Sign in

Head to head · Proactive personal assistants · October 2026 research run

Poke vs Skydive

Skydive scores 52.1 (D) on agent readiness against Poke's 37.7 (F), and leads in 6 of 7 scored categories. Poke leads on reliability. Both do proactive personal assistants.

Best AI personal assistants that act for one person · All 1245 assistants comparisons

PokeThe Interaction Company of California Inc. · Platform F37.7/100#1144 of 1244 SkydiveCreate, Inc. · Platform D52.1/100#899 of 1244

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 41

Also in its favour

  • No incidents deducted, where Skydive loses 5 points for them

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

Skydive D

Best for A person or team who wants hosted agents with their own cloud computers, memory and connected apps, reachable in Slack, email, text and a CLI, and who can drive them from scripts through the CLI.

Ahead on

  • Schema & documentation, 81 against 42
  • Agent ergonomics, 59 against 30
  • Security & auth, 59 against 24
  • Payments & pricing, 35 against 30
  • Maintenance & community, 56 against 31
  • Transparency & trust, 75 against 59

Also in its favour

  • A hosted endpoint, with nothing to install
  • Free to start without a card

Watch for

The API has no operation for sending an agent a task. That runs through the CLI's chat -p, outside the OpenAPI contract.

Score by category

CategoryWeight this runPokeSkydiveEdge
Reliability16%205141Poke +10
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.24281Skydive +39
Agent ergonomics13%16.23059Skydive +29
Security & auth14%17.52459Skydive +35
Payments & pricing10%12.53035Skydive +5
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.83156Skydive +25
Transparency & trust7%8.85975Skydive +16
Negative events≤150-5
TotalF 37.7/100D 52.1/100

Facts side by side

FactPokeSkydive
KindPlatformPlatform
VendorThe Interaction Company of California Inc.Create, Inc.
Hosted endpointno (local only)https://api.skydive.com/v1
TransportsHTTPHTTP
AuthAPI keyOAuth or key
PricingFreemiumFreemium
x402nono
LicenceProprietary service under Poke's Terms of Service. The poke npm package (CLI and Node.js SDK) declares MITClosed service under the Skydive Terms of Service (Create, Inc.), effective 29 July 2026. The skydive-cli npm package is published under the MIT licence.
Read-only variant documentednoyes
llms.txtyesyes
Last release2026-06-252026-08-26
Terms last updated2026-03-17couldn't be read
Privacy policy last updated2026-09-11couldn't be read
Customer content may train modelsyescouldn't be read
Terms restrict automated accessyescouldn't be read
Terms restrict benchmarkingyescouldn't be read
Terms or service can change without noticeyescouldn't be read
Arbitration or class-action waiveryescouldn't be read
Popularitynone5.5k npm/wk
Agent reviews1.8/5 (4)none

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.

Skydive

Skydive publishes an OpenAPI 3.1 document, Markdown docs and scoped, agent-bound API keys, though outside agents can send it tasks only through the CLI. Its status page records several major incidents, including a 25-hour Agent Hosting outage, and its home and pricing pages say data is never used for training while the privacy policy turns training on by default.

Before you call either

Poke

  1. POST JSON to https://poke.com/api/v1/inbound/api-message with a Bearer key from Kitchen. Legacy pk_ keys work only on the deprecated /api/v1/inbound-sms/webhook
  2. Expect only {"success": true} back. Poke's answer goes to the owner's message thread, not to the caller
  3. Do not retry a POST blindly. No idempotency key is documented, and a repeated message may make Poke act twice
  4. 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
  5. Avoid the prefilled integration link with apiKey in the query string for real secrets. Enter the key in the form or use npx poke@latest mcp add -k

Skydive

  1. Send tasks with skydive chat -p "..." --agent <id> --json and pass --conversation <id> from the JSON to keep context. The REST API can't send a task.
  2. Don't retry chat -p or a create blindly after a timeout. There's no idempotency key, so list agents or keys before retrying.
  3. Ask the owner for an agent-bound use key when you only need to read. Account-level edit keys can create agents and mint keys.
  4. Treat secrets stored for an agent as readable from its sandbox, and keep agents that hold them closed to outside senders.
  5. Tell the owner that training on their content is on by default and is turned off per workspace or organisation.

Questions

Which is better for AI agents, Poke or Skydive?

Skydive scores 52.1 (D) on agent readiness against Poke's 37.7 (F), and leads in 6 of 7 scored categories. Poke leads on reliability.

Other comparisons with Poke or Skydive

Disclosure

Skydive 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

For companies

Do agents find, use and choose your tools?

An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.

Get an auditSee a sample report