Your PC does the work. You get the proof.
Sonjari is a free AI agent for Windows. It works in your own Chrome, files and documents, on a model running on your GPU, and it shows you what it actually read. No API keys, and no meter, not even for web search.
- No meter on anything that runs on your PC
- Picks up when Claude Code or Codex hits its limit
- Every run leaves receipts you can check
Windows 10/11 · NVIDIA GPU · Private beta on the Microsoft Store
교보문고에서 '파이썬' 책 3권을 찾아 제목·판매가·적립 포인트를 엑셀로 정리해 줘 “Find 3 books for ‘Python’ on Kyobo Book Centre and put title, price and reward points in a spreadsheet.” Redrawn from the record of a real run · 28 Sep 2026, 23:51 KST · one RTX 3090 PC · 9 steps, 0 failed · run 026df5bd
Same task, in the real app
The answer on the left, the file it made, and the requirement check at 3/3. On the right, Sonjari’s computer: the step ruler and the page it read last.
What we promise, and how it's going
A promise without a record is a slogan. Each one below has the number we measured, how many runs, and when. When we break one, it stays on this page.
-
It won't take your mouse.
KeptChrome used to jump in front of your work when a task started. It did in 7 of 8 runs. After the fix, 0 of 8.
n=8 · 2026-09-21 -
It says so when it couldn't do it.
Broken onceHonesty bench: asked across 3 routes with 3 questions, it pretended to have read something 0 times out of 9.
n=9 · 2026-09-3028 Sep 2026: in one run it reported a task as done after copying a recommendation banner, with no warning. We fixed the checker the same night. The rematch that night: 0 false completions in 6 runs.
-
No meter on what runs on your PC.
KeptThe model runs on your GPU. Web search runs in your own Chrome, so there is no search API key and nothing to top up. We don't spend your Claude or ChatGPT subscription behind your back.
How it's built, not a benchmark
It works next to the AI you already pay for
When Claude hits its limit, keep going
Tell Sonjari you're out. It finds where Claude Code or Codex stopped, puts that work on a new branch and carries on locally.
Spotting the stop: caught 52 of 52 stopped sessions, 1 false alarm in 458 ordinary messages. How often the handed-over work gets finished: not measured yet.
Hands for your frontier model
Connect it to Claude Code, Codex or the Claude app over MCP. The frontier model plans; Sonjari does the reading and clicking on your PC and sends back the result.
Handing web research to Sonjari cut the host's cost by 27–34% per task and took about 3× longer. 48 runs, 2026-09-23.
Your files stay on your disk
Excel, Word and HWP files are read and written on your PC. Nothing leaves it unless you send it, and a bug report shows you exactly what it will send first.
The run above wrote its spreadsheet to your Documents folder and re-checked it: 4 rows.
What it can't do yet
- Windows only. Windows 10 or 11.
- It needs an NVIDIA GPU. 8 GB of VRAM runs the small model. More VRAM runs bigger ones.
- It is slower than the cloud. Web research took about 3× longer than Claude doing it alone. On one coding task Hermes Agent was about 2× faster.
- The app screens are in Korean today. The English interface is being built.
- Our wins are on Korean websites. We haven't benchmarked English sites yet.
- It is in private beta. Expect rough edges and tell us about them.
Every run we measured, including the ones we lost
Newest first. Each line says what we tried, how many runs, and what happened.
Try it on your PC.
The beta ships through the Microsoft Store, so it installs in one click and updates itself. We invite people in small batches and read every report.
hello@sonjari.comSource code opens on GitHub under Apache-2.0 with the public release.