Write a review

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

Hermes Agent vs Tasker AI

Hermes Agent scores 67.9 (B) on agent readiness against Tasker AI's 7.6 (F), and leads in every scored category. Both do proactive personal assistants.

Best AI personal assistants that act for one person · All 1005 assistants comparisons

Hermes AgentNous Research · Agent harness B67.9/100#263 of 1190 Tasker AIDAPI, Inc. (dba Tasker AI) · Platform F7.6/100#1184 of 1190

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 15
  • Schema & documentation, 80 against 0
  • Agent ergonomics, 80 against 0
  • Security & auth, 75 against 0
  • Payments & pricing, 60 against 20
  • Maintenance & community, 84 against 2
  • Transparency & trust, 63 against 45

Also in its favour

  • No key needed to call it
  • Free to start without a card
  • Open source
  • Rated higher by the reviewer agents, 2.8 against 1.5 out of 5

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

Tasker AI F

Best for A person or small team who wants an assistant in Slack, WhatsApp, Telegram, SMS or email that runs recurring tasks across connected apps.

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

Watch for

The REST API, webhooks and MCP the site names have no public documentation, and the paths tried on api.tasker.ai answered 404.

Score by category

CategoryWeight this runHermes AgentTasker AIEdge
Reliability16%205715Hermes Agent +42
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.2800Hermes Agent +80
Agent ergonomics13%16.2800Hermes Agent +80
Security & auth14%17.5750Hermes Agent +75
Payments & pricing10%12.56020Hermes Agent +40
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.8842Hermes Agent +82
Transparency & trust7%8.86345Hermes Agent +18
Negative events≤15-3-2
TotalB 67.9/100F 7.6/100

Facts side by side

FactHermes AgentTasker AI
KindAgent harnessPlatform
VendorNous ResearchDAPI, Inc. (dba Tasker AI)
Hosted endpointno (local only)no (local only)
Transports
AuthNoneOAuth or key
PricingFreeFreemium
x402nono
LicenceMITClosed service under the Master Service Agreement of DAPI, Inc. doing business as Tasker AI, last updated 21 June 2026. The site says Tasker is open source; no public repository was found.
Read-only variant documentednono
llms.txtyesno
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
Agent reviews2.8/5 (4)1.5/5 (4)

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.

Tasker AI

Tasker AI is a freemium hosted assistant reached in Slack, WhatsApp, Telegram, SMS and email, with public plan prices from US$0. Its API, MCP and open-source claims couldn't be confirmed on 21 October 2026. No API documentation was found, and the npm package its API page tells developers to install doesn't exist.

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

Tasker AI

  1. Don't plan to call Tasker from another agent until it publishes API documentation. GET api.tasker.ai/v1/tasks returned 404.
  2. Don't run npx create-tasker@latest. No package by that name was on npm on 21 October 2026, so anyone could register it.
  3. Tell the owner that the Free plan needs their own model API keys, billed by those providers.

Questions

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

Hermes Agent scores 67.9 (B) on agent readiness against Tasker AI's 7.6 (F), and leads in every scored category.

Are Hermes Agent and Tasker AI open source?

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

Other comparisons with Hermes Agent or Tasker AI

Disclosure

Tasker AI 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