Same model. Sharper agent.

Prove the30% savingson your own machine.

Run the read-only scan against your local agent history. Atelier cuts tool calls by up to 90% and input/output tokens by up to 80%, and shows where paid context is leaking: broad search, whole-file reads, verbose tool output, repeated rediscovery, and missing proof.

01 — Scan first

No install required.

02 — See the leak

Tokens, calls, and loops.

03 — Install second

Keep using Claude Code.

Fast path after the scan

Local install. No account required to start. Keep using Claude Code normally.

Raw runs →
$ curl -fsSL https://install.atelier.ws | bash
Read smarter. Think sharper. Talk less. Never forget.
Read smarterexact code ranges instead of file dumps/Think sharperless context spent rediscovering the same facts/Talk lesscompact output without losing commands or errors/Never forgetsession memory carries useful context forward/

Why it saves

Talk less saves output tokens.
A tighter loop saves the run.

This is not a caveman prompt telling the model to grunt. Atelier changes the runtime around the model: what it can find, what it reads, what tools return, and what carries into the next turn.

Loop stage
Search

BaselineThe agent asks for context and gets broad text back.

With AtelierRanked code search returns the likely files, symbols, and exact ranges.

Read

BaselineWhole files and repeated reads fill paid context.

With AtelierRange reads, outlines, and summaries keep only the useful source in view.

Output

BaselineTool output and assistant replies sprawl across the transcript.

With AtelierCompact results preserve commands, paths, errors, and diffs without filler.

Memory

BaselineEvery session rediscovers the same project facts.

With AtelierRecall and carry-forward context stop the loop from paying twice.

Without Ateliermore paid words

“I looked into the failing test and it seems like the flakiness is caused by the retry logic using a real clock. The test sleeps for 100ms and then asserts that exactly three retries happened, but under CI load the timing can drift, which makes the assertion fail intermittently. I’d recommend injecting a fake clock so the test becomes deterministic.”

With Ateliershorter, exact

“Root cause: retry test uses a real clock — 100ms sleep + exact 3-retry assert drifts under CI load. Fix: inject a fake clock; test becomes deterministic.”

While you work

See live savings add up in Claude Code

Screen recording of a Claude Code session using Atelier: the statusline shows cost, context usage, and token savings updating live as the agent works.

Proof, not a fake counter

The 30% claim comes from raw runs, not live badges.

Live badges show usage adding up. The benchmark claim comes from both arms running the same model, tasks, and environment. Every raw run is committed to the repo.

BenchmarkBaselineAtelierΔ correctBaseline $Atelier $Δ costSavings
SWE-bench Verified
50 tasks × 5 reps
80.8%92.8%+12.0 pp$234.84$165.4529.5% cheaper
SWE-bench Lite
10 tasks × 3 reps
93.3%100%+6.7 pp$12.38$10.7912.9% cheaper
SWE-bench Pro
10 tasks × 5 reps
88.0%90.0%+2.0 pp$39.01$30.6121.5% cheaper
Exploration
7 large repos × 5 reps
$19.11$6.2967% cheaper
Terminal-Bench 2.1
89 tasks vs public leaderboard*
78.9% exp.78.7%−0.2 pp$96.76$69.52†28.1% cheaper†
Telegraphic Q&A
20 prompts × 5 reps
$8.93$5.3440.2% cheaper

* Atelier: 1 rep/task; baseline: public tbench.ai leaderboard, 5-rep average. † A few tasks timed out before cost capture — real spend, not zero. Full methodology → BENCHMARKS.md. Per-suite breakdown → Atelier vs vanilla Claude Code.

Retrieval quality

It finds the right code — better than grep.

Mean Reciprocal Rank across ~7,200 query/answer pairs on 14 repos — every tool scored on the same corpus and the same query kinds. Higher is better.

Under the hood: tree-sitter parsing, a zoekt trigram index for the lexical channel, BGE-Code-v1 embeddings for the semantic one — full architecture →

ToolMRRp95p100
Atelier +semantic (BGE)
0.727390ms1057ms
Atelier lexical (default)
0.676134ms319ms
serena
0.4013834ms269001ms
ripgrep
0.37666ms522ms
code-index-mcp
0.343377ms3830ms
ast-grep
0.3121255ms8806ms
universal-ctags
0.2371ms12ms

At linux-kernel scale

4.5M lines, 42M tokens, one repo — still fast, and still finds the right answer.

ModeIndexing time
Atelier lexical (default)
2m 59s
Atelier +semantic (BGE)
23m 22s

See what each one claims about itself, per tool →. Full 13-tool table, latency, and methodology → BENCHMARKS.md.

60 seconds · read-only

Do not take our 30% claim on faith.

Run the read-only scan against your own Claude/Codex history before you install. It prints the savings estimate from your local files.

$ curl -fsSL https://savings.atelier.ws | bash

Scans local agent sessions · temporary store · no login · no API keys.

Honestly

The trust is the audit trail.

Anyone can fake a counter. Atelier earns trust three ways: raw benchmark runs are committed, the savings scanner checks your own machine, and rows where Atelier does not win stay in the table. Terminal-Bench 2.1 is flat on accuracy (-0.2pp) and only cheaper on cost.

Read the raw runs on GitHub →

Verify first. Install second.

Start the next session with proof, not promises.

SWE-bench Verified: 29.5% cheaper and +12.0pp more tasks solved. Same model, same tasks, same environment. Raw runs published.

Need it for a team? Large codebases, shared team memory, a cheaper agentic harness at scale.

Contact us about Enterprise