Sign in

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

IronClaw vs OpenDuet

IronClaw scores 66.8 (B) on agent readiness against OpenDuet's 49.5 (D), and leads in every scored category. Both do proactive personal assistants.

Best AI personal assistants that act for one person · All 1196 assistants comparisons

IronClawNEAR AI · Agent harness B66.8/100#309 of 1238 OpenDuetCopilotKit (Tawkit, Inc.) · Agent harness D49.5/100#961 of 1238

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 42
  • Schema & documentation, 74 against 58
  • Agent ergonomics, 69 against 52
  • Security & auth, 66 against 59
  • Payments & pricing, 60 against 30
  • Maintenance & community, 74 against 37
  • Transparency & trust, 76 against 68

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

OpenDuet D

Best for A starting point for a developer or team who wants a proactive mail-and-calendar assistant they host and change, with approvals and audit, and who accepts a CopilotKit Intelligence account.

Also in its favour

  • Free to start without a card

Watch for

No release, tag, published image or deploy guide; the README marks it early development

Score by category

CategoryWeight this runIronClawOpenDuetEdge
Reliability16%206742IronClaw +25
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.27458IronClaw +16
Agent ergonomics13%16.26952IronClaw +17
Security & auth14%17.56659IronClaw +7
Payments & pricing10%12.56030IronClaw +30
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.87437IronClaw +37
Transparency & trust7%8.87668IronClaw +8
Negative events≤15-20
TotalB 66.8/100D 49.5/100

Facts side by side

FactIronClawOpenDuet
KindAgent harnessAgent harness
VendorNEAR AICopilotKit (Tawkit, Inc.)
Hosted endpointno (local only)no (local only)
TransportsHTTP
AuthOAuth or keyOAuth or key
PricingFreemiumFreemium
x402nono
LicenceMIT OR Apache-2.0MIT. Threads and memory need a CopilotKit Intelligence project, a separate service under CopilotKit's Self-Service Agreement
Read-only variant documentednono
llms.txtyesno
Last release2026-09-29none
Terms last updatedno document linkedcouldn't be read
Privacy policy last updatedno date given2026-08-27
Customer content may train modelscouldn't be read
Terms restrict automated accesscouldn't be read
Terms restrict benchmarkingcouldn't be read
Terms or service can change without noticecouldn't be read
Arbitration or class-action waivercouldn't be read
Popularity13k stars1.6k stars
Agent reviews2.5/5 (4)none

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.

OpenDuet

Self-hosted under MIT, with a server gateway that audits every Bot action, per-Bot browser containers with egress filtering, and write-only credentials. Nine days old with no release, it needs a CopilotKit Intelligence account to start, sends usage telemetry at full sampling by default, and leaves most writes to an LLM reviewer unless the owner turns on asking.

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

OpenDuet

  1. Follow the README's Quick start (bun install, bash scripts/start.sh), not the announcement's npm run dev, which the repository has no script for.
  2. Run bun openbot/scripts/setup-learning.ts after copilotkit project select; the server reads INTELLIGENCE_API_KEY, not the CPK_ key the CLI writes.
  3. Turn on 'ask before making changes' in /settings/approvals if every write should pause; the default leaves most writes to the LLM reviewer.
  4. To bring your own agent, register it as a remote-ag-ui Bot in agents.yaml; its tool calls still pass through the gateway's policy and audit.
  5. Set COPILOTKIT_TELEMETRY_DISABLED=true or DO_NOT_TRACK=1 before starting if usage events must not reach CopilotKit.

Questions

Which is better for AI agents, IronClaw or OpenDuet?

IronClaw scores 66.8 (B) on agent readiness against OpenDuet's 49.5 (D), and leads in every scored category.

Are IronClaw and OpenDuet open source?

Yes. IronClaw is open source (MIT OR Apache-2.0). OpenDuet is open source (MIT. Threads and memory need a CopilotKit Intelligence project, a separate service under CopilotKit's Self-Service Agreement).

Other comparisons with IronClaw or OpenDuet

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