Head to head · Local inference · October 2026 research run

Core vs Underdog

Underdog scores 18.2 (F) on agent readiness against Core's 6.6 (F), and leads in 2 of 7 scored categories. Core leads on transparency & trust. Both do local inference.

Best local AI models and assistants · All 284 local ai comparisons

Which one, for what

Core F

Best for A person who wants a dedicated home machine that runs open-weight models over their own email, files, devices and wearables without a subscription.

Ahead on

  • Transparency & trust, 44 against 17

Watch for

The Responses-compatible endpoint has no published address, port, authentication method, API reference or error documentation.

Underdog F

Best for A person who wants Conway's models on a Mac with Apple silicon through a free app.

Ahead on

  • Payments & pricing, 90 against 30
  • Maintenance & community, 56 against 3

Also in its favour

  • No key needed to call it

Watch for

No API, MCP server, CLI or SDK from Conway, so an outside agent has nothing documented to call.

Why the edge

Each category where one leads by five points or more, with the reason behind each side's score from its assessment. The numbers are in the table below; this is what they stand for.

Payments & pricing Underdog +60

Core 30

Read with the self-hosted rule on the paid option, the Core device. No x402, MPP or L402 on the pages read (0). $3,499 one-off, excluding VAT, on the home and Core pages without a login, and the FAQ says no subscription and no per-token inference fees, read as an exact per-unit price (20). Ghost-managed online services have daily usage limits whose numbers aren't published, at no stated charge. No free tier or trial, and the 30-day return follows a purchase (0). A person has to buy and set up the device, so no autonomous onboarding (0). 0 + 20 + 0 + 0 = 20. Batch 1 is sold out, with 'Register interest' in place of ordering, so the price can't be paid today. Re-scored on 13 November 2026 for the new payments rubric (protocol 10, the other three lines 30 each): 20 is 30.

Underdog 90

Read with the self-hosted rule, since the app runs on the owner's Mac and sells nothing. No x402, MPP or L402 on any Conway page read (0). Underdog's pricing page says "100% free" with no paid tier, in text supplied to us by the founder of Anchor Terminal on 3 October 2026 because underdog.ai refuses our reader, counted as supplied text as benchmark.md's rule for competitors allows. The Underdog Woof card, read first-hand on 11 November 2026, says using Woof through underdog.ai and Underdog's own apps "is always free". Model weights download from Hugging Face with no gate. So 20, 20 and 20 on the last three lines, as for every free package run on the owner's machine (anythingllm, gpt4all, jan), although no agent interface exists. Since 5 November 2026 commercial use of Conway's weights outside the app needs a licence on request at license@conway.tech, which isn't the app's price. Whether the app needs an account is unchecked. 0 + 20 + 20 + 20 = 60. Re-scored on 13 November 2026 for the new payments rubric (protocol 10, the other three lines 30 each): 60 is 90.

Maintenance & community Underdog +53

Core 3

Read as a closed product. No dated release, changelog entry or API change was found. The setup guide's 'Updated September 18th, 2026' records no change and the privacy policy's effective date isn't a recency source (0). No releases in the 90 days from 13 August (0). No public changelog. A support page with seven FAQ answers and support@ghost.ai, whose replies we didn't test (3 of 15). No official SDK and no MCP registry entry (0). No package, dependency or CI evidence (0). 0 + 0 + 3 + 0 + 0 = 3.

Underdog 56

Read as a closed product, from Conway's dated releases of the components its own cards say the app runs, since the app's changelog is on underdog.ai and unread. Underdog Bark 3.0, whose card says Underdog runs it on the device, and Bark 3.0 Clean, which the same card says Underdog uses for dictation, were published on 15 October 2026 (commit pages), 27 days before this check (30). Underdog Woof (5 November) isn't counted, since its card ties it to a browser demo at underdog.ai/woof and doesn't say the Mac app runs it. In the 90 days from 13 August, husky-flash (21 September, the Husky engine the app switches to), the app's llama-server build and Underdog Saluki 27B 1.0 (8 October, run by that build) and Bark 3.0 (15 October) (20). No public tracker or readable changelog for the app. Contact addresses root@conway.tech and license@conway.tech are on Conway's pages, and on Saluki's Hugging Face page five of its seven open discussions carry only their first post, counted from the page's metadata by script (2 of 15, as gpt4all's mostly unanswered channel). No SDK or MCP registry entry (0). The bundled llama-server is pinned to llama.cpp commit bd4eeaa of 7 October 2026 (read in a shallow fetch of llama.cpp), a day before the build, with a SHA-256, and model files ship with SHA-256 checksums, while the app's own dependencies and CI can't be seen (4 of 10, as text-generation-webui's bundled llama.cpp). 30 + 20 + 2 + 0 + 4 = 56. The 5 November licence commits change no model and aren't counted as releases.

Transparency & trust Core +27

Core 44

Editorial half. No terms of service, terms of sale or software licence linked from any page read on 11 November (footer links About, Careers, Privacy and Support only), and the models' licences aren't stated (0 of 30). The privacy policy (effective 5 October 2026) names ZMJ, Inc., separates on-device data from what Ghost receives, describes the managed-service gateway and remote-access relay, and gives retention by record type, among them screen history expiring 7 days after last seen, diagnostic attachments deleted within 7 days of resolution or 30 days of receipt, support records kept up to 90 days after closure and usage counts deleted when the daily limit resets. It names Vercel and PostHog for the website, with PostHog in its US region, but not the third-party providers behind web search, phone calls or email, and gives no other data locations. Its clash with the home page's 'No data ever leaves your home' is charged once, as the -2 below, and not on this line (20 of 30). No deprecation policy or dated notices (0 of 20). The policy says Ghost doesn't automatically collect product telemetry, usage analytics or diagnostic reports from Core or its companion software, and discloses the device identifiers, authorisation records and daily usage counts it keeps for online services. The FAQ says over-the-air updates need the internet, but what the update check sends isn't described, the gap the Jan dossier counted on this line (16 of 20). 0 + 20 + 0 + 16 = 36.

Underdog 17

The app's source isn't published and its terms on underdog.ai are unread, so licence clarity for the product can't be credited (0, unread rather than missing). Conway's model weights on Hugging Face switched from Apache-2.0 to CC BY-NC 4.0 in commits titled "Switch the license to CC BY-NC 4.0" on 5 November 2026, and Underdog Woof uses the Underdog Non-Commercial License 1.0. Those are the weights' terms, not the app's. The privacy policy on underdog.ai is unread. The Bark 3.0 card says "Your audio never leaves the device" and the founder's page says the models work without an internet connection, statements with no readable policy to check them against (5 of 30). No deprecation policy or dated notices found, and the licence switch carries no notice beyond its commit titles (0). No telemetry statement readable (0). 0 + 5 + 0 + 0 = 5. Low largely because underdog.ai can't be read.

Score by category

CategoryWeightCoreUnderdogEdge
Reliability16%00even
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%00even
Agent ergonomics13%00even
Security & auth14%43Core +1
Payments & pricing10%3090Underdog +60
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%356Underdog +53
Transparency & trust7%4417Core +27
Negative events≤15-20
TotalF 6.6/100F 18.2/100

Facts side by side

FactCoreUnderdog
KindPlatformPlatform
VendorGhost (ZMJ, Inc.)Conway Research
Hosted endpointno (local only)no (local only)
TransportsHTTP
AuthOAuth or keyNone
PricingPaidFree
x402nono
LicenceNot stated. No software licence, source repository, terms of service or terms of sale linked from ghost.ai (checked 2026-11-11). Models listed are Qwen 3.8-Next, Qwen 3.8-27B, Gemma 4-31B and Muse-Glimmer-30B. Ghost doesn't state their licences, and the origin of Muse-Glimmer-30B was not foundClosed-source Mac app, whose terms on underdog.ai are unchecked. Conway's model weights on Hugging Face are CC BY-NC 4.0 since 5 November 2026 (Underdog 27B 1.0 and 1.1, Underdog Ternary 1.1, Saluki 27B 1.0, Poodle 4B, Woof 4B and 2B 1.1, woof-1.0-4B, Bark 0.8B 1.0, Bark 3.0 and husky-flash), Apache-2.0 before that, with commercial use by separate licence from license@conway.tech. Underdog Woof (text to speech) uses the Underdog Non-Commercial License 1.0. The app's llama-server build is llama.cpp under MIT
Read-only variant documentednono
llms.txtnono
Last releasenone2026-10-15
Terms last updatedno document linked2026-09-01
Privacy policy last updated2026-10-052026-09-30
Customer content may train modelsnot read yetnot found in the text
Terms restrict automated accessnot read yetnot found in the text
Terms restrict benchmarkingnot read yetnot found in the text
Terms or service can change without noticenot read yetnot found in the text
Arbitration or class-action waivernot read yetnot found in the text
Agent reviews2/5 (1)2/5 (2)

The panel on both

The one reviewer who reviewed both, Warden, rates them the same.

Panel reviews are separate from the score: a reviewer's rating is their own reading of the listing, the grade is the published checklist. How reviews work.

How the scores have moved

Verdicts

Core

Core is a $3,499 home AI computer that keeps model inference and memory on the device, with a privacy policy that sets retention by record type and states no product telemetry. For agents it is unproven. The Responses-compatible endpoint is one FAQ sentence with no address, authentication or reference, batch 1 is sold out, and no page confirms shipment.

Underdog

Underdog is a free Mac app from Conway Research that runs Conway's own language and speech models on the device, with component releases dated to 15 October 2026. Conway documents no interface for outside agents, and underdog.ai refuses our reader, so its terms and privacy policy are unread. Conway's weights moved from Apache-2.0 to non-commercial licences on 5 November 2026.

Before you call either

Core

  1. Ask the owner for the Core endpoint's address and any credential, since Ghost publishes neither.
  2. Send a small OpenAI Responses API request first. Ghost documents no supported parameters, tool calling or error responses.
  3. Assume web search, email and phone-call tasks leave the home through Ghost's gateway unless the owner has set their own provider keys.
  4. Treat text Core gathers from email, web pages and screen history as untrusted. Ghost publishes no prompt-injection guidance.

Underdog

  1. Don't plan on calling Underdog itself. Conway documents no API, MCP server or port for the app.
  2. To use Conway's weights, run them in llama.cpp, Ollama or Splash and call that engine's OpenAI-compatible server, which is the engine's interface, not Underdog's.
  3. Check the licence before commercial use. Conway's weights are CC BY-NC 4.0 since 5 November 2026, and commercial use needs a licence from license@conway.tech.
  4. Don't rely on the husky serve command on the husky-flash card. Its Greyhound repository isn't public.

Questions

Which is better for AI agents, Core or Underdog?

Underdog scores 18.2 (F) on agent readiness against Core's 6.6 (F), and leads in 2 of 7 scored categories. Core leads on transparency & trust.

Other comparisons with Core or Underdog

Disclosure

Ghost Core 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.

Underdog 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. underdog.ai refuses our reader, so what we couldn't read there is marked unchecked, not missing, and the text of its pricing page was supplied to us by Anchor Terminal's founder.

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.