Head to head · Assistant proactive · October 2026 research run
Haven vs Poke
Poke scores 37.6 (F) on agent readiness against Haven's 22.2 (F), and leads in 5 of 7 scored categories. Both do assistant proactive.
Best AI personal assistants that act for one person · All 190 assistants comparisons
Which one, for what
Haven F
Best for A consumer assistant for one person who wants to phone, text or email it and have it remember them.
No category where it leads by five points or more, and no fact that sets it apart.
Watch for
No approval setting or list of actions that need confirmation was found on the public pages. The terms say it sends emails, SMS and calls following the user's instructions.
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 35
- Schema & documentation, 42 against 4
- Agent ergonomics, 30 against 6
- Security & auth, 24 against 13
- Transparency & trust, 58 against 51
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
Score by category
| Category | Weight this run | Haven | Poke | Edge |
|---|---|---|---|---|
| Reliability | 16%20 | 35 | 51 | Poke +16 |
| Performance | 10%pending | pending | pending | not scored in this run |
| Schema & documentation | 13%16.2 | 4 | 42 | Poke +38 |
| Agent ergonomics | 13%16.2 | 6 | 30 | Poke +24 |
| Security & auth | 14%17.5 | 13 | 24 | Poke +11 |
| Payments & pricing | 10%12.5 | 30 | 30 | even |
| Task success | 10%pending | pending | pending | not scored in this run |
| Maintenance & community | 7%8.8 | 35 | 31 | Haven +4 |
| Transparency & trust | 7%8.8 | 51 | 58 | Poke +7 |
| Negative events | ≤15 | 0 | 0 | |
| Total | F 22.2/100 | F 37.6/100 |
Facts side by side
| Fact | Haven | Poke |
|---|---|---|
| Kind | Platform | Platform |
| Vendor | Hello Haven, Inc. | The Interaction Company of California Inc. |
| Hosted endpoint | no (local only) | no (local only) |
| Transports | HTTP | HTTP |
| Auth | OAuth or key | API key |
| Pricing | Free | Freemium |
| x402 | no | no |
| Licence | Proprietary service under Hello Haven's Terms of Service | Proprietary service under Poke's Terms of Service. The poke npm package (CLI and Node.js SDK) declares MIT |
| Read-only variant documented | no | no |
| llms.txt | no | yes |
| Last release | 2026-09-17 | 2026-06-25 |
| Terms last updated | 2026-07-24 | 2026-03-17 |
| Privacy policy last updated | 2026-07-24 | 2026-09-11 |
| Customer content may train models | not found in the text | yes |
| Terms restrict automated access | not found in the text | yes |
| Terms restrict benchmarking | not found in the text | yes |
| Terms or service can change without notice | not found in the text | yes |
| Arbitration or class-action waiver | not found in the text | yes |
Verdicts
Haven
Haven answers by phone call, text, email and app, is free in beta with no card, and publishes a status page with dated incidents. No public page read says which actions need approval, which accounts it connects or how their tokens are kept, and it names no model provider or sub-processor.
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.
Before you call either
Haven
- Haven has no documented API or MCP server. An outside agent can reach it only through the owner's channels (call, SMS, email, app).
- Do not assume an approval step before Haven sends mail, texts or calls. None is documented on the public pages.
- Email Haven sends to other people names Hello Haven as sender and says it was sent on the user's behalf, per the terms.
- Chat messages, history, profile context and uploaded files go to third-party AI model providers that the vendor does not name.
- Check status.hellohaven.ai before relying on phone or voice. All four published incidents affected those channels.
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
Questions
Which is better for AI agents, Haven or Poke?
Poke scores 37.6 (F) on agent readiness against Haven's 22.2 (F), and leads in 5 of 7 scored categories.
Other comparisons with Haven or Poke
- AstrBot vs Haven
- AstrBot vs Poke
- CowAgent vs Haven
- CowAgent vs Poke
- GAIA vs Haven
- GAIA vs Poke
- Gemini Spark vs Haven
- Gemini Spark vs Poke
- Grok Bot vs Haven
- Grok Bot vs Poke
- Haven vs Hermes Agent
- Haven vs Instinct
- Haven vs IronClaw
- Haven vs Leon
- Haven vs Lindy
- Haven vs nanobot
- Haven vs NanoClaw
- Haven vs Dots
- Haven vs OpenClaw
- Haven vs PicoClaw
- Haven vs QwenPaw
- Haven vs ZeroClaw
- Haven vs Zo Computer
- 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
Machine-readable
- This page as Markdown
/compare/haven-vs-poke.md· slim.min.md· JSON.json(or sendAccept: text/markdown) - Each listing in full
/api/v1/tools/haven.json·/api/v1/tools/poke.json - From a terminal
anchor compare haven poke(the CLI) - Over MCP
compare_tools {"a": "haven", "b": "poke"}at/mcp, no key