Rabbit R1 alternatives: AI assistants for online tasks, purchasing, memory and permissions
What can I use instead of a Rabbit R1 if I want an assistant that handles online tasks and purchases, remembers me and asks before it acts?
19 assistants ranked
Nineteen of the 47 assistants in our catalog took all four tests closest to what Rabbit's site describes: online tasks, purchasing, memory and permissions. Instinct leads at 8.25, then Neo and Dots at 7.75 and szn at 7.5. Rabbit R1 is not in our catalog and we have not tested it, so this is a ranking of other assistants, not a comparison with the R1. Rabbit's site (read 2026-11-14) describes the r1 as a handheld device for OS3, its AI system, which works through multi-step jobs such as researching and comparing options, uses apps with your permission, and is also reached on the web and Telegram.
Top picks
- 18.3InstinctTop pick
Tested on 4 of 4Best: Memory10, Online tasks9
- 27.8NeoBest free option
Tested on 4 of 4Best: Purchasing8, Memory8
- 37.8DotsFastest that's still good
Tested on 4 of 4Best: Online tasks9, Memory8Time to finish 6m 51s
- 47.5
Tested on 4 of 4Best: Memory9, Purchasing8
- 57.0
Tested on 4 of 4Best: Permissions8, Online tasks7
Top pick: highest average here. Best free option: highest among assistants you can use for free. Fastest that's still good: quickest median time to finish among those averaging 7 or more.
Full ranking
| # | Assistant | Online tasks | Purchasing | Memory | Permissions | Average |
|---|---|---|---|---|---|---|
| 1 | Instinct | 9 | 9 | 10 | 5 | 8.3 |
| 2 | Neo | 7 | 8 | 8 | 8 | 7.8 |
| 3 | Dots | 9 | 7 | 8 | 7 | 7.8 |
| 4 | szn | 7 | 8 | 9 | 6 | 7.5 |
| 5 | Tomo | 7 | 6 | 7 | 8 | 7.0 |
| 6 | Familiar | 7 | 7 | 6 | 8 | 7.0 |
| 7 | Waldo | 6 | 6 | 8 | 7 | 6.8 |
| 8 | Buoy | 7 | 8 | 5 | 7 | 6.8 |
| 9 | Today | 8 | 8 | 5 | 4 | 6.3 |
| 10 | Wajo / Fo | 2 | 8 | 7 | 7 | 6.0 |
| 11 | Ask Ranger | 4 | 7 | 6 | 7 | 6.0 |
| 12 | Vellum | 4 | 4 | 7 | 7 | 5.5 |
| 13 | OpenClaw | 7 | 6 | 5 | 4 | 5.5 |
| 14 | Tab | 2 | 5 | 5 | 9 | 5.3 |
| 15 | Manus | 4 | 7 | 4 | 6 | 5.3 |
| 16 | Gemini Spark | 6 | 6 | 4 | 4 | 5.0 |
| 17 | Lucas | 4 | 5 | 5 | 6 | 5.0 |
| 18 | Del | 5 | 1 | 4 | 8 | 4.5 |
| 19 | AVA | 3 | 6 | 4 | 4 | 4.3 |
How this report works
Included are all assistants that took every one of Online task, Purchasing, Memory and Permissions & privacy, ranked by the average of the four. We test the assistant's replies and actions in a conversation, not hardware, so nothing here rates a device. It differs from the Manus alternatives report, which tests online tasks, travel and purchasing on a chosen list, and from the remembers-preferences report, which ranks memory, purchasing and travel and needs only three tests: this one adds Permissions, drops Travel and needs all four.
How to choose
- Look at Permissions next to the average. Instinct leads but scores 5 on permissions; Neo, Tomo and Familiar score 8 and Tab scores 9.
- Check the task columns. Instinct scores 9 on online tasks and 9 on purchasing, Dots scores 9 and 7, and Neo scores 7 and 8.
- Check how you reach it. Instinct and Dots list an app, Neo lists Telegram and iMessage, Tomo lists iMessage and SMS, and szn lists no channel in our catalog.
What can I use instead of a Rabbit R1?
Nineteen assistants took all four closest tests. Instinct averages 8.25, Neo and Dots 7.75. Rabbit R1 was not tested, so this is not a comparison with it.
Do these need a separate device?
Our catalog lists how you reach each assistant, such as an app, iMessage, SMS, WhatsApp or Telegram, and does not track hardware. Check each vendor's page for what you need.
Why are travel and phone calls not counted?
Rabbit's site, as read on 2026-11-14, centres on multi-step online jobs and permission to use apps, so this report uses online tasks, purchasing, memory and permissions. Travel and phone calls are in the ai-assistant-that-gets-things-done report.
Why is Rabbit R1 not in the ranking?
It is not in our catalog and we have not tested it. This page ranks other assistants on the same published tests.
What users say
One day, Instinct canceled a DoorDash order that was seriously delayed, forcing me to forfeit $64. (I'd explicitly told it to cancel only if I could get a refund.)
Open sourceLast week it told me 'NOT TO OPEN' an email from a friend inviting me to a backyard BBQ—it turned out to be a phishing scam.
Open sourceLike fully getting my timezone wrong, forgetting conversations from the prior week. It also wouldn’t respond and messages to me wouldn’t come through.
Open sourceFrequently asked questions
Which assistant is best for this?
Instinct leads with an average of 8.3, ahead of Neo and Dots.
Is there a good free option?
Neo is the highest-ranked assistant with a free plan, averaging 7.8.
How did you test these assistants?
Every assistant got the same published tests, word for word, scored from three checkpoints and the number of corrections it needed. Each test is on the Dimensions page.