Head to head · Assistants that act in your accounts · October 2026 research run
Poke vs Tomo
Poke scores 37.6 (F) on agent readiness against Tomo's 13.1 (F), and leads in 6 of 7 scored categories. Tomo leads on maintenance & community. Both do assistants that act in your accounts.
Best AI personal assistants that act for one person · All 314 assistants comparisons
Which one, for what
Poke F
Best for One person who wants an assistant in their text messages that reads and drafts mail, manages a calendar and reaches other apps through MCP.
Ahead on
- Reliability, 51 against 15
- Schema & documentation, 42 against 0
- Agent ergonomics, 30 against 0
- Security & auth, 24 against 0
- Payments & pricing, 30 against 10
- Transparency & trust, 58 against 47
Watch for
No documented setting for which actions need approval before Poke sends, deletes or spends. Release notes mention email draft approval only in passing
Tomo F
Best for People who want accountability, check-ins and reminders by text, including in group chats.
Ahead on
- Maintenance & community, 54 against 31
Watch for
No API, MCP server or A2A endpoint for an outside agent.
Score by category
| Category | Weight this run | Poke | Tomo | Edge |
|---|---|---|---|---|
| Reliability | 16%20 | 51 | 15 | Poke +36 |
| Performance | 10%pending | pending | pending | not scored in this run |
| Schema & documentation | 13%16.2 | 42 | 0 | Poke +42 |
| Agent ergonomics | 13%16.2 | 30 | 0 | Poke +30 |
| Security & auth | 14%17.5 | 24 | 0 | Poke +24 |
| Payments & pricing | 10%12.5 | 30 | 10 | Poke +20 |
| Task success | 10%pending | pending | pending | not scored in this run |
| Maintenance & community | 7%8.8 | 31 | 54 | Tomo +23 |
| Transparency & trust | 7%8.8 | 58 | 47 | Poke +11 |
| Negative events | ≤15 | 0 | 0 | |
| Total | F 37.6/100 | F 13.1/100 |
Facts side by side
| Fact | Poke | Tomo |
|---|---|---|
| Kind | Platform | Platform |
| Vendor | The Interaction Company of California Inc. | Mapo Labs, Inc. |
| Hosted endpoint | no (local only) | no (local only) |
| Transports | HTTP | |
| Auth | API key | OAuth or key |
| Pricing | Freemium | Paid |
| x402 | no | no |
| Licence | Proprietary service under Poke's Terms of Service. The poke npm package (CLI and Node.js SDK) declares MIT | Closed service under Tomo's Terms of Service (Mapo Labs, Inc., last updated 24 September 2026). |
| Read-only variant documented | no | no |
| llms.txt | yes | no |
| Last release | 2026-06-25 | 2026-09-29 |
| Terms last updated | 2026-03-17 | |
| Privacy policy last updated | 2026-09-11 | |
| Customer content may train models | yes | |
| Terms restrict automated access | yes | |
| Terms restrict benchmarking | yes | |
| Terms or service can change without notice | yes | |
| Arbitration or class-action waiver | yes |
Verdicts
Poke
Hosted assistant that answers in Apple Messages, WhatsApp, Telegram and RCS and acts in Gmail, Outlook, calendars and MCP servers. Plan prices and a status page are public. No approval settings, credential storage, model providers or retention periods are documented, and customer content trains models unless Maximum Privacy is selected.
Tomo
Tomo is a hosted personal AI over iMessage and an iOS app, centred on goals, check-ins and reminders, with regular iOS releases since April 2026. No outside agent can call it, there's no free plan, and no status page, security contact or subprocessor list was found.
Before you call either
Poke
- POST JSON to
https://poke.com/api/v1/inbound/api-messagewith a Bearer key from Kitchen. Legacypk_keys work only on the deprecated/api/v1/inbound-sms/webhook - Expect only
{"success": true}back. Poke's answer goes to the owner's message thread, not to the caller - Do not retry a POST blindly. No idempotency key is documented, and a repeated message may make Poke act twice
- Treat an API key as full access to the owner's mail, calendar and integrations. Create one key per automation and revoke it when done
- Avoid the prefilled integration link with
apiKeyin the query string for real secrets. Enter the key in the form or usenpx poke@latest mcp add -k
Tomo
- Don't plan to call Tomo from another agent. It answers only the owner's iMessage, group chats it's added to and the iOS app.
- Tell the owner that adding Tomo to a group chat applies its terms to every participant.
Questions
Which is better for AI agents, Poke or Tomo?
Poke scores 37.6 (F) on agent readiness against Tomo's 13.1 (F), and leads in 6 of 7 scored categories. Tomo leads on maintenance & community.
Other comparisons with Poke or Tomo
- AstrBot vs Poke
- CowAgent vs Poke
- GAIA vs Poke
- Gemini Spark vs Poke
- Grok Bot vs Poke
- Haven vs Poke
- Hermes Agent vs Poke
- Instinct vs Poke
- IronClaw vs Poke
- Leon vs Poke
- Lindy vs Poke
- nanobot vs Poke
- NanoClaw vs Poke
- Dots vs Poke
- OpenClaw vs Poke
- PicoClaw vs Poke
- Poke vs QwenPaw
- Poke vs ZeroClaw
- Poke vs Zo Computer
- CowAgent vs Tomo
- GAIA vs Tomo
- Gemini Spark vs Tomo
- Grok Bot vs Tomo
- Haven vs Tomo
- Hermes Agent vs Tomo
- Instinct vs Tomo
- IronClaw vs Tomo
- Leon vs Tomo
- Lindy vs Tomo
- nanobot vs Tomo
- NanoClaw vs Tomo
- Natura tinyNature vs Poke
- Natura tinyNature vs Tomo
- Dots vs Tomo
- OpenClaw vs Tomo
- Pally vs Poke
- Pally vs Tomo
- Poke vs Wajo (Fo)
- QwenPaw vs Tomo
- Tomo vs Wajo (Fo)
- Tomo vs ZeroClaw
- Tomo vs Zo Computer
- Poke vs Talorys
- Talorys vs Tomo
- AstrBot vs Tomo
- PicoClaw vs Tomo
Disclosure
Tomo competes with LocalGhost, which Anchor Terminal's founder builds. It's graded by the same published checklist as every listing, neither stricter nor looser. Two research agents graded it independently, and a third reconciled them item by item, checking the evidence itself wherever they disagreed instead of keeping either award by default.
Machine-readable
- This page as Markdown
/compare/poke-vs-tomo.md· slim.min.md· JSON.json(or sendAccept: text/markdown) - Each listing in full
/api/v1/tools/poke.json·/api/v1/tools/tomo.json - From a terminal
anchor compare poke tomo(the CLI) - Over MCP
compare_tools {"a": "poke", "b": "tomo"}at/mcp, no key