>>>>>>>>>> │ ┌──────────┐ │ 100K tokens │ =========>│ >>> AST >>> cache >>> signal >>> │ =========> │ ~5K tok │ │ 100K tokens │ =========>│ >>> AST >>> cache >>> signal >>> │ =========> │ ~5K tok │ └─────────────┘ │ >>>>>>>>>>>>>>> filter >>>>>>>>>>>> │ └──────────┘ └─────────────┘ │ >>>>>>>>>>>>>>> filter >>>>>>>>>>>> │ └──────────┘ │ >>>>>>>>>>>>>>> dedupe >>>>>>>>>>>> │ │ >>>>>>>>>>>>>>> dedupe >>>>>>>>>>>> │ ╔══════════════╗ ╰──────────────────────────────────────────╯ ╔══════════╗ ╔══════════════╗ ╰──────────────────────────────────────────╯ ╔══════════╗ ║ raw input ║ ─ ─ ─ ─ ─ ─ ─ ─ LeanCTX ─ ─ ─ ─ ─ ─ ─ ─ ─ ─ ║ output ║ ║ raw input ║ ─ ─ ─ ─ ─ ─ ─ ─ LeanCTX ─ ─ ─ ─ ─ ─ ─ ─ ─ ─ ║ output ║ ╚══════════════╝ ╚══════════╝ ╚══════════════╝ ╚══════════╝ ┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄ ┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄ ┌──┐ ┌──┐ ┌──┐ ┌──┐ ┌──┐ ┌──┐ ┌──┐ ┌──┐ ┌──┐ ┌──┐ ┌──┐ ┌──┐ ┌──┐ ┌──┐ ┌──┐ ┌──┐ ┌──┐ ┌──┐ ┌──┐ ┌──┐ ┌──┐ ┌──┐ ┌──┐ ┌──┐ ┌──┐ ┌──┐ │░░│ │░░│ │░░│ │░░│ │▓▓│ │▓▓│ │▓▓│ │░░│ │░░│ │░░│ │░░│ │░░│ │░░│ │░░│ │░░│ │░░│ │░░│ │▓▓│ │▓▓│ │▓▓│ │░░│ │░░│ │░░│ │░░│ │░░│ │░░│ │░░│ │░░│ │░░│ │░░│ ───> │▓▓│ │▓▓│ │▓▓│ ───> │░░│ │░░│ │░░│ │░░│ │░░│ │░░│ │░░│ │░░│ │░░│ │░░│ ───> │▓▓│ │▓▓│ │▓▓│ ───> │░░│ │░░│ │░░│ │░░│ │░░│ │░░│ └──┘ └──┘ └──┘ └──┘ └──┘ └──┘ └──┘ └──┘ └──┘ └──┘ └──┘ └──┘ └──┘ └──┘ └──┘ └──┘ └──┘ └──┘ └──┘ └──┘ └──┘ └──┘ └──┘ └──┘ └──┘ └──┘ file file file file read cache send tok tok tok tok tok tok file file file file read cache send tok tok tok tok tok tok ╭──────────────────────────────────────────╮ ╭──────────────────────────────────────────╮ │ >>>>>>>>>>>>>>> ctx_read >>>>>>>>>>>> │ │ >>>>>>>>>>>>>>> ctx_read >>>>>>>>>>>> │ ┌─────────────┐ │ >>>>>>>>>>>>>>> compress >>>>>>>>>>>> │ ┌──────────┐ ┌─────────────┐ │ >>>>>>>>>>>>>>> compress >>>>>>>>>>>> │ ┌──────────┐ │ 100K tokens │ =========>│ >>> AST >>> cache >>> signal >>> │ =========> │ ~5K tok │ │ 100K tokens │ =========>│ >>> AST >>> cache >>> signal >>> │ =========> │ ~5K tok │ └─────────────┘ │ >>>>>>>>>>>>>>> filter >>>>>>>>>>>> │ └──────────┘ └─────────────┘ │ >>>>>>>>>>>>>>> filter >>>>>>>>>>>> │ └──────────┘ │ >>>>>>>>>>>>>>> dedupe >>>>>>>>>>>> │ │ >>>>>>>>>>>>>>> dedupe >>>>>>>>>>>> │ ╔══════════════╗ ╰──────────────────────────────────────────╯ ╔══════════╗ ╔══════════════╗ ╰──────────────────────────────────────────╯ ╔══════════╗ ║ raw input ║ ─ ─ ─ ─ ─ ─ ─ ─ LeanCTX ─ ─ ─ ─ ─ ─ ─ ─ ─ ─ ║ output ║ ║ raw input ║ ─ ─ ─ ─ ─ ─ ─ ─ LeanCTX ─ ─ ─ ─ ─ ─ ─ ─ ─ ─ ║ output ║ ╚══════════════╝ ╚══════════╝ ╚══════════════╝ ╚══════════╝ ┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄ ┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄┄ ┌──┐ ┌──┐ ┌──┐ ┌──┐ ┌──┐ ┌──┐ ┌──┐ ┌──┐ ┌──┐ ┌──┐ ┌──┐ ┌──┐ ┌──┐ ┌──┐ ┌──┐ ┌──┐ ┌──┐ ┌──┐ ┌──┐ ┌──┐ ┌──┐ ┌──┐ ┌──┐ ┌──┐ ┌──┐ ┌──┐ │░░│ │░░│ │░░│ │░░│ │▓▓│ │▓▓│ │▓▓│ │░░│ │░░│ │░░│ │░░│ │░░│ │░░│ │░░│ │░░│ │░░│ │░░│ │▓▓│ │▓▓│ │▓▓│ │░░│ │░░│ │░░│ │░░│ │░░│ │░░│ │░░│ │░░│ │░░│ │░░│ ───> │▓▓│ │▓▓│ │▓▓│ ───> │░░│ │░░│ │░░│ │░░│ │░░│ │░░│ │░░│ │░░│ │░░│ │░░│ ───> │▓▓│ │▓▓│ │▓▓│ ───> │░░│ │░░│ │░░│ │░░│ │░░│ │░░│ └──┘ └──┘ └──┘ └──┘ └──┘ └──┘ └──┘ └──┘ └──┘ └──┘ └──┘ └──┘ └──┘ └──┘ └──┘ └──┘ └──┘ └──┘ └──┘ └──┘ └──┘ └──┘ └──┘ └──┘ └──┘ └──┘ file file file file read cache send tok tok tok tok tok tok file file file file read cache send tok tok tok tok tok tok

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, summed from tamper-evident local ledgers. Add yours and push the numbers higher.

Install LeanCTX Star on GitHub

Live savings

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.

Live

16.7B

Tokens saved

stripped from LLM context

$41,728

Money saved

at published model rates

1.9 MWh

Energy saved

≈ 154,548 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.

Leaderboard

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
1	frpboy Leader	5.1B	71%	562.5 kWh	$12,656 est.
2	yvgude	1.0B	79%	114.4 kWh	$2,573 est.
3	lex_ter	124.6M	95%	13.8 kWh	$312 est.
4	mas	106.8M	70%	11.9 kWh	$267 est.
5	cses	88.5M	61%	9.8 kWh	$221 est.
6	Ignacio Monge	76.0M	79%	8.4 kWh	$190 est.
7	AlvaroBrasilia	53.8M	78%	6.0 kWh	$134 est.
8	sb	53.1M	85%	5.9 kWh	$133 est.
9	Ageratum Studio	33.7M	78%	3.7 kWh	$84 est.
10	mkloouo	32.5M	99%	3.6 kWh	$81 est.
11	anonymous	27.7M	44%	3.1 kWh	$69 est.
12	ibrahimogod	22.4M	53%	2.5 kWh	$56 est.
13	anonymous	17.8M	68%	2.0 kWh	$45 est.
14	tana	10.4M	55%	1.2 kWh	$26 est.
15	paper	10.2M	56%	1.1 kWh	$25 est.
16	anonymous	8.5M	59%	947 Wh	$21 est.
17	anonymous	6.1M	68%	678 Wh	$15 est.
18	Ageratum Studio	5.6M	62%	618 Wh	$14 est.
19	anonymous	4.0M	43%	450 Wh	$10 est.
20	ScotXlander	3.4M	53%	374 Wh	$8 est.
21	boundary-operator	2.3M	88%	261 Wh	$6 est.
22	Stephen.S	1.6M	93%	174 Wh	$4 est.
23	webut	1.4M	52%	152 Wh	$3 est.
24	aka-lab	1.0M	66%	116 Wh	$3 est.
25	Mohammad Jony	1.0M	48%	113 Wh	$3 est.
26	Richard Capraro	705.6K	50%	78 Wh	$2 est.
27	Stephen.S	564.6K	84%	63 Wh	$1 est.
28	mukeshrishit	119.8K	73%	13 Wh	$0 est.
29	notLucky	117.9K	51%	13 Wh	$0 est.
30	anonymous	102.9K	50%	11 Wh	$0 est.
31	lex_ter	97.6K	28%	11 Wh	$0 est.
32	Richard Capraro	55.8K	61%	6 Wh	$0 est.
33	anonymous	30.7K	51%	3 Wh	$0 est.
34	Richard Capraro	22.4K	45%	2 Wh	$0 est.
35	anonymous	1.7K	1%	0 Wh	$0 est.
36	anonymous	1.5K	5%	0 Wh	$0 est.
37	Suleyman Laarabi unverified	9.9B	100%	1.1 MWh	$24,763 est.

No one has opted in yet. Be the first to claim #1 and set the pace: lean-ctx gain --publish --leaderboard

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 true keeps 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.

Your move

Claim your spot on the leaderboard

Install LeanCTX, let it shrink what your AI reads, and your tokens, dollars and watt-hours start adding to the community total. Publish your recap with one command. Your numbers stay verifiable offline, and every saved token is a little less energy burned.

Install LeanCTX Star on GitHub

The LeanCTXcommunity

Collective impact, measured

Top realized savings

Claim your spot on the leaderboard

The LeanCTX
community