Tokdiet

tokdiet

Your AI agent is paying to send the same file dump five times. tokdiet is a local proxy that sits between your agent and the model API, meters every token, puts your bloated context on a diet — and *proves* the answer didn't get worse.
ccusage that shrinks the bill — without losing quality.

🌐 Live demo (watch one request lose the weight): agiwhitelist.github.io/tokdiet
📝 Launch write-up + full benchmark methodology: I cut an AI agent's input tokens by 71% and quality held — here's the 66-task benchmark

The proof (this is the whole point)

Every "context optimizer" cuts tokens. The scary question is the one they can't answer:
*"If I cut the context, does the model get dumber?"*

So we measured it. A 66-task A/B benchmark across 6 categories on a real model (MiniMax‑M3), each task run twice — full context (baseline) vs through tokdiet (governed) — graded against the known answer, repeated ×3 and majority‑voted to cancel model noise:

−71% tokens, quality on par with baseline. Real requests, real grading — not a mock. The ~1–2 task gap is model nondeterminism plus the model *declining to echo a secret* — not context loss; the hardest "needle buried in junk" adversarial cases pass, because tokdiet doesn't delete blindly — it pages cold context out *recoverably* and protects anything on‑topic. Reproduce it yourself: node bench/run.mjs (needs an API key in env).

How it compares

Everyone shows the bill or cuts it blind. tokdiet is the one that cuts it and proves the model didn't get dumber — and stops cutting the moment it might.

Quick start

Now run your agent (Claude Code, Cursor, Codex, your own script) as usual. Traffic flows through tokdiet, gets metered and compacted, and is forwarded upstream unchanged in every way that matters.

Your API key stays with…