PagentRequest a testRequest

Free AI assistants you can use in iMessage on iPhone

Which AI assistants list iMessage and a free plan or free tier, and how do they score across our ten tests?

10 assistants ranked

Ten assistants in our catalog list iMessage and a free plan or free tier, and each took at least four of our ten tests. Pally (8.1 over eight tests) and Neo (8.1 over all ten tests) lead, then Ollie (7.8 over eight tests), Caddy (7.2 over six tests) and Wajo / Fo (7.1 over all ten tests). OpenInstinct (6.0 over five tests), Nessi (5.4 over five tests), Ka (5.2 over five tests), OpenClaw (5.1 over all ten tests) and Alfi by Text.ai (4.6 over five tests) follow.

Top picks

  1. 1
    PallyTop pickFastest that's still good

    Tested on 8 of 10Best: Routines10, Purchasing9Time to finish 7m 1s

    Free · iMessage, SMS, WhatsApp, Telegram · 86% positive in 38 public quotes

    8.1
  2. 2

    Tested on 10 of 10Best: Travel9, Phone calls9

    Free tier · Telegram, iMessage

    8.1
  3. 3

    Tested on 8 of 10Best: Online tasks9, Routines9

    Free tier · iMessage, SMS · 76% positive in 44 public quotes

    7.8
  4. 4

    Tested on 6 of 10Best: Travel9, Online tasks8

    Free tier · iMessage, SMS · 86% positive in 26 public quotes

    7.2
  5. 5

    Tested on 10 of 10Best: Connected apps10, Phone calls9

    Free tier · iMessage, SMS, Telegram, App · 100% positive in 43 public quotes

    7.1

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

#AssistantOnline tasksTravelPurchasingPhone callsEmailProactiveRoutinesConnected appsPermissionsMemoryAverage
1Pally779N/A791079—8.1
2Neo79896989888.1
3Ollie977N/A78978—7.8
4Caddy897N/A7——6—67.2
5Wajo / Fo258979710777.1
6OpenInstinct10———3——6746.0
7Nessi————75—5645.4
8Ka—6—6——54—55.2
9OpenClaw73634577455.1
10Alfi by Text.ai——446—54——4.6

How this report works

Included are assistants whose catalog entry (checked 2026-10-26) lists iMessage as a channel and either a free plan or a free tier with paid upgrades, with at least four of our ten tests taken, ranked by the average of the tests they took. Pally and Neo both round to 8.1; Pally's average is slightly higher.

How to choose

  • Check what happens after the free start. Ka lists $14.99 a month, Ollie $25 and Neo $49; Caddy, Wajo / Fo and Alfi list no price, and Pally, OpenInstinct, Nessi and OpenClaw are free.
  • See whether you need another app. Pally, Ollie, Caddy and Ka list only messaging channels; Neo adds Telegram, and Wajo / Fo, OpenInstinct, Nessi, OpenClaw and Alfi list an app too.
  • Check the data default before you share anything sensitive. Each assistant's page shows what its policy says about training on your data, and our report on assistants that do not train on your data lists the ones that say they don't.

Is there a free AI assistant for iMessage?

Ten list iMessage with a free plan or free tier. Pally 8.1 over eight tests, Neo 8.1 over ten and Ollie 7.8 over eight lead on average.

Do these work on Android too?

Some list SMS, WhatsApp or Telegram as well, such as Pally, Wajo / Fo and Alfi, but iMessage itself is Apple only.

Which free iMessage assistant took every test?

Neo, Wajo / Fo and OpenClaw took all ten. They average 8.1, 7.1 and 5.1.

What users say

Wajo / Fo · @samwarren ·

I’ve paired Fo with my creative director agent and they workshop X posts in my text group chat every morning lmao

Open source
Wajo / Fo · @qqazzrh ·

Try Fo @wajo_ai, which does an amazing job at voice calls and so many other things.

Open source
Caddy · @hudsonliao ·

Caddy finding a $2 beer pays for itself already

Open source
Pally · @Abrahammetaa ·

Pally asks me before sending each message out to clients but now Pallyai can attend to my photography clients without asking me, it's all automated.

Open source

Frequently asked questions

Which assistant is best for this?

Pally leads with an average of 8.1, ahead of Neo and Ollie.

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.

Related reports