Back to search
sonjari
SkillWorks with CodexGitHub
Your PC does the work. You get the proof. Sonjari is a free local AI agent for Windows: web research, Excel and Word documents, and code. Works on its own, or takes on tasks from Claude and Codex. No meter.
Safety scan
A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.
Checked today
Badge for your README
Markdown
[](/listings/sonjari--sonjari)HTML
<a href="/listings/sonjari--sonjari"><img src="/api/listings/sonjari--sonjari/badge.svg" alt="findsafeskills safety rating" /></a>Install
i
What was scanned
The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.
README.md · README · 184 lines
- <h1 align="center">Sonjari (손자리)</h1>
- <p align="center">
- <b>An AI coworker that works in your own browser.</b><br>
- Runs on your GPU. No usage limits, no meter.
- </p>
- <p align="center">
- <b>The seat next to Claude Code.</b><br>
- When it runs out of usage or forgets after compaction, Sonjari picks it up.
- </p>
- <p align="center">
- <a href="LICENSE"><img alt="License: Apache-2.0" src="https://img.shields.io/badge/license-Apache--2.0-blue"></a>
- <img alt="Windows 10/11 x64" src="https://img.shields.io/badge/Windows-10%20%7C%2011%20x64-0078D4">
- <a href="https://apps.microsoft.com/detail/9N458V8HPTR2"><img alt="Microsoft Store" src="https://img.shields.io/badge/Microsoft%20Store-free-107C10"></a>
- <img alt="Runs on your GPU" src="https://img.shields.io/badge/runs%20on-your%20GPU-76B900">
- <a href="https://glama.ai/mcp/servers/sonjari/sonjari"><img alt="sonjari MCP server on Glama" src="https://glama.ai/mcp/servers/sonjari/sonjari/badges/score.svg" height="20"></a>
- </p>
- <p align="center">
- <a href="README.ko.md">한국어</a> ·
- <a href="https://sonjari.com">sonjari.com</a> ·
- <a href="CONTRIBUTING.md">Contributing</a> ·
- <a href="https://github.com/sonjari/sonjari/discussions">Discussions</a> ·
- <a href="SECURITY.md">Security</a>
- </p>
- ---
- ## An AI coworker in your own browser
- ```mermaid
- flowchart LR
- Y["You<br/>(app or phone)"] --> S["Sonjari<br/>on your GPU"]
- S -->|"opens · clicks · reads"| C["Your Chrome<br/>and files"]
- S --> R["Answer + file<br/>with the pages it read"]
- ```
- One sentence in, an Excel file out. Sonjari opens GitHub Trending, reads the top three Python repositories and saves name,
- stars and description as a table. Shown at about 9x; the real run took 2 min 46 s on an RTX 3090 with Qwen3.8 27B.
- https://github.com/user-attachments/assets/91763b31-fe72-4614-b574-b3457ef0518c
- | It does this | How | More |
- |---|---|---|
- | **Works in your logged-in Chrome — and you can watch** | Opens, clicks and reads pages in a Chrome profile on your PC. "Sonjari's computer" shows the page and the progress; add a note mid-task to change direction. Stops at login, CAPTCHA and payment and hands the screen to you. | [Browser](docs/guide/browser.md) |
- | **A job it did well once, it follows next time** | After a clean run it offers to keep the steps as a recipe, each step with the result it should see. Next time it opens the right screen directly and checks every step. | [Recipes](docs/guide/recipes.md) |
- | **Give it work from your phone** | Message your own Discord bot; the PC at home does the job and answers in the same chat. Approvals stay on the PC. | [Discord](docs/guide/remote.md) |
- ## The seat next to Claude Code
- ```mermaid
- flowchart LR
- CC["Claude Code · Codex · Cursor"] -->|"sonjari_task (MCP)"| S["Sonjari reads<br/>on this PC"]
- S -->|"only the result + a receipt"| CC
- L["Conversation logs"] -->|"scribe, while idle"| K["Cards: decided ·<br/>dropped · left to do"]
- K -->|"after compaction"| CC
- ```
- Claude Code hands the research to Sonjari over MCP. Sonjari reads the release page on this PC and only the answer, its
- source and a short receipt go back to Claude. Claude then checks it. Shown at 4x.
- https://github.com/user-attachments/assets/415a77b1-6126-45cb-afd3-88bf71ddbea9
- | It does this | How | More |
- |---|---|---|
- | **Your Claude, Codex or Cursor hands it the heavy reading** | `sonjari_task` over MCP. Pages are read on this PC; only the result comes back, so the host's context and usage are spared. In one price task, Claude's cost per complete row was $0.074–0.100 with Sonjari against $0.246 alone. | [MCP guide](docs/guide/mcp.md) |
- | **Picks up where Claude Code stopped at a usage limit** | Finds, from the records on this PC, which conversation stopped and how far it got, and asks how to continue. Code changes go to a separate branch. | [How we use it](docs/guide/workflows.md) |
- | **Keeps what you decided, even after compaction** | The scribe reads your Claude Code logs while Sonjari is idle and writes cards — decided, dropped, left to do — each with a line number and a quote. They go back to Claude right after a compaction. Off by default. | [Scribe](docs/guide/scribe.md) |
- ## What do you use your subagents for?
- A subagent, done properly: it takes the tedious part, does it on its own, and brings back only what you need.
- Your main agent should do the thinking. A subagent should take the part that is tedious and expensive: clicking through a
- booking site, reading twenty pages, filling in a form. In most setups that part still runs on the same paid model and the
- same usage limit.
- **Why an agent, not a set of tools.** We could have shipped Sonjari as browser tools for your AI. But then your AI still
- pays to read every page through its own context — the meter just moves from the agent to the hands. Sonjari is built on
- one premise: cut what you spend on the AI platform you already use. So it does the whole job on your GPU and sends back
- only the result.
- **Why we rebuilt the tools.** For the same reason, we took the browser tools apart and wrote our own, so a page comes back
- as the part that matters, not the whole page. We did not wrap an existing agent framework. The browser tools are where most
- of the work went.
- Same price task, Claude Code (`claude-sonnet-5`) in charge, 27 rows per way:
- | How Claude got the pages | Claude cost per complete row |
- |---|---|
- | A general browser tool (Playwright MCP) | $0.635 |
- | Claude alone (web fetch and search) | $0.246 |
- | Sonjari's browser tools, driven by Claude | $0.074–0.100 |
- | The whole task handed to Sonjari | $0.075–0.090 |
- Small numbers, some rows graded by hand, and slower: 6–7 minutes a task against about 1.5 for Claude alone.
- Every caveat: [What we measured](docs/guide/measurements.md#with-claude-code--same-task-clean-setup).
- It is not as smart as your main agent, and it is built not to pretend otherwise — every result says where it looked, so
- you or your main agent can check it.
- ## Will it run on my PC?
- | You need | |
- |---|---|
- | Windows | 10 (19041) or later, x64 |
- | GPU | NVIDIA (see the table below) |
- | [Ollama](https://ollama.com) | the first-run wizard offers to install it |
- | Chrome | for browser tasks (Edge works if Chrome is not installed) |
- | Your graphics card | What Sonjari recommends |
- |---|---|
- | RTX 3090 · 4090 · 5090 (24 GB or more) | the largest model (27B) |
- | RTX 4060 Ti 16GB · 4070 Ti Super · 4080 · 5070 Ti · 5080 (16 GB) | a compressed build of the same model |
- | RTX 3060 12GB · 4070 · 5070 (12 GB) | the mid-size model (9B) |
- | RTX 3060 Ti · 3070 · 4060 · laptop 4060 · 5050 (8 GB) | the mid-size model (9B), compressed, text only (no picture reading) |
- | laptop 3050 · 4050 (6 GB) | the small model (4B), compressed, text only — weak; best shared with the AI you already use |
- ## Install
- 1. Get it from the [Microsoft Store](https://apps.microsoft.com/detail/9N458V8HPTR2) — free, updates itself.
- 2. On first launch the wizard measures this PC, picks a model that fits, downloads it (several GB) and runs it once to
- check. ([Watch the first run](https://github.com/user-attachments/assets/c6dd2281-8981-404d-9222-d9f1534f79bc))
- 3. Press **Connect** in the app to add Sonjari to Claude Code, Claude Desktop, Codex or Cursor. The original config is
- backed up first. By hand: [MCP guide](docs/guide/mcp.md).
- Build from source: [Developing](#developing).
- ## Why you can check it
- - **It shows where it looked.** Every run leaves its steps, the pages it read and where each value came from.
- - **It flags what it cannot back up.** A number no tool returned is marked, and a job that did not finish says where it stopped.
- - **You press the irreversible buttons.** Sending, publishing, paying and deleting wait for an approval card in the app.
- Every number we have, including the runs that went badly: [What we measured](docs/guide/measurements.md).
- **Where it falls short:** Windows and NVIDIA only · slower than cloud AI · on small cards, long research gets about halfway ·
- fiddly page controls (autocomplete, date pickers, cookie overlays) fail often.
- ## Documentation
- | I want to … | Read |
- |---|---|
- | see how the maintainers use it day to day, with real numbers | [How we use it](docs/guide/workflows.md) |
- | use Sonjari from Claude Code, Codex or Cursor | [MCP guide](docs/guide/mcp.md) |
- | know exactly what leaves my PC when another AI uses Sonjari | [What leaves your PC](docs/guide/privacy.md) |
- | understand which model I got and what to do if it does not fit | [How Sonjari picks a model](docs/guide/models.md) |
- | add know-how or a whole field — skills, skill packs, domain packs (games, video) | [Skills and packs](docs/guide/packs.md) |
- | see every measurement and its limits | [What we measured](docs/guide/measurements.md) |
- | read the rules it keeps — local first, no meter, honest results, you press the irreversible buttons | [Principles](docs/why.md) |
- ## Contributing
- > **Whatever your work is, your field experience is Sonjari's teacher.**
- > Every failure you report becomes a test Sonjari must pass, forever.
- Measure it on your card, fix one site with a two-line JSON file, report a run that went wrong, write a text-only skill
- pack, or send code with one test. Details: [CONTRIBUTING.md](CONTRIBUTING.md).
- ## Developing
- ```powershell
- powershell -NoProfile -ExecutionPolicy Bypass -File scripts\install.ps1
- .venv\Scripts\python.exe -m alture_jarvis
- .venv\Scripts\python.exe -m pytest tests -q -p no:cacheprovider
- cd ui; npm ci; npm run build
- ```
- Copy `.env.example` to `.env` only if you need to change a default. Never commit `.env`, `data/`, OAuth tokens or browser
- profiles. Internal names (`alture_jarvis` package, `JARVIS_*` variables, `X-JARVIS-TOKEN` header) come from the project's
- earlier name and are kept so existing installs keep working.
- Sonjari is maintained by two people, so replies can be slow. Much of the code is written with Claude (Anthropic) as a coding
- collaborator — commits carry a `Co-Authored-By` line — and every change is run, checked and released by the maintainers.
- ## License
- Apache License 2.0 — see [LICENSE](LICENSE) and [NOTICE](NOTICE).
- Third-party components keep their own licenses; see `packaging/THIRD_PARTY_NOTICES.md`.
- The optional camera module uses Ultralytics YOLO (AGPL-3.0); it is **not** installed by default.
- "Sonjari", "손자리" and the Sonjari logo are trademarks. The license covers the code, not the name or logo
- (Apache-2.0, section 6). Forks are welcome under a different name.
Ratings and comments
Sign in to rate this skill.
Sign inFree to use. If it’s helped, pass it on.