Your Orb

Your own AI model. In your browser.

The Orb lives inside Skillerr and understands what you're working on: which tabs belong to one journey, what you and your AIs have already read, where you left off. It runs on your computer, learns from how you browse, and sends nothing to anyone. Not even us.

7.9 MBThe whole model. Smaller than a phone photo.
8 µsTo read a page title, on one CPU core. No GPU.
250×Faster than all-MiniLM-L6-v2, the transformer it learned from, at 1/11 the size.
0 bytesSent anywhere. It learns you on your computer, in about 70 ms.

Measured on a MacBook Air (M1, 8 GB). Details and how to reproduce them below.

What your Orb does

Sorts your tabs into journeys

Tabs you opened together stay together; journeys on different days join when they're about the same thing. Bring over the tabs you have open in Chrome and watch them arrive sorted, with their real icons. Nothing reloads, and nothing closes in Chrome.

Finds anything by meaning

Type what you remember in the address bar ("train from Tokyo to Kyoto", "newborn feeding") and the page you had comes back, scrolled where you were.

Recorded in Skillerr: open Chrome tabs arrive sorted into journeys, waiting left of the address bar.

Keeps your AIs' research

When Claude, Cursor or Codex browse through Skillerr, what they read becomes a trail beside your own: named after what they looked into, with their conclusion and sources. It's marked unfinished only from the facts: a page that couldn't open, a robot check, a step you declined.

Suggests skills from your habits

Research the same kind of thing the same way three times and the Orb offers to save how you do it as a skill your AI can follow. Worked out from your trails, with no AI model writing it.

The Skillerr window: Your AIs' research lists four research trails by Codex, Cursor and Claude Desktop, new or unfinished; the start page shows The Orb noticed a habit, with Save skill.
Your AIs' research, right of the address bar, and a habit the Orb noticed.

Learns you, privately

Every week (it asks first) your Orb learns your words from your own trails and your AIs' research, on your computer. It keeps what it learned only if that files your pages better. Each source can be switched off.

Shows you everything it knows

The Your Orb page (⇧⌘Y) maps everything you and your AIs looked into around the Orb: yours in warm colours, your AIs' in cool ones. Click the Orb for its size, memory and speed, live.

The Your Orb page: a glowing orb at the centre, with rays of light out to 81 things looked into, yours warm and your AIs' cool.
The Orb's own panel: Yours, on this computer. 7.9 MB on disk, 8.1 MB of memory, 30,522 words it knows, and how fast it is.

Benchmarks

Everything here was measured on a MacBook Air (M1, 8 GB) with scripts anyone can run (scripts/kilr/ in the Skillerr repository). Where another model does better, it says so.

Speed and size, one text at a time (as a browser meets them)

Per page titlePer secondModel sizeMemory
Your Orb (one core)8.4 µs~120,0007.9 MB~30 MB
all-MiniLM-L6-v2, 4 threads2,171 µs46690 MB~140–230 MB
all-MiniLM-L6-v2, 1 thread4,690 µs21390 MB~100–120 MB

all-MiniLM-L6-v2 run with ONNX Runtime (native code): the Orb is over 250× faster than it on 4 threads, and about 550× faster on one. On a GPU, in large batches, a transformer gets through more text per second; a browser meets titles one at a time, on your CPU.

Sorting tabs kept open for weeks into journeys

PrecisionF1F1 when a quarter of titles say nothing ("Log In")
Your Orb (sittings joined by meaning)0.910.830.79
Same rule, with all-MiniLM-L6-v2 (90 MB)–0.850.81
Word matching1.000.250.19

87 tabs from 14 threads of work, opened over sittings across four weeks, 20 random layouts. The Orb reaches 98% of all-MiniLM-L6-v2's accuracy on this job (F1 0.83 vs 0.85).

Real people's searches: Webis-SMC-12

8,840 searches by 127 people, split into tasks by two human annotators (Hagen et al., 2013). Deciding where one search session ends and the next begins, F1.5 as in the paper:

F1.5Needs the web?
Your Orb, with Skillerr's journey model0.922No, on your computer
Best published, without web lookups0.930No
Best published, with search-engine results0.946Yes

Tuned on a quarter of the people and tested on the rest, as in the paper; our split is by person, theirs isn't published, so the numbers are close to comparable, not identical.

General sentence similarity (STS-B, SICK)

STS-BSICKSize
all-MiniLM-L6-v2 (the transformer the Orb learned from)82.177.190 MB
potion-base-8M (static, open)75.464.530 MB
Your Orb72.362.97.9 MB
Word overlap56.557.5–

Spearman × 100 against human scores; neither test set is used to build the Orb. General sentence similarity isn't the Orb's job, and bigger models do better here.

Yours, not ours

On your computer

The model, what it learns and your trails stay in Skillerr's folder on your machine. It works offline.

Nothing sent

The Orb makes no network requests. Watch it with any network monitor while you browse.

Yours to reset

Forget what it learned, or turn it off, in Trails settings. Clear browsing data clears it all.

When you let an AI app like Claude browse through Skillerr, the pages it reads go to that AI, as they would in any browser. The Orb itself never sends anything. It chooses from the facts of your own trails and never writes text, so it can't make things up.

Only in Skillerr

Your Orb comes with Skillerr, the browser that skills your AI. Free for Mac, Windows and Linux.