Head to head · Assistants that remember you · October 2026 research run

LearnHarness vs Town

LearnHarness scores 59.3 (C) on agent readiness against Town's 48.7 (D), and leads in 5 of 7 scored categories. Town leads on security & auth. Both do assistants that remember you.

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

Which one, for what

LearnHarness C

Best for A tutor for one learner that keeps a local record of sessions and a graph of propositions and reasoning chains.

Ahead on

  • Reliability, 56 against 35
  • Schema & documentation, 63 against 33
  • Agent ergonomics, 60 against 49
  • Payments & pricing, 60 against 30
  • Maintenance & community, 71 against 60

Also in its favour

  • No key needed to call it
  • Open source

Watch for

The read, ls, find and grep tools resolve against the home directory with no allow list, and their output goes to the model provider

Town D

Best for An owner who wants a mail and calendar assistant whose routines other systems can trigger.

Ahead on

  • Security & auth, 79 against 52

Watch for

The privacy policy describes training with an opt-out and the trust page says training is opt-in.

Score by category

CategoryWeight this runLearnHarnessTownEdge
Reliability16%205635LearnHarness +21
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.26333LearnHarness +30
Agent ergonomics13%16.26049LearnHarness +11
Security & auth14%17.55279Town +27
Payments & pricing10%12.56030LearnHarness +30
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.87160LearnHarness +11
Transparency & trust7%8.86063Town +3
Negative events≤1500
TotalC 59.3/100D 48.7/100

Facts side by side

FactLearnHarnessTown
KindAgent harnessPlatform
VendorAmos BlomqvistTown.com, Inc.
Hosted endpointno (local only)no (local only)
TransportsHTTP
AuthNoneOAuth or key
PricingFreeFreemium
x402nono
LicenceAGPL-3.0-onlyClosed service under Town's Terms of Service (Town.com, Inc., updated 21 July 2026).
Read-only variant documentednoyes
llms.txtnono
Last release2026-10-292026-10-10
Terms last updatedno date given2026-07-21
Privacy policy last updatedno document linked2026-07-21
Customer content may train modelsnot found in the textyes, with an opt-out
Terms restrict automated accessnot found in the textyes
Terms restrict benchmarkingnot found in the textnot found in the text
Terms or service can change without noticenot found in the textnot found in the text
Arbitration or class-action waivernot found in the textyes
Popularity4.2k starsnone

Verdicts

LearnHarness

The in-app agent reads files but cannot change them or run commands, and a bundled skill gives other agents a documented read-only view of sessions and the knowledge graph. The project is 14 days old at 0.4.0, its file reads reach the whole home directory without approval, and it has no security policy.

Town

Town is a hosted assistant that works across the owner's mail, calendar and work apps, and other systems can start its routines through per-routine webhooks with rotatable secrets, idempotency keys and documented errors. A caller can't read a run's result. The privacy policy and trust page disagree on whether training is on by default.

Before you call either

LearnHarness

  1. Use the bundled skill (skills/learnharness/SKILL.md) to read a learner's record. It needs Python 3.10 or later and writes nothing
  2. Pass --format json before the subcommand, for example python3 -B scripts/graph.py --format json propositions
  3. Treat stored answer keys and teacher prose as model-authored. A proposition in the graph is not evidence the learner understood it
  4. Do not read auth.json, which sits one folder above the data folder and holds provider keys in plain text
  5. Close the app or re-read when a stable snapshot matters. The readers do not lock files while the app writes

Town

  1. Start a Town routine with POST to its webhook URL, Authorization Bearer whsec_ secret, and application/json or text/plain. Expect 202 only.
  2. Send X-Town-Idempotency-Key with a stable event id on every retry so Town doesn't start a second run.
  3. Treat 404 as wrong secret, disabled endpoint or missing endpoint alike, and ask the owner to check Routine Settings rather than retrying.
  4. Send account_email only if the owner allowed the override. It must match a connected account in full and can't widen the routine's scope.
  5. Ask the owner to keep routines that act on webhook input in approval-required mode, as Town's own docs advise.

Questions

Which is better for AI agents, LearnHarness or Town?

LearnHarness scores 59.3 (C) on agent readiness against Town's 48.7 (D), and leads in 5 of 7 scored categories. Town leads on security & auth.

Are LearnHarness and Town open source?

LearnHarness is open source (AGPL-3.0-only). No open-source release is listed for Town.

Other comparisons with LearnHarness or Town

Disclosure

Town 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.