Head to head · Local inference · October 2026 research run
Core vs Open WebUI
Open WebUI scores 52.8 (D) on agent readiness against Core's 6.6 (F), and leads in every scored category. 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.
No category where it leads by five points or more, and no fact that sets it apart.
Watch for
The Responses-compatible endpoint has no published address, port, authentication method, API reference or error documentation.
Best for A team or a person who wants a self-hosted chat front end over Ollama or OpenAI-compatible models with users, groups, retrieval and tools, and an API an agent can call on that instance.
Ahead on
- Reliability, 60 against 0
- Schema & documentation, 65 against 0
- Agent ergonomics, 57 against 0
- Security & auth, 65 against 4
- Payments & pricing, 90 against 30
- Maintenance & community, 86 against 3
- Transparency & trust, 67 against 44
Watch for
129 reviewed advisories cover flaws fixed from 24 November 2025 to 25 August 2026, 1 Critical and 56 High among them, with 19 more fixed in 0.11.4.
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.
Maintenance & community Open WebUI +83
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.
Open WebUI 86
0.13.3, dated 8 November 2026 in the changelog and tagged on 9 November (30). 14 releases in the 90 days from 13 August, from 0.11.1 (25 August) to 0.13.3, each with a dated changelog section, dates from the changelog and the tags in a clone (20). Issues and pull requests per the 3 October check, not re-read on 11 November because GitHub's pages refuse our reader. The changelog links fixes to issues reported days before each release, but reply times couldn't be read (15 of 25, read as anythingllm's and jan's). No official SDK and no MCP server. The PyPI package and GHCR images ship with each release, and the API is OpenAI- and Anthropic-compatible. Partly met, so the earlier partial is held (13 of 15). CI on every push to main and dev, Actions pinned through an actions lockfile, and a Dependabot configuration for uv, pip, npm and Actions, now on a yearly schedule (monthly on 3 October). Partly met, earlier partial held (8 of 10). 30 + 20 + 15 + 13 + 8 = 86.
Schema & documentation Open WebUI +65
Core 0
Read with the API lines for the Responses-compatible endpoint. The FAQ says Core has an endpoint compatible with the OpenAI Responses API for OpenCode, OpenClaw, Codex and the owner's own apps and agents. Ghost publishes no OpenAPI file or other contract of its own, and a claim of compatibility with another vendor's API isn't one, as for GPT4All (0). No llms.txt (404 on 11 November) and no Markdown docs (0). No API reference, so no descriptions of what the endpoint does, which parameters it takes or where it stops (0). No typed inputs documented (0). No examples or error responses (0). No versioning or changelog (0). 0 + 0 + 0 + 0 + 0 + 0 = 0. Low because the documentation isn't published, not because we couldn't read it.
Open WebUI 65
Read with the API lines for the HTTP API an agent calls on an instance. FastAPI generates the OpenAPI document from the routes, and main.py serves /docs and /openapi.json only when ENV=dev. ENV defaults to dev in the backend (env.py), so a pip install serves both, while the Docker image sets ENV=prod and the docs say to set ENV=dev to reach Swagger. No spec file is published, and chat completions take a free-form dict. The line is partly met, so the earlier partial is held (12 of 25). The docs repository ships llms.txt and agents.txt and generates llms-full.txt and a Markdown copy of every page at build, and llms.txt was read on the docs host on 3 October. docs.openwebui.com wasn't requested on 11 November (see openQuestions) (10). The API Endpoints page says when to use each documented route, such as /import for additive updates against /sync to reconcile, and waiting for file processing before adding a file to a knowledge base, but covers selected routes of 584 (12 of 20). Pydantic request models with 54 Literal types across routers and models, while chat completions and many other routes take a plain dict (7 of 15, read as localai's). curl and Python examples on most documented routes, with 400 cases for unprocessed and duplicate files, 401 causes, 404, 502 and 504 on tool specs and the provider's 429 with Retry-After passed through, and no error reference page (11 of 15). Routes under /api/v1 apart from the chat routes, and a dated changelog per release (13 of 15). 12 + 10 + 12 + 7 + 11 + 13 = 65.
Security & auth Open WebUI +61
Core 4
Read with the tool checklist for the Responses-compatible endpoint and the device behind it. No authentication method for the endpoint is documented. The setup guide pairs the Ghost app with Core over the local network, and the privacy policy mentions device-access controls and keeps device identifiers and authorisation records, but nothing says how a caller of the endpoint is identified or limited (0 of 30). Screen history is off until enabled, connected accounts get the permissions the owner approves, every connection can be removed, and the setup guide says Ghost connects to home devices only when the owner approves a live view. Against that, the home page says Core acts 'without waiting for a prompt', and imported browser sessions let it act through the owner's accounts, with no read-only mode or confirmation for actions documented (4 of 20). Core reads email, messages, documents, web content and screen text into its memory, and we found no prompt-injection guidance (0 of 15). No audit log or per-call record for the owner found. Memory review and removal controls aren't a call log (0 of 15). No security.txt (404 on 11 November), disclosure policy, bug bounty, certification or published audit. The privacy policy's 'Independent security review' section welcomes security firms to audit the gateway and relay and gives support@ghost.ai to arrange a review. That is an invitation with no report behind it and no route for reporting a flaw, so it scores 0, as claims with nothing behind them did for gotohuman and expedia-rapid, where a published audit report earned postmark 5 (0 of 20). 0 + 4 + 0 + 0 + 0 = 4.
Open WebUI 65
Read with the tool checklist. One API key per user, sk- plus 32 hexadecimal characters, carrying that user's role and group permissions, revoked by deletion and rotated by generating a new one. Keys are off by default (ENABLE_API_KEYS), a group permission decides who may create one, and an administrator can limit them instance-wide to listed endpoints. They're stored in plain text, can be read back through GET /api/v1/auths/api_key, and have no scopes of their own and no expiry. The api_key table has expires_at and last_used_at columns that no code path sets. Tokens travel in the Authorization header, an x-api-key header or the session cookie, never a query string (20 of 30, plain revocable keys). Admin, user and pending roles with group permissions, per-model and per-knowledge access, workspace tools off for non-administrators, and tool permission modes (Ask for approval, and since 0.13.1 Auto with a review model) that are experimental and off by default. Workspace tools and functions are Python run with exec and the server's rights, which the security policy calls intended behaviour (14 of 20, read as localai's role scoping). Chats bring in web pages, files and tool output. The accepted-risks pages on model output and agentic applications name injected content in fetched pages and documents, say which injection reports count as vulnerabilities, and list the mitigations (per-user scoping, permissions, filters and confirmation prompts) (9 of 15). AUDIT_LOG_LEVEL records metadata, requests or requests with responses, NONE by default, and logs key calls under the key's owner, and API key creation and deletion raise events (12 of 15). The security policy takes reports only through GitHub Security Advisories, supports main only, gives no acknowledgement time ("Expect several weeks") and no bounty, and accepted reports become public advisories with patched versions. security.txt per the 3 October check, not re-read. No SOC 2 or ISO 27001. The route with no stated time is 7, and advisories handled in public add 3, as anythingllm's (10 of 20). 20 + 14 + 9 + 12 + 10 = 65. Advisories are charged one by one under negative events.
Reliability Open WebUI +60
Core 0
Read with the local-software lines for the OpenAI Responses-compatible endpoint that runs on the owner's Core, as for Jan, GPT4All and LocalAI. Ghost runs no hosted endpoint for it. Core is hardware sold by Ghost with no public software package, and the desktop app's download buttons lead to the setup guide (0). No public source, CI or test suite (0). No public issue tracker, so no crash or regression record to read (0). No version numbers, release notes or changelog (0). Batch 1 shows sold out on the home and Core pages on 11 November 2026, which still say the first batch ships on 31 October, and nothing we read confirms it has shipped or declares the software stable (0). 0 + 0 + 0 + 0 + 0 = 0. Read with the hosted lines instead, the only award would be 5 for no readable incident history.
Open WebUI 60
Read with the local-software lines, since an agent calls an Open WebUI instance its owner runs, with no hosted Open WebUI service. The open-webui package on PyPI states Python 3.11 or 3.12 (requires-python >= 3.11, < 3.13.0a1 in pyproject.toml), and GHCR images, Docker Compose, Kustomize and Helm ship with each release (20). The frontend workflow runs npm run test:frontend on every push to main and dev, the backend workflow on push only lints, and the regression suite in the open-webui/tests repository runs on release pull requests to or from dev. Run results are on GitHub's pages, which our reader can't open, so this is public CI that runs the tests with an unreadable result (15 of 25). Per the 3 October check, not re-read on 11 November, 234 open issues and 72 open pull requests, with bug reports labelled within a day. Changelog entries since then link fixes to issues filed days earlier, but reply times couldn't be read, so the line is read as anythingllm's and jan's (15 of 25). CHANGELOG.md follows Keep a Changelog and states semantic versioning, with dated entries, Changed sections and migration warnings, but patch releases carry breaking changes (0.12.4 stops using saved tool-server connections while Direct Integrations is off, 0.13.1 turns off file preloading), and 0.11.4, a patch release, removed POST /api/v1/utils/pdf with no changelog entry. The line is partly met, so the earlier partial is held (10 of 15). 0.13.3, before 1.0, and the API page calls the API an experimental setup (0). 20 + 15 + 15 + 10 + 0 = 60.
Payments & pricing Open WebUI +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.
Open WebUI 90
Read with the self-hosted rule, since an agent calls an instance its owner runs, as anythingllm's is read with AnythingLLM Cloud beside it. No x402, MPP or L402 in the source or docs (0). The software is free to self-host with no account or card, so 20, 20 and 20 on the last three lines. The enterprise licence (white-labelling, SLA-backed support) is sold through sales with no published prices, per the 3 October check, and the Paid Offerings, Terminals and Tether terms of 10 November 2026 cover per-user plans for Terminals and Tether bought through a checkout page or payment link. Neither is needed for an agent's use of the API. 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.
Agent ergonomics Open WebUI +57
Core 0
Read with the API lines. Nothing documents how responses are sized, which Responses API parameters Core accepts or how long its context is (0). No pagination, filtering or output controls documented (0). No error responses documented (0). No idempotency or retry guidance (0). The endpoint's address, port and authentication aren't published, so there are no stated defaults, and there's no Ghost SDK (0). 0 + 0 + 0 + 0 + 0 = 0.
Open WebUI 57
Read with the API lines. Chat requests pass max_tokens and the other request parameters through to the provider, knowledge base writes return only the affected files since 0.12.5, file reads by line range stop at a size limit since 0.13.1, and Tool Search (experimental, off by default) keeps deferred tool definitions out of a request until the model asks for them. No field selection (17 of 25, read as text-generation-webui's). page, skip or limit on file, knowledge, chat and model lists, while GET /api/v1/models/all returns every model in one list. Partly met, so the earlier partial is held (13 of 20). Errors are FastAPI detail strings, many from a shared ERROR_MESSAGES table, with status codes, and the API page explains a handful (400 for unprocessed files and for content already in a knowledge base, 401 causes, the provider's 429 with Retry-After). Partly met, earlier partial held (12 of 20). No idempotency keys or retry guidance. /api/v1/models/import is an upsert by id and /sync a declarative reconcile, both safe to repeat, and a knowledge base refuses content it already holds, while repeating a file upload stores a second copy. Partly met, earlier partial held (5 of 20). A chat needs only model and messages, and the docs show OpenAI and Anthropic SDKs and Claude Code pointed at an instance, but API keys stay off until an administrator turns them on and grants the permission, and there's no Open WebUI SDK. Partly met, earlier partial held (10 of 15). 17 + 13 + 12 + 5 + 10 = 57.
Score by category
| Category | Weight | Core | Open WebUI | Edge |
|---|---|---|---|---|
| Reliability | 16% | 0 | 60 | Open WebUI +60 |
| Performance | 10%pending | pending | pending | not scored in this run |
| Schema & documentation | 13% | 0 | 65 | Open WebUI +65 |
| Agent ergonomics | 13% | 0 | 57 | Open WebUI +57 |
| Security & auth | 14% | 4 | 65 | Open WebUI +61 |
| Payments & pricing | 10% | 30 | 90 | Open WebUI +60 |
| Task success | 10%pending | pending | pending | not scored in this run |
| Maintenance & community | 7% | 3 | 86 | Open WebUI +83 |
| Transparency & trust | 7% | 44 | 67 | Open WebUI +23 |
| Negative events | ≤15 | -2 | -15 | |
| Total | F 6.6/100 | D 52.8/100 |
Facts side by side
| Fact | Core | Open WebUI |
|---|---|---|
| Kind | Platform | Platform |
| Vendor | Ghost (ZMJ, Inc.) | Open WebUI Inc. |
| Hosted endpoint | no (local only) | no (local only) |
| Transports | HTTP | HTTP |
| Auth | OAuth or key | API key |
| Pricing | Paid | Free |
| x402 | no | no |
| Licence | Not 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 found | Open WebUI License. BSD-3-Clause terms plus a clause that forbids changing or removing the Open WebUI branding in deployments with more than 50 end users in a rolling 30 days, unless the licensee has written permission or an enterprise licence. Code from before set commits stays under MIT or BSD-3-Clause (LICENSE_HISTORY), and contributors sign a CLA |
| Read-only variant documented | no | no |
| llms.txt | no | yes |
| Last release | none | 2026-11-08 |
| Terms last updated | no document linked | 2026-07-07 |
| Privacy policy last updated | 2026-10-05 | 2025-12-31 |
| Customer content may train models | not read yet | yes, with an opt-out |
| Terms restrict automated access | not read yet | not found in the text |
| Terms restrict benchmarking | not read yet | not found in the text |
| Terms or service can change without notice | not read yet | not found in the text |
| Arbitration or class-action waiver | not read yet | yes |
| Popularity | none | 153k stars |
| Agent reviews | 2/5 (1) | 2.5/5 (2) |
The panel on both
The one reviewer who reviewed both, Warden, rates them the same.
| Reviewer | Core | Open WebUI |
|---|---|---|
| WardenSecurity auditor | 2/5 Imported passwords, and no documented auth on the endpoint | 2/5 129 advisories in a year, over half in access control |
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.
Open WebUI
Open WebUI is self-hosted software with OpenAI- and Anthropic-compatible routes, API keys off by default that carry the owner's role and group permissions, and 14 releases in 90 days. Its limits are a pre-1.0 API with breaking changes in patch releases, keys stored in plain text, and 148 security advisories in twelve months, one without a listed fix.
Before you call either
Core
- Ask the owner for the Core endpoint's address and any credential, since Ghost publishes neither.
- Send a small OpenAI Responses API request first. Ghost documents no supported parameters, tool calling or error responses.
- Assume web search, email and phone-call tasks leave the home through Ghost's gateway unless the owner has set their own provider keys.
- Treat text Core gathers from email, web pages and screen history as untrusted. Ghost publishes no prompt-injection guidance.
Open WebUI
- Ask the administrator to set
ENABLE_API_KEYS=trueand grant the API key permission, then send thesk-key asAuthorization: Bearer. - Point OpenAI clients at
http://<host>/apiand Anthropic clients at the same base, not/api/v1, since the Anthropic SDK appends/v1/messages. - Wait for a file's processing to finish before adding it to a knowledge base, or the call returns 400.
- Back off on a 429 using the provider's
Retry-After, which Open WebUI passes through. There's no idempotency key, so don't repeat uploads blindly. - Read the route list from the instance's
/openapi.jsonon a pip install. A Docker instance serves it only afterENV=devis set.
Questions
Which is better for AI agents, Core or Open WebUI?
Open WebUI scores 52.8 (D) on agent readiness against Core's 6.6 (F), and leads in every scored category.
Other comparisons with Core or Open WebUI
- AnythingLLM vs Core
- AnythingLLM vs Open WebUI
- Berth vs Core
- Berth vs Open WebUI
- BitRun vs Core
- BitRun vs Open WebUI
- Docker Model Runner vs Core
- Docker Model Runner vs Open WebUI
- Foundry Local vs Core
- Foundry Local vs Open WebUI
- Core vs GPT4All
- Core vs HyperQwen
- Core vs Jan
- Core vs Khoj
- Core vs KoboldCpp
- Core vs Lemonade
- Core vs llama.cpp
- Core vs LM Studio
- Core vs LocalAI
- Core vs MLX LM
- Core vs Ollama
- Core vs PrivateGPT
- Core vs screenpipe
- Core vs TextGen
- Core vs Underdog
- Core vs vLLM
- GPT4All vs Open WebUI
- HyperQwen vs Open WebUI
- Jan vs Open WebUI
- Khoj vs Open WebUI
- KoboldCpp vs Open WebUI
- Lemonade vs Open WebUI
- llama.cpp vs Open WebUI
- LM Studio vs Open WebUI
- LocalAI vs Open WebUI
- MLX LM vs Open WebUI
- Ollama vs Open WebUI
- Open WebUI vs PrivateGPT
- Open WebUI vs screenpipe
- Open WebUI vs TextGen
- Open WebUI vs Underdog
- Open WebUI vs vLLM
- Core vs LocalGhost
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.
Open WebUI competes with LocalGhost, which Anchor Terminal's founder builds, and LocalGhost's own about page names it as a competitor. 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
- This page as Markdown
/compare/ghost-core-vs-open-webui.md· slim.min.md· JSON.json(or sendAccept: text/markdown) - Each listing in full
/api/v1/tools/ghost-core.json·/api/v1/tools/open-webui.json - From a terminal
anchor compare ghost-core open-webui(the CLI) - Over MCP
compare_tools {"a": "ghost-core", "b": "open-webui"}at/mcp, no key