Get an audit

Head to head · Local inference · October 2026 research run

Core vs vLLM

vLLM scores 57.7 (C) on agent readiness against Core's 7.3 (F), and leads in every scored category. Both do local inference.

Best local AI models and assistants · All 184 local ai comparisons

CoreGhost (ZMJ, Inc.) · Model platform F7.3/100#950 of 950 vLLMvLLM project (PyTorch Foundation) · HTTP API C57.7/100#600 of 950

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

vLLM C

Good for An owner with a GPU server who wants many concurrent requests against one open-weight model behind OpenAI or Anthropic compatible routes.

Ahead on

  • Reliability, 62 against 5
  • Schema & documentation, 68 against 7
  • Agent ergonomics, 64 against 4
  • Security & auth, 50 against 6
  • Payments & pricing, 60 against 10
  • Maintenance & community, 88 against 3
  • Transparency & trust, 67 against 45

Also in its favour

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

Watch for

--api-key guards only the /v1, /v2, /inference and /cohere prefixes. /invocations, /pooling, /classify, /score, /rerank, /pause and /update_weights answer without it

Score by category

CategoryWeight this runCorevLLMEdge
Reliability16%20562vLLM +57
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.2768vLLM +61
Agent ergonomics13%16.2464vLLM +60
Security & auth14%17.5650vLLM +44
Payments & pricing10%12.51060vLLM +50
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.8388vLLM +85
Transparency & trust7%8.84567vLLM +22
Negative events≤15-2-6
Total7.3 · F57.7 · C

Facts side by side

FactCorevLLM
KindModel platformHTTP API
VendorGhost (ZMJ, Inc.)vLLM project (PyTorch Foundation)
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 foundApache-2.0
Read-only variant documentednono
llms.txtnono
Last releasenone2026-10-02
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
Popularitynone93k 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.

vLLM

Apache-2.0 software with a release about every two weeks, each with notes that list breaking changes and security fixes. The optional API key covers only some path prefixes, so /invocations and control routes such as /pause answer without it, and at least 81 security advisories were published in the 12 months to 9 October 2026.

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

vLLM

  1. Put a reverse proxy that allowlists routes in front of the server. --api-key leaves /invocations and the control routes open
  2. Pass --host 127.0.0.1 for single-machine use. With no --host the server listens on every interface
  3. Set VLLM_NO_USAGE_STATS=1 or DO_NOT_TRACK=1 before starting if nothing should be sent to stats.vllm.ai
  4. Start with --enable-auto-tool-choice and the --tool-call-parser for the model before sending tools. Tool calling is off without them
  5. Send max_tokens on every request, and read the breaking changes section of the release notes before upgrading a minor version

Questions

Which is better for AI agents, Core or vLLM?

vLLM scores 57.7 (C) on agent readiness against Core's 7.3 (F), and leads in every scored category.

Can an agent call Core and vLLM without installing anything?

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

Are Core and vLLM open source?

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

Other comparisons with Core or vLLM

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