Free AI assistants you can use on WhatsApp
Which AI assistants list WhatsApp and a free plan or free tier, and how do they score across our ten tests?
6 assistants ranked
Six assistants in our catalog list WhatsApp and a free plan or free tier, and each took at least four of our ten tests. Muse (9.0 over seven tests) leads, then Town (8.4 over five tests) and Pally (8.1 over eight tests). Luke (7.2 over six tests), OpenClaw (5.1 over all ten tests) and Alfi by Text.ai (4.6 over five tests) follow.
Top picks
- 19.0MuseTop pick
Tested on 7 of 10Best: Purchasing10, Email10
- 28.4TownFastest that's still good
Tested on 5 of 10Best: Connected apps10, Email9Time to finish 6m 30s
- 38.1
Tested on 8 of 10Best: Routines10, Purchasing9
- 47.2
Tested on 6 of 10Best: Travel9, Phone calls8
- 55.1
Tested on 10 of 10Best: Online tasks7, Routines7
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 | Travel | Purchasing | Phone calls | Proactive | Routines | Connected apps | Permissions | Memory | Average | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 1 | Muse | 8 | 7 | 10 | — | 10 | — | 10 | 9 | 9 | — | 9.0 |
| 2 | Town | — | — | — | — | 9 | — | 8 | 10 | 8 | 7 | 8.4 |
| 3 | Pally | 7 | 7 | 9 | N/A | 7 | 9 | 10 | 7 | 9 | — | 8.1 |
| 4 | Luke | 6 | 9 | — | 8 | 7 | — | 7 | — | — | 6 | 7.2 |
| 5 | OpenClaw | 7 | 3 | 6 | 3 | 4 | 5 | 7 | 7 | 4 | 5 | 5.1 |
| 6 | Alfi by Text.ai | — | — | 4 | 4 | 6 | — | 5 | 4 | — | — | 4.6 |
How this report works
Included are assistants whose catalog entry (checked 2026-10-26) lists WhatsApp 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. The number of tests taken is shown next to each average, so read it before comparing.
How to choose
- Check what free means. Pally, Luke and OpenClaw are free in our catalog, though OpenClaw is self-hosted and you pay your own model provider. Muse lists $20 a month, Town $15 with 30 free chat messages a month, and Alfi lists no price.
- Look at where else it works. Pally covers iMessage, SMS, WhatsApp and Telegram, Alfi adds an app, Town lists WhatsApp, Telegram and an app, and Muse WhatsApp and an app.
- 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.
Which free AI assistant works on WhatsApp?
Six list WhatsApp with a free plan or free tier. Muse 9.0 over seven tests, Town 8.4 over five and Pally 8.1 over eight lead on average; Pally and Luke are free outright.
Do I need an app to use them on WhatsApp?
Not for all of them. Pally lists only messaging channels (iMessage, SMS, WhatsApp, Telegram); Muse, Town, Luke, OpenClaw and Alfi also list an app.
Is a free WhatsApp assistant really free?
Pally, Luke and OpenClaw are free in our catalog, but OpenClaw has you pay your own model provider. Muse, Town and Alfi have free tiers with paid upgrades or message limits, so check the plan before relying on it.
What users say
The agent, which Meta launched on September 8, booked a Friday date night and made a packing schedule for my upcoming move. It also emailed a friend about a trip next month and made a planning document with places we want to visit.
Open sourceWhen I asked for a list of places to go for date night, it pulled up two options in my neighborhood that had been closed for years.
Open sourcethe memory just… drifts. Had it handling a simple multi-step task and it straight-up forgot a key detail from the same conversation 20 minutes earlier.
Open sourceIt figured out the Spotify API, wrote the skill itself, and now it just pings me.
Open sourceFrequently asked questions
Which assistant is best for this?
Muse leads with an average of 9.0, ahead of Town and Pally.
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.