Head to head · Assistants reached by message · October 2026 research run

IronClaw vs Tab

IronClaw scores 66.7 (B) on agent readiness against Tab's 10.7 (F), and leads in every scored category. Both do assistants reached by message.

Best AI personal assistants that act for one person · All 834 assistants comparisons

Which one, for what

IronClaw B

Best for One technical owner who wants a self-hosted assistant over Gmail, Calendar, Slack and Telegram with credentials kept out of the model's reach.

Ahead on

  • Reliability, 67 against 5
  • Schema & documentation, 74 against 0
  • Agent ergonomics, 69 against 0
  • Security & auth, 66 against 4
  • Payments & pricing, 60 against 0
  • Maintenance & community, 74 against 58
  • Transparency & trust, 75 against 45

Also in its favour

  • Open source

Watch for

Global auto-approve defaults to on in the 1.4.1 source, so tools marked ask (send, trash, delete) run without a prompt. Only financial, approval and budget effects always ask

Tab F

Best for A person who wants a texting assistant that browses, calls and buys with tight checkout controls.

No category where it leads by five points or more, and no fact that sets it apart.

Watch for

Private beta behind a waitlist.

Score by category

CategoryWeight this runIronClawTabEdge
Reliability16%20675IronClaw +62
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.2740IronClaw +74
Agent ergonomics13%16.2690IronClaw +69
Security & auth14%17.5664IronClaw +62
Payments & pricing10%12.5600IronClaw +60
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.87458IronClaw +16
Transparency & trust7%8.87545IronClaw +30
Negative events≤15-20
TotalB 66.7/100F 10.7/100

Facts side by side

FactIronClawTab
KindAgent harnessPlatform
VendorNEAR AITerrasoft, Inc.
Hosted endpointno (local only)no (local only)
TransportsHTTP
AuthOAuth or keyOAuth or key
PricingFreemiumPaid
x402nono
LicenceMIT OR Apache-2.0Closed service under Tab's Terms of Use (Terrasoft, Inc., effective 2 September 2026).
Read-only variant documentednono
llms.txtyesno
Last release2026-09-29none
Terms last updatedno document linked
Privacy policy last updatedno date given
Customer content may train models
Terms restrict automated access
Terms restrict benchmarking
Terms or service can change without notice
Arbitration or class-action waiver
Popularity13k starsnone

Verdicts

IronClaw

Credentials stay in an encrypted store and are injected at the host boundary, and extensions declare per-tool permissions, network targets and OAuth scopes. The global auto-approve setting defaults to on in the 1.4.1 source, so tools marked ask, such as gmail.send_message, run unprompted until the owner turns it off.

Tab

Tab is a private-beta texting assistant with a detailed security page on credential isolation and checkout binding, and a public updates page. No outside agent can call it, no price is published, and its privacy policy says nothing on training with user content.

Before you call either

IronClaw

  1. Open Settings and turn off global auto-approve, or set send and delete tools to ask each time, before connecting mail or chat accounts
  2. Install with the release installer and run ironclaw onboard. 1.x does not migrate 0.29 data, so use a fresh home directory
  3. Call POST /api/v1/responses with the bearer token from ~/.ironclaw/reborn/webui-token. Keep under 30 requests in 60 seconds
  4. Resolve approval and OAuth gates in the web interface. The Responses API fails the turn instead of surfacing them
  5. Connect MCP servers over HTTP only. The stdio transport is rejected

Tab

  1. Don't plan to call Tab from another agent. It answers only the owner's Messages or WhatsApp thread.
  2. Tell the owner that access needs a waitlist place and no price is published.

Questions

Which is better for AI agents, IronClaw or Tab?

IronClaw scores 66.7 (B) on agent readiness against Tab's 10.7 (F), and leads in every scored category.

Are IronClaw and Tab open source?

IronClaw is open source (MIT OR Apache-2.0). No open-source release is listed for Tab.

Other comparisons with IronClaw or Tab

Disclosure

Tab 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.