Get an audit

Head to head · Assistant proactive · October 2026 research run

Hermes Agent vs IronClaw

Hermes Agent scores 67.9 (B) on agent readiness against IronClaw's 66.7 (B), and leads in 4 of 7 scored categories. IronClaw leads on reliability and transparency & trust. Both do assistant proactive.

Best AI personal assistants that act for one person · All 190 assistants comparisons

Hermes AgentNous Research · Agent harness B67.9/100#244 of 986 IronClawNEAR AI · Agent harness B66.7/100#288 of 986

Which one, for what

Hermes Agent B

Best for A technical owner who wants one always-on agent across chat apps with memory and scheduled jobs, on their own machine or a small server, with any model.

Ahead on

  • Schema & documentation, 80 against 74
  • Agent ergonomics, 80 against 69
  • Security & auth, 75 against 66
  • Maintenance & community, 84 against 74

Also in its favour

  • No key needed to call it
  • Free to start without a card

Watch for

The default terminal backend runs commands on the host, and the default smart mode lets an auxiliary model approve commands it rates low-risk

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 57
  • Transparency & trust, 75 against 63

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

Score by category

CategoryWeight this runHermes AgentIronClawEdge
Reliability16%205767IronClaw +10
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.28074Hermes Agent +6
Agent ergonomics13%16.28069Hermes Agent +11
Security & auth14%17.57566Hermes Agent +9
Payments & pricing10%12.56060even
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.88474Hermes Agent +10
Transparency & trust7%8.86375IronClaw +12
Negative events≤15-3-2
TotalB 67.9/100B 66.7/100

Facts side by side

FactHermes AgentIronClaw
KindAgent harnessAgent harness
VendorNous ResearchNEAR AI
Hosted endpointno (local only)no (local only)
TransportsHTTP
AuthNoneOAuth or key
PricingFreeFreemium
x402nono
LicenceMITMIT OR Apache-2.0
Read-only variant documentednono
llms.txtyesyes
Last release2026-10-112026-09-29
Terms last updatedno document linkedno document linked
Privacy policy last updatedno document linkedno 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
Popularity253k stars13k stars

Verdicts

Hermes Agent

Card payments always ask first and are refused in unattended sessions, and the messaging gateway denies every sender until an allowlist is set. Shell commands run on the host by default with a model judging risk, and sending mail through the Google Workspace skill is held back only by an instruction to the model.

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.

Before you call either

Hermes Agent

  1. Set approvals.mode: manual before giving it real accounts. The default smart lets an auxiliary model approve commands
  2. Run the gateway with terminal.backend: docker or the project's Docker image when it reads mail, web pages or group chats
  3. Set memory.write_approval: true and skills.write_approval: true to review what it saves about the owner
  4. Leave approvals.cron_mode and approvals.unattended_mode at deny for scheduled and webhook runs
  5. Set TELEGRAM_ALLOWED_USERS or the matching allowlist per channel. Never set GATEWAY_ALLOW_ALL_USERS=true

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

Questions

Which is better for AI agents, Hermes Agent or IronClaw?

Hermes Agent scores 67.9 (B) on agent readiness against IronClaw's 66.7 (B), and leads in 4 of 7 scored categories. IronClaw leads on reliability and transparency & trust.

Are Hermes Agent and IronClaw open source?

Yes. Hermes Agent is open source (MIT). IronClaw is open source (MIT OR Apache-2.0).

Other comparisons with Hermes Agent or IronClaw

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