Get an audit

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

Hermes Agent vs Orchid

Hermes Agent scores 67.9 (B) on agent readiness against Orchid's 20.2 (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

Hermes AgentNous Research · Agent harness B67.9/100#244 of 1010 OrchidZero Email, Inc. · Platform F20.2/100#992 of 1010

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

  • Reliability, 57 against 50
  • Schema & documentation, 80 against 10
  • Agent ergonomics, 80 against 0
  • Security & auth, 75 against 0
  • Payments & pricing, 60 against 10
  • Maintenance & community, 84 against 24

Also in its favour

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

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

Orchid F

Best for A founder or operator who wants Gmail and calendar triage by text with approval before anything leaves.

Also in its favour

  • No incidents deducted, where Hermes Agent loses 3 points for them

Watch for

No API, MCP server or A2A endpoint for an outside agent.

Score by category

CategoryWeight this runHermes AgentOrchidEdge
Reliability16%205750Hermes Agent +7
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.28010Hermes Agent +70
Agent ergonomics13%16.2800Hermes Agent +80
Security & auth14%17.5750Hermes Agent +75
Payments & pricing10%12.56010Hermes Agent +50
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.88424Hermes Agent +60
Transparency & trust7%8.86360Hermes Agent +3
Negative events≤15-30
TotalB 67.9/100F 20.2/100

Facts side by side

FactHermes AgentOrchid
KindAgent harnessPlatform
VendorNous ResearchZero Email, Inc.
Hosted endpointno (local only)no (local only)
Transports
AuthNoneOAuth or key
PricingFreePaid
x402nono
LicenceMITClosed service under Orchid's Terms of Service (Zero Email, Inc., last updated 16 January 2026).
Read-only variant documentednono
llms.txtyesyes
Last release2026-10-11none
Terms last updatedno document linked
Privacy policy last updatedno document linked
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 starsnone

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.

Orchid

Orchid is a paid executive assistant over iMessage, SMS and Telegram that holds drafts and calendar holds until the owner approves, with a public status page and a named subprocessor list. No outside agent can call it, there's no free tier, and its privacy policy allows training a personal model while its blog says it never trains.

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

Orchid

  1. Don't plan to call Orchid from another agent. It answers only the owner's iMessage, SMS and Telegram threads.
  2. Check status.orchid.ai before telling the owner Orchid is down. The 7 August incident moved it to a new number.
  3. Tell the owner that drafts and holds wait for their approval unless they widen it.

Questions

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

Hermes Agent scores 67.9 (B) on agent readiness against Orchid's 20.2 (F), and leads in every scored category.

Are Hermes Agent and Orchid open source?

Hermes Agent is open source (MIT). No open-source release is listed for Orchid.

Other comparisons with Hermes Agent or Orchid

Disclosure

Orchid 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