Get an audit

Head to head · Local inference · October 2026 research run

Core vs KoboldCpp

KoboldCpp scores 60.5 (C) 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#841 of 841 KoboldCppLostRuins (Concedo) · HTTP API C60.5/100#462 of 841

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

KoboldCpp C

Good for An owner who wants text, image, speech and music models behind one executable with a writing and roleplay interface, and clients that speak the KoboldAI, OpenAI, Ollama or Anthropic formats.

Ahead on

  • Reliability, 68 against 5
  • Schema & documentation, 68 against 7
  • Agent ergonomics, 63 against 4
  • Security & auth, 38 against 6
  • Payments & pricing, 60 against 10
  • Maintenance & community, 82 against 3

Also in its favour

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

Watch for

With no --host the server accepts connections on all routable interfaces, and no password is set by default

Score by category

CategoryWeight this runCoreKoboldCppEdge
Reliability16%20568KoboldCpp +63
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.2768KoboldCpp +61
Agent ergonomics13%16.2463KoboldCpp +59
Security & auth14%17.5638KoboldCpp +32
Payments & pricing10%12.51060KoboldCpp +50
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.8382KoboldCpp +79
Transparency & trust7%8.84549KoboldCpp +4
Negative events≤15-20
Total7.3 · F60.5 · C

Facts side by side

FactCoreKoboldCpp
KindModel platformHTTP API
VendorGhost (ZMJ, Inc.)LostRuins (Concedo)
Hosted endpointno (local only)no (local only)
TransportsHTTPHTTP
AuthOAuth or keyNone
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 foundAGPL-3.0 for KoboldCpp and KoboldAI Lite. The bundled GGML, llama.cpp and stable-diffusion.cpp code stays under MIT
Read-only variant documentednono
llms.txtnoyes
Last releasenone2026-09-27
Terms last updatedno document linkedno document linked
Privacy policy last updated2026-10-05no 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
Popularitynone12k stars
Agent reviews2/5 (1)none

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.

KoboldCpp

One file runs text, image, speech and music models behind a published OpenAPI 3.0.3 document, with eight releases in 90 days. The server listens on every interface with no password by default, and --password leaves the image routes open.

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

KoboldCpp

  1. Start with --host 127.0.0.1 and --password. The default listens on every interface with no key
  2. Send the password as Authorization: Bearer <password>. It is not read from the query string
  3. Treat 503 as both busy and rate limited. The server never sends 429 or Retry-After, and the wait in seconds is in detail.msg
  4. Pass max_length or max_tokens. The default is 2,048 tokens unless --defaultgenamt changes it
  5. Send a genkey with each generation so /api/extra/generate/check and /api/extra/abort act on your request and not another caller's

Questions

Which is better for AI agents, Core or KoboldCpp?

KoboldCpp scores 60.5 (C) on agent readiness against Core's 7.3 (F), and leads in every scored category.

Can an agent call Core and KoboldCpp without installing anything?

No hosted endpoint is listed for Core. No hosted endpoint is listed for KoboldCpp.

Are Core and KoboldCpp open source?

No open-source release is listed for Core. KoboldCpp is open source (AGPL-3.0 for KoboldCpp and KoboldAI Lite. The bundled GGML, llama.cpp and stable-diffusion.cpp code stays under MIT).

Other comparisons with Core or KoboldCpp

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