A free, open-source CLI for Claude Code, Codex, opencode and your own API calls. It reads the usage already on your machine, and every line of it is on GitHub under MIT.
It finds wasted tokens, prices every fix in exact dollars, and applies the ones you accept, like compacting long conversations or a cheaper model for the session you’re in.
“good to see the per-model read rates in there, that’s the part most tools still have at a flat 0.1x.”
“I tried optimAIzr, it’s really good. Great work, thanks.”
One optimaizr profile run on Oct 7, 2026, over 182 days of my own Claude Code and Codex use. Every call re-reads the whole conversation. Printed below as the receipt my AI bill never came with.
optimaizr live.$ optimaizr results0.10Oct 7, 2026A cache countdown, no mod neededA status line under Claude Code's prompt shows your context, what each message costs to re-read, and how long the cache stays warm.now 0.10.3 · Spot conversations that start heavy, and see what each cache write was for in optimaizr sessions.$ optimaizr statusline on0.9Oct 6, 2026Savings you can act onYour plan is detected and every saving is labelled: clear waste, likely, or up to. Compacting earlier, the biggest lever, is one command.$ optimaizr apply context-compactionOn my machine, yes. A week after I started compacting at 200K, optimaizr results measured a prompt at 26% less than the two weeks before (7% less against just the 5 days before), and showed what it cost me: 7.1 minutes a day waiting for summaries. Run it on your own history and see. If a number looks wrong, tell me.
No. Model choice is one of fourteen rules, and on most Claude Code bills it is not the biggest lever: every call re-reads the whole conversation, so compacting earlier usually saves more. The other rules catch files read twice, blind retries, oversized tool output, heavy reasoning on trivial answers and coming back after the cache expired.
Since 0.9 it judges whole tasks instead of single calls, and leaves out normal debugging, files being written and switches that would not pay back. Clear waste is the headline, and the bigger savings are shown as what they are: up to, if you test them. Every figure holds up when you check it.
Your usage never does. It reads token counts from files your agents already write. verify calls your own provider with your own key, live --jev is opt-in, and once a day it asks npm for the latest version number, which you can turn off with OPTIMAIZR_NO_UPDATE_CHECK=1.
Yes. The CLI is MIT-licensed and developed in the open on GitHub. Pro, the hosted version, is a separate product.
The CLI is free, with no account. Pro, a hosted version for you or your team, is coming soon.
Claude Code, Codex and opencode sessions, your own Anthropic or OpenAI calls through wrap(), or a CSV export.
just trying it once? npx optimaizr profile runs without installing
A hosted version for you or your team: a dashboard, 12 months of history, auto-apply fix and spend guardrails, with Jev double-checking every model switch.
The CLI stays free either way.