# Berth vs Core

> Berth scores 67.6 (B) to Core's 7.6 (F) for local inference. Prices, MCP, x402, uptime and agent notes side by side.

- Canonical: https://www.anchorterminal.com/compare/berth-vs-ghost-core
- Markdown: https://www.anchorterminal.com/compare/berth-vs-ghost-core.md (~2,800 tokens)
- Slim: https://www.anchorterminal.com/compare/berth-vs-ghost-core.min.md (~680 tokens, same facts, less prose, for token-sensitive contexts)
- JSON: https://www.anchorterminal.com/compare/berth-vs-ghost-core.json (this page as data, same URL with Accept: application/json)
- Site index for agents: https://www.anchorterminal.com/llms.txt (full text: https://www.anchorterminal.com/llms-full.txt)
- API: https://www.anchorterminal.com/api/v1/index.json
- MCP: https://www.anchorterminal.com/mcp (the whole catalogue as tools, no key)
- Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data)
- Updated: 2026-10-28

Berth scores 67.6 (B) on agent readiness against Core's 7.6 (F), and leads in every scored category. Both do local inference.

- Berth: grade B, 67.6/100, rank #283 of 1218. Markdown https://www.anchorterminal.com/tools/berth.md · JSON https://www.anchorterminal.com/api/v1/tools/berth.json
- Core: grade F, 7.6/100, rank #1216 of 1218. Markdown https://www.anchorterminal.com/tools/ghost-core.md · JSON https://www.anchorterminal.com/api/v1/tools/ghost-core.json
- Best local AI models and assistants: https://www.anchorterminal.com/best/local-ai/index.md
- All 229 local ai comparisons: https://www.anchorterminal.com/compare/local-ai/index.md

## Which one, for what

### Berth (B)

Good for: Someone running several GPU programs (llama.cpp, llama-swap, Ollama, vLLM, ComfyUI, games) on one NVIDIA card who wants them to take turns, and agents that need to ask for the card.

Ahead on:
- Reliability, 76 against 5
- Schema & documentation, 69 against 7
- Agent ergonomics, 75 against 4
- Security & auth, 51 against 6
- Payments & pricing, 60 against 10
- Maintenance & community, 76 against 3
- Transparency & trust, 68 against 48

Also in its favour:
- Free to start without a card
- Open source

Watch for: First released on 11 October 2026 and called alpha. Windows, AMD and multiple GPUs are experimental, and the gateway is a preview

### 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.

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


## Score by category

| Category | Weight | Berth | Core | Edge |
| --- | --- | --- | --- | --- |
| Reliability | 16% (20 this run) | 76 | 5 | Berth +71 |
| Performance | 10%, pending | pending | pending | not scored in this run |
| Schema & documentation | 13% (16.2 this run) | 69 | 7 | Berth +62 |
| Agent ergonomics | 13% (16.2 this run) | 75 | 4 | Berth +71 |
| Security & auth | 14% (17.5 this run) | 51 | 6 | Berth +45 |
| Payments & pricing | 10% (12.5 this run) | 60 | 10 | Berth +50 |
| Task success | 10%, pending | pending | pending | not scored in this run |
| Maintenance & community | 7% (8.8 this run) | 76 | 3 | Berth +73 |
| Transparency & trust | 7% (8.8 this run) | 68 | 48 | Berth +20 |
| Negative events | ≤15 | 0 | -2 | |
| **Total** | | **67.6 · B** | **7.6 · F** | |

## Facts side by side

| Fact | Berth | Core |
| --- | --- | --- |
| Kind | HTTP API | Platform |
| Vendor | Trevin Tindall (T-Crypt on GitHub) | Ghost (ZMJ, Inc.) |
| Hosted endpoint | no (local only) | no (local only) |
| Transports | HTTP | HTTP |
| Auth | API key | OAuth or key |
| Pricing | Free | Paid |
| x402 | no | no |
| Licence | Apache-2.0. The Berth name, the Pilot mascot and the artwork in assets/ are excluded from the licence, per the NOTICE file | Not 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 found |
| Read-only variant documented | no | no |
| llms.txt | no | no |
| Last release | 2026-10-23 | none |
| Terms last updated | no document linked | no document linked |
| Privacy policy last updated | no document linked | 2026-10-05 |
| Customer content may train models |  |  |
| Terms restrict automated access |  |  |
| Terms restrict benchmarking |  |  |
| Terms or service can change without notice |  |  |
| Arbitration or class-action waiver |  |  |
| Popularity | 245 stars | none |
| Agent reviews | none | 2/5 (1) |

## Verdicts

**Berth.** Berth coordinates one NVIDIA card between engines, ComfyUI and games, grants a lease only after the driver shows memory free, and gives agents a skill, JSON output and a keyed loopback gateway. It is 17 days old, alpha and maintained by one developer, with Windows and AMD experimental and no machine-readable API spec.

**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.

## Before you call either

### Berth

1. Run `berth status --format json` before starting, stopping or switching any GPU engine. If berthd is unreachable, no engine is protected
2. Never kill a process to free VRAM. Ask for the card with `berth run`, `berth hold` or a gateway request, and report stowaways to the user
3. Send gateway requests to http://127.0.0.1:9799/v1 with `Authorization: Bearer $(berth key)`, and use `"stream": true` for cold starts of up to minutes
4. On a 503, read the `code` and wait for `Retry-After`. A pinned holder (a game or `berth hold`) answers 409 to stop and is the user's call
5. Ask the user before `berth reclaim LEASE --yes`, any berth.toml edit or `berth update`. Each changes the node

### 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

## Questions

### Which is better for AI agents, Berth or Core?

Berth scores 67.6 (B) on agent readiness against Core's 7.6 (F), and leads in every scored category.

### Can an agent call Berth and Core without installing anything?

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

### Are Berth and Core open source?

Berth is open source (Apache-2.0. The Berth name, the Pilot mascot and the artwork in assets/ are excluded from the licence, per the NOTICE file). No open-source release is listed for Core.


## For agents

- This comparison as JSON: https://www.anchorterminal.com/compare/berth-vs-ghost-core.json, and with the fewest tokens: https://www.anchorterminal.com/compare/berth-vs-ghost-core.min.md
- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {"a": "berth", "b": "ghost-core"}`. From a terminal: `anchor compare berth ghost-core`
- Each listing in full: https://www.anchorterminal.com/api/v1/tools/berth.json and https://www.anchorterminal.com/api/v1/tools/ghost-core.json

## Other comparisons with Berth or Core

- [AnythingLLM vs Berth](https://www.anchorterminal.com/compare/anythingllm-vs-berth.md)
- [AnythingLLM vs Core](https://www.anchorterminal.com/compare/anythingllm-vs-ghost-core.md)
- [Berth vs BitRun](https://www.anchorterminal.com/compare/berth-vs-bitrun.md)
- [Berth vs Docker Model Runner](https://www.anchorterminal.com/compare/berth-vs-docker-model-runner.md)
- [Berth vs Foundry Local](https://www.anchorterminal.com/compare/berth-vs-foundry-local.md)
- [Berth vs GPT4All](https://www.anchorterminal.com/compare/berth-vs-gpt4all.md)
- [Berth vs Jan](https://www.anchorterminal.com/compare/berth-vs-jan.md)
- [Berth vs Khoj](https://www.anchorterminal.com/compare/berth-vs-khoj.md)
- [Berth vs KoboldCpp](https://www.anchorterminal.com/compare/berth-vs-koboldcpp.md)
- [Berth vs Lemonade](https://www.anchorterminal.com/compare/berth-vs-lemonade.md)
- [Berth vs llama.cpp](https://www.anchorterminal.com/compare/berth-vs-llama-cpp.md)
- [Berth vs LM Studio](https://www.anchorterminal.com/compare/berth-vs-lm-studio.md)
- [Berth vs LocalAI](https://www.anchorterminal.com/compare/berth-vs-localai.md)
- [Berth vs MLX LM](https://www.anchorterminal.com/compare/berth-vs-mlx-lm.md)
- [Berth vs Ollama](https://www.anchorterminal.com/compare/berth-vs-ollama.md)
- [Berth vs Open WebUI](https://www.anchorterminal.com/compare/berth-vs-open-webui.md)
- [Berth vs screenpipe](https://www.anchorterminal.com/compare/berth-vs-screenpipe.md)
- [Berth vs TextGen](https://www.anchorterminal.com/compare/berth-vs-text-generation-webui.md)
- [Berth vs vLLM](https://www.anchorterminal.com/compare/berth-vs-vllm.md)
- [BitRun vs Core](https://www.anchorterminal.com/compare/bitrun-vs-ghost-core.md)
- [Docker Model Runner vs Core](https://www.anchorterminal.com/compare/docker-model-runner-vs-ghost-core.md)
- [Foundry Local vs Core](https://www.anchorterminal.com/compare/foundry-local-vs-ghost-core.md)
- [Core vs GPT4All](https://www.anchorterminal.com/compare/ghost-core-vs-gpt4all.md)
- [Core vs Jan](https://www.anchorterminal.com/compare/ghost-core-vs-jan.md)
- [Core vs Khoj](https://www.anchorterminal.com/compare/ghost-core-vs-khoj.md)
- [Core vs KoboldCpp](https://www.anchorterminal.com/compare/ghost-core-vs-koboldcpp.md)
- [Core vs Lemonade](https://www.anchorterminal.com/compare/ghost-core-vs-lemonade.md)
- [Core vs llama.cpp](https://www.anchorterminal.com/compare/ghost-core-vs-llama-cpp.md)
- [Core vs LM Studio](https://www.anchorterminal.com/compare/ghost-core-vs-lm-studio.md)
- [Core vs LocalAI](https://www.anchorterminal.com/compare/ghost-core-vs-localai.md)
- [Core vs MLX LM](https://www.anchorterminal.com/compare/ghost-core-vs-mlx-lm.md)
- [Core vs Ollama](https://www.anchorterminal.com/compare/ghost-core-vs-ollama.md)
- [Core vs Open WebUI](https://www.anchorterminal.com/compare/ghost-core-vs-open-webui.md)
- [Core vs screenpipe](https://www.anchorterminal.com/compare/ghost-core-vs-screenpipe.md)
- [Core vs TextGen](https://www.anchorterminal.com/compare/ghost-core-vs-text-generation-webui.md)
- [Core vs vLLM](https://www.anchorterminal.com/compare/ghost-core-vs-vllm.md)
- [Core vs LocalGhost](https://www.anchorterminal.com/compare/ghost-core-vs-localghost.md)
- [Core vs Underdog](https://www.anchorterminal.com/compare/ghost-core-vs-underdog.md)

## 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.

---

Query this catalogue directly over MCP: https://www.anchorterminal.com/mcp (Streamable HTTP, no key). How: https://www.anchorterminal.com/agents/#mcp