A terminal coding agent
Squeezy inspects code, edits files, runs commands, plans work, and resumes sessions, all from your terminal and all tied to local evidence.
coding agent Squeezy does the busywork.
Squeezy does the busywork.
Your model does the thinking.
Squeezy prepares each task on your machine and sends the model only what it needs. Thirty-plus cost strategies work together, so you get the same result on a smaller bill.
▉ add a /cost summary to the status line
▌──────────────────────────────────────╯
│
→ I'll read the status-line renderer, then wire in the cost broker.
│
✓ Read 2 files
│ read_slice · statusline.rs:120-168
│ read_slice · cost_broker.rs:1-52
◇ Plan 3 steps
│ add a compact cost segment after the model chip
⊏▓█▓⊐ Squeezing (4s • esc esc to interrupt) · Patch: statusline.rs
A session mid-turn: the busywork runs local, so you only pay for the thinking.
measured
40% less spend for the same result.
Across our 15-language code-understanding benchmark, Squeezy answered the same questions as an external baseline for 60 cents on the dollar at the median. Same model, same pricing, same grader. It cost less in every language, on both tiers tested, without giving up accuracy.
Languages 22 with local code understanding
Cost strategies 30+ across four saving layers
Providers 27 from cloud APIs to local runtimes
Platforms 3 macOS, Linux, Windows
what it is
A full coding agent that costs less to run.
Everything you expect from a terminal coding agent: it reads code, edits files, runs commands, and verifies the result. The difference is the prep work it does before each model call, so you keep the capability and lose the waste.
It reads your codebase
A local knowledge database across 22 languages maps your symbols, references, and call paths, so Squeezy navigates your code's structure instead of guessing from text.
Your model, your machine, your rules
Bring your key for any of 27 providers, keep the work on your machine, and gate edits, shell, and web access behind permissions you set.
how the saving happens
More than thirty ways to cut waste.
They group into four independent layers. Local code understanding is the first, not the whole story: it works alongside reusing stable context, right-sizing each turn, and putting you in control of the bill.
01
Understand the code first
Before spending a token, Squeezy reads your repository locally and works out which files and lines matter.
local code understandingcode knowledge database
02 Don't pay for the same bytes twice
Most of a coding session repeats: the same instructions, the same files, the same command output. Squeezy keeps that out of the bill.
prompt cachingreceiptsdeferred tool schemasstale bytes
03 Right-size every turn
Not every turn deserves the biggest model or the longest history. Squeezy matches the effort and the context to the task in front of it.
routingcompactionshaped outputsubagents
04 Control the bill, don't just watch it
Seeing where the tokens go only helps if you can act on it. Squeezy turns the numbers into control: cap the spend, force a turn cheaper or stronger, and see exactly where it all went.
spend capmodel overridevisibility
when it adds up
Token bills grow one turn at a time. So do savings.
Each strategy works on a single turn, and that is exactly why it matters at scale: the same waste repeats across every session, every day. Squeezy removes it before the request is sent, and keeps receipts, so the saving is a number you can check rather than a feeling.
Savings scale with usage
Re-read files, re-sent history, oversized output: the same waste repeats in almost every turn, and Squeezy trims it every time. The saving grows with every session, every seat, every day.
A bill you can explain
The savings ledger records every avoided byte and estimated dollar, labeled measured, deterministic, or estimate, and exports a report. What was spent and what wasn't are both on the record.
Only the focused request leaves
Repository analysis happens on your machine. What crosses the network is the prepared request to your own provider, with edits, shell, and web access behind permissions you set.
your model
Bring your own key. Squeezy keeps the saving local.
Run Squeezy against 27 providers: first-party APIs, aggregators, cloud hosts, local runtimes, or any OpenAI-compatible endpoint. The context work happens on your machine, before the call.