Start with one URL.
Point your app’s baseURL at MESH and keep your own key. Five minutes later you have a tamper-evident record of what you spend — and what you stopped spending. No signup; the source is public.
Start in five minutesSame answers — MESH sits in front of your LLM traffic and strips out wasted tokens without changing a single reply. You pay 1% of the savings, verified on the provider’s own usage, never our estimate.
One command · keep your own key · verify every number yourself
curl -fsSL https://www.mesh-technology.com/install.sh | shnpx @harrym1707/mesh startThen mesh start · needs Node 22+ · your key never leaves Claude Code · full setup guide
off repetitive API calls — the top of the range when they can wait a few seconds
off background work that can wait a few extra seconds
just from switching on Claude’s cache — many apps never do
Measured in our open test harness at the providers’ real prices, with answer quality checked on every task. Some setups save nothing — then we say it plainly: do not pay us. Every number comes with a command you can run → evidence.
Point it at whatever you already use. MESH speaks Anthropic and OpenAI natively, plus anything with an OpenAI-style API — Grok, Llama, Mistral, DeepSeek and more. Full savings verification is live for Claude, GPT and DeepSeek today; other models are reduced and recorded while their price tables land. *Gemini via its OpenAI-compatible endpoint.
{"model":"claude-sonnet-5-5",
"tools":[ {"name":"lookup_0","description":"Look up records in subsystem 0…","input_schema":{"$schema":"http://json-schema.org/draft-07/schema#","type":"object","additionalProperties":false,"properties":{"id":{"type":"string"}}}}, …11 more verbose schemas… ],
"system":"You are a careful assistant. Cite sources. Escalate anything risky.",
"messages":[
{"role":"user","content":"Step 1: inspect account 1001."},
{"role":"assistant","content":"Records 0-19: settlement entry nominal, reconciliation standard, no notification sent, annotation routine. Records 0-19: settlement entry nominal, reconciliation standard, no notification sent, annotation routine. Records 0-19: settlement entry nominal, reconciliation standard, no notification sent, annotation routine."},
{"role":"user","content":"Step 2: reconcile the ledger entries.
Records 0-19: settlement entry nominal, reconciliation standard, no notification sent, annotation routine.
Records 0-19: settlement entry nominal, reconciliation standard, no notification sent, annotation routine."},
{"role":"tool","content":"Row 1 of 400: settlement nominal… Row 2 of 400: settlement nominal… Row 3 of 400… (397 more rows)"},
{"role":"user","content":"Investigate account 1009 and summarise."}]}
A demonstration of the moves — token counts computed at build time from the full sample request (abridged on screen). Your real number comes from your own traffic. How we measure.
First, point your client at it.
$ npx -y -p @harrym1707/sdk mesh-proxy
# then one line in your app — keep your own key
baseURL: "http://127.0.0.1:8787"MESH proxy listening on http://127.0.0.1:8787
Ledger spools: ./mesh-ledger (one hash-chained JSONL per app + provider)
Anthropic SDK: new Anthropic({ baseURL: "http://127.0.0.1:8787" })
Then run your traffic as normal.
await anthropic.messages.create({ model, system, messages }) // unchanged{"seq":0,"prevHash":"000…0","event":{"requestId":"a1f2…","model":"claude-sonnet-5-5",
"usage":{"inputTokens":1695,"outputTokens":412},"levers":[{"leverId":"duplicate-context-removal",
"kind":"lossless","savedUsd":0.00130,"basis":"estimated-baseline"}],"status":"succeeded"}}
Last, recompute the invoice yourself.
$ node --import tsx evals/run-invoice.ts mesh-ledger/my-app-anthropic.jsonl| lever | kind | basis | events | saved |
|---|---|---|---|---|
| duplicate-context-removal | lossless | estimated-baseline | 6 | $0.0086 |
| tool-schema-compaction | lossless | estimated-baseline | 6 | $0.0054 |
| execution-tier-flex | tier | measured | 8 | $0.0193 |
| fresh-tool-result-cap | lossy | recorded — unbilled, no gate verdict | 4 | — |
Most savings claims are projections. Ours come with the receipt: we ran real requests, published every line, and the rows add up to the total — check them.
saved by a single lever — switching Claude’s cache on — measured both ways on identical prompts, answers unchanged. The receipt beside is our latest small live run: 22.0% of real spend saved and billing on every active agent, the cache lever earning live. The full measured range is 26–73% by traffic type → evidence.
SPEND, BY AGENT
VERIFIED SAVINGS, BY LEVER
Theo ships with MESH. He studies your own traffic, finds new waste to cut, and only ever tunes MESH — never your prompts, never your answers.
When he finds a saving he tells you what it is and what it might cost in quality, then waits for your yes. Anything that could touch an answer stays off until a replay of your own traffic proves it safe — and once a month he reports his own honesty: what he tried, what he saved, and where he held back.
No subscription. No seats. No minimum. You pay a slice of what MESH actually saved you — and you can recheck the maths behind every invoice yourself.
of verified savings, monthly — nothing else
Point your app’s baseURL at MESH and keep your own key. Five minutes later you have a tamper-evident record of what you spend — and what you stopped spending. No signup; the source is public.
Start in five minutes