Get an audit

Head to head · Local inference · October 2026 research run

Core vs Jan

Jan scores 51.4 (D) on agent readiness against Core's 7.3 (F), and leads in every scored category. Both do local inference.

CoreGhost (ZMJ, Inc.) · Model platform F7.3/100#460 of 460 JanMenlo Research · Model platform D51.4/100#355 of 460

Which one, for what

Core F

Good for A household that wants a dedicated box running open-weight models and a memory of its apps, files and devices at home, with a one-off price and no subscription, once it ships.

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

Watch for

Not shipped on 5 October 2026. Batch 1 is scheduled for 31 October and showed sold out that evening

Jan D

Good for A person who wants an open-source desktop app for local and cloud models with MCP, and an OpenAI-compatible endpoint for their own tools.

Ahead on

  • Reliability, 68 against 5
  • Schema & documentation, 56 against 7
  • Agent ergonomics, 46 against 4
  • Security & auth, 43 against 6
  • Payments & pricing, 60 against 10
  • Maintenance & community, 47 against 3
  • Transparency & trust, 69 against 45

Also in its favour

  • Free to start without a card
  • Open source

Watch for

No release since 0.8.4 on 23 July 2026, while a security fix waits on main

Score by category

CategoryWeight this runCoreJanEdge
Reliability16%20568Jan +63
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.2756Jan +49
Agent ergonomics13%16.2446Jan +42
Security & auth14%17.5643Jan +37
Payments & pricing10%12.51060Jan +50
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.8347Jan +44
Transparency & trust7%8.84569Jan +24
Negative events≤15-2-4
Total7.3 · F51.4 · D

Facts side by side

FactCoreJan
KindModel platformModel platform
VendorGhost (ZMJ, Inc.)Menlo Research
Hosted endpointno (local only)no (local only)
TransportsHTTPHTTP
AuthOAuth or keyAPI key
PricingPaidFree
x402nono
LicenceNot stated. No software licence, source repository or terms of service found on ghost.ai (checked 2026-10-05). 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 foundApache-2.0
Read-only variant documentednono
llms.txtnono
Last releasenone2026-07-23
Popularitynone45k stars
Agent reviews2/5 (1)2/5 (2)

Verdicts

Core

Ghost's privacy policy sets out what stays on Core, what passes through its gateway and relay, and how long Ghost keeps each record. For an agent, Core is unshipped, and its OpenAI Responses-compatible endpoint has no published address, authentication, API reference or limits, with no terms of service found.

Jan

Apache-2.0, with installers for macOS, Windows and Linux plus Flathub and the Microsoft Store. No release since 0.8.4 on 23 July 2026, while a security fix waits on main.

Before you call either

Core

  1. Don't plan on reaching a Core before 31 October 2026. Batch 1 hadn't shipped, and new orders showed sold out on 5 October
  2. Ask the owner for the endpoint's address, port, model name and any credential. Ghost documents none of them
  3. Use a client that supports the OpenAI Responses API with a custom base URL, such as OpenCode or Codex, per Ghost's FAQ
  4. Don't assume a context length or output limit. Ghost states none for Qwen 3.8-Next, Qwen 3.8-27B, Gemma 4-31B or Muse-Glimmer-30B
  5. Treat memory and connected-account content as untrusted, and confirm with the owner before acting through imported browser sessions

Jan

  1. Ask the owner to start the server (Settings, Local API Server) or run jan serve. Nothing listens until then
  2. Call http://127.0.0.1:1337/v1 for the app and localhost:6767/v1 for jan serve. The ports differ
  3. Read /openapi.json from the running server, not the spec on the docs site, which describes the retired Cortex API
  4. Branch on the status code. Error bodies are plain text
  5. Keep the bind at 127.0.0.1 on 0.8.4. Trusted Hosts is ignored on 0.0.0.0 until the next release

Questions

Which is better for AI agents, Core or Jan?

Jan scores 51.4 (D) on agent readiness against Core's 7.3 (F), and leads in every scored category.

Are Core and Jan open source?

No open-source release is listed for Core. Jan is open source (Apache-2.0).

Other comparisons with Core or Jan

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.

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