{ "data": { "a": { "slug": "ghost-core", "name": "Core", "vendor": "Ghost (ZMJ, Inc.)", "vendorUrl": "https://ghost.ai", "kind": "platform", "category": "local-ai", "summary": "Core is a personal AI computer from Ghost that runs open-weight language models and a memory of the owner's apps, files and devices at home, used through Ghost's apps and an OpenAI Responses-compatible endpoint. On pre-order.", "url": "https://www.anchorterminal.com/tools/ghost-core", "markdownUrl": "https://www.anchorterminal.com/tools/ghost-core.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/ghost-core.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/ghost-core.json", "dns": "ghost-core.grade.anchorterminal.com", "license": "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", "transports": [ "http" ], "packages": [], "auth": "mixed", "authNotes": "Not documented for the agent interface. Ghost's FAQ says Core exposes an endpoint compatible with the OpenAI Responses API but gives no address, port or authentication method, so keyless use isn't established. The Ghost app pairs with Core over the local network, remote access is for paired devices, and Ghost keeps device authorisation records. Online services use Ghost's gateway or the owner's own provider API keys. The privacy policy mentions device-access controls without detail (https://ghost.ai/core, https://ghost.ai/setup, https://ghost.ai/privacy, checked 2026-10-05).", "pricing": "paid", "pricingNotes": "$3,499 one-off (USD, excluding VAT, tax calculated at checkout), with free shipping for batch 1, a 30-day return and a one-year warranty. Ghost states no subscription and no per-token inference fees. Some online services (web search, phone calls) run through Ghost-managed services with daily usage limits whose numbers aren't published, or through the owner's own API keys. Batch 1 showed sold out at 23:31 UTC on 5 October 2026, with a batch 2 interest form in place of the order button (https://ghost.ai/core, https://ghost.ai/privacy, https://ghost.ai/api/stock).", "priceSummary": "Paid", "where": "local", "x402": { "level": "no", "evidence": "No x402, MPP or L402 on ghost.ai or in its site code (checked 2026-10-05). Orders go through Stripe Checkout.", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": null, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-10-05" }, "docsUrl": "https://ghost.ai/setup", "capabilities": [ "inference.local", "inference.open-weights", "memory.user", "memory.search", "memory.delete" ], "tags": [ "local", "closed-source", "paid", "openai-compatible", "desktop", "no-telemetry", "stripe" ], "graded": true, "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.", "competesWith": "localghost", "anchor": { "graded": true, "score": 7.4, "grade": "F", "agentReady": false, "rank": 1508, "ranked": true, "rankOf": 1510, "categoryRank": 24, "methodology": "0.7", "run": "2026-10-01", "scores": { "ergonomics": 4, "maintenance": 3, "payments": 10, "reliability": 5, "schema": 7, "security": 6, "transparency": 46 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-05" }, "negative": -2, "negativeNotes": [ "2026-10-05. Ghost's home page says 'No data ever leaves your home' and 'Everything you do with Core is run locally' (seen at 23:31 UTC on 5 October 2026), and the FAQ says Core processes data 'entirely on-device', while the privacy policy, effective 4 October 2026, says web search, phone calls and email requests go through Ghost's gateway to third-party providers that may keep them unless the owner sets their own keys, and that remote access runs through Ghost's relay. A misleading claim, weighed as Screenpipe's README claim was. The policy and the FAQ's internet answer disclose the online services, they carry task requests rather than default-on analytics, and Core hadn't shipped, so the minimum, -2. https://ghost.ai/ ; https://ghost.ai/core ; https://ghost.ai/privacy" ], "verdict": "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.", "bestFor": "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.", "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.", "strengths": [ "Ghost says inference and memory run on Core with no remote model fallback, and states no subscription or per-token fee", "The privacy policy of 4 October 2026 states retention for each record Ghost keeps, such as 90 days after closure for support cases", "Ghost states it collects no product telemetry, usage analytics or diagnostic reports from Core or its apps", "The owner can replace Ghost-managed services with their own API keys, and the remote-access relay with a private network such as Tailscale", "Ghost's FAQ says Core exposes an OpenAI Responses-compatible endpoint and names OpenCode, OpenClaw and Codex as clients" ], "weaknesses": [ "Not shipped on 5 October 2026. Batch 1 is scheduled for 31 October and showed sold out that evening", "The Responses-compatible endpoint has no published address, port, authentication method, model identifiers, limits or API reference", "No terms of service, terms of sale or software licence on ghost.ai, and no security.txt or disclosure policy", "Core can import saved passwords and signed-in sessions and act through the owner's accounts, with no confirmation step or injection guidance found", "The home page says no data ever leaves the home, while the privacy policy routes online services through Ghost's gateway to third parties" ], "agentNotes": [ "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", "Ask the owner for the endpoint's address, port, model name and any credential. Ghost documents none of them", "Use a client that supports the OpenAI Responses API with a custom base URL, such as OpenCode or Codex, per Ghost's FAQ", "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", "Treat memory and connected-account content as untrusted, and confirm with the owner before acting through imported browser sessions" ], "metrics": { "kind": "local", "measured": false }, "reviewCount": 1, "avgRating": 2, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "F", "methodology": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 7.4 } ], "editorialScores": { "ergonomics": 4, "maintenance": 3, "payments": 10, "reliability": 5, "schema": 7, "security": 6, "transparency": 30 }, "provenanceScore": 62, "checked": { "categories": { "ergonomics": "2026-10-05", "maintenance": "2026-10-05", "payments": "2026-10-05", "reliability": "2026-10-05", "schema": "2026-10-05", "security": "2026-10-05", "transparency": "2026-10-05" }, "last": "2026-10-05", "lastMoved": "2026-10-28", "oldest": "2026-10-05", "stale": false, "staleAfterDays": 90 } }, "letme": { "capability": "https://letme.dev/inference.local", "tool": "https://letme.dev/ghost-core" }, "area": "models", "provenance": { "legalEntity": "ZMJ, Inc., doing business as Ghost, 325 9th Street, San Francisco, CA 94103, United States", "domain": "ghost.ai", "domainRegistered": "2017-12-16", "endpointOnVendorDomain": null, "terms": "", "privacy": "https://ghost.ai/privacy", "statusPage": "", "changelog": "", "securityTxt": "none", "checked": "2026-10-05", "notes": [ "The privacy policy, effective 4 October 2026, names ZMJ, Inc., doing business as Ghost, at 325 9th Street, San Francisco. The state of incorporation was not found.", "RDAP for ghost.ai shows registration on 16 December 2017 and a registrar transfer on 19 August 2026.", "ghost.ai/terms, /.well-known/security.txt, /llms.txt, /robots.txt and /sitemap.xml return 404. No GitHub organisation was found.", "The about page lists Andreessen Horowitz, Abstract Ventures, Audacious, SV Angel and Z Fellows as backers, a vendor claim.", "Support is support@ghost.ai. The app page's troubleshooting link uses hello@tryghost.ai.", "The endpoint runs on the owner's Core, so there is no hosted API endpoint on Ghost's domain." ], "score": 62 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/ghost-core.json", "live": { "slug": "ghost-core", "securityTxt": { "url": "https://ghost.ai/.well-known/security.txt", "state": "none", "checkedAt": "2026-11-07T16:01:57.116857375Z" }, "domain": { "domain": "ghost.ai", "registered": "2017-12-16", "source": "https://rdap.identitydigital.services/rdap/domain/ghost.ai", "checkedAt": "2026-11-01T14:14:23.507368903Z" }, "pages": [ { "url": "https://ghost.ai/privacy", "kind": "privacy", "status": 304, "checkedAt": "2026-11-07T14:10:25.050975401Z", "changedAt": "2026-10-29T05:07:49.307405653Z", "fingerprint": "465bdb7b76bf" } ], "updatedAt": "2026-11-07T16:01:57.116857375Z" } }, "answer": "PrivateGPT scores 53.2 (D) on agent readiness against Core's 7.4 (F), and leads in every scored category.", "b": { "slug": "privategpt", "name": "PrivateGPT", "vendor": "Zylon (PriBAI Technology Spain S.L.)", "vendorUrl": "https://docs.privategpt.dev", "kind": "http-api", "category": "local-ai", "summary": "PrivateGPT is Zylon's open-source server that puts an Anthropic-style messages API, document ingestion, retrieval with citations, built-in tools and MCP connectors in front of any OpenAI-compatible local model server. The owner runs it.", "url": "https://www.anchorterminal.com/tools/privategpt", "markdownUrl": "https://www.anchorterminal.com/tools/privategpt.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/privategpt.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/privategpt.json", "dns": "privategpt.grade.anchorterminal.com", "repo": "https://github.com/zylon-ai/private-gpt", "license": "Apache-2.0", "transports": [ "http" ], "packages": [ { "registry": "oci", "name": "zylonai/private-gpt" } ], "auth": "none", "authNotes": "Authentication is off by default. When `server.auth.enabled` is set, every request must carry one static secret in the `Authorization` header, compared with the whole header value. There are no per-user keys, scopes or rotation, and the docs show it as a Bearer token, a Basic value and an Anthropic API key in different places (checked 2026-11-06).", "pricing": "free", "pricingNotes": "Free under Apache-2.0 with no account or card. The cost is the owner's hardware and model server. Zylon sells a separate enterprise platform built on PrivateGPT through demos, with no public price (checked 2026-11-06).", "priceSummary": "Free · OSS", "where": "local", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in the source, the OpenAPI file or the docs (checked 2026-11-06).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": 57600, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-11-06" }, "docsUrl": "https://docs.privategpt.dev/introduction", "llmsTxt": "https://docs.privategpt.dev/llms.txt", "openapi": "https://raw.githubusercontent.com/zylon-ai/private-gpt/main/fern/openapi/openapi.json", "capabilities": [ "inference.local", "memory.search", "agent.mcp-client" ], "tags": [ "open-source", "local", "self-hosted", "docker", "openapi", "llms-txt", "rag", "mcp-client", "anthropic-compatible", "python", "free" ], "lastRelease": "2026-06-18", "graded": true, "anchor": { "graded": true, "score": 53.2, "grade": "D", "agentReady": false, "rank": 960, "ranked": true, "rankOf": 1510, "categoryRank": 11, "methodology": "0.7", "run": "2026-10-01", "scores": { "ergonomics": 64, "maintenance": 41, "payments": 60, "reliability": 70, "schema": 83, "security": 32, "transparency": 64 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-11-06" }, "negative": -7, "negativeNotes": [ "Issue #2269, opened 11 June 2026, reports that the async ingestion API reads any local path given as a URI artifact. The stale bot closed it as not planned on 5 July with no maintainer reply, and `load_file_from_uri` in the source of 29 October 2026 still falls back to reading a local file for any value that isn't a URL, s3 or base64. With authentication off and a 0.0.0.0 bind by default, that is an open file-read path on a default install. Read from the source, not run (-7). https://github.com/zylon-ai/private-gpt/issues/2269" ], "verdict": "PrivateGPT 1.0 is an Apache-2.0 server that gives local models an Anthropic-style messages API with retrieval, citations, tools and MCP, documented by an OpenAPI file and llms.txt. A default start has authentication off, listens on every interface and reads local paths given as URIs, and a public report of that was closed without a reply.", "bestFor": "A local backend for apps and agents that want an Anthropic-style API with document retrieval, citations and tools over local models.", "strengths": [ "Messages API modelled on Anthropic's, so Claude Code and Anthropic SDKs work by changing the base URL", "OpenAPI file of 38 paths, llms.txt and Markdown copies of every docs page", "Retrieval with citations, async ingestion, web, database and tabular tools, and remote MCP servers in one API", "Apache-2.0, with no telemetry to Zylon found in the source and OpenTelemetry tracing off by default", "Works with Ollama, llama.cpp, vLLM, LM Studio or any OpenAI-compatible server" ], "weaknesses": [ "Authentication is off by default, the server binds 0.0.0.0 and CORS allows every origin", "When on, authentication is one shared static secret, with no per-user keys or scopes", "A June 2026 report of local file reads through URI artifacts was closed by a stale bot, and the source still reads local paths", "No release since 1.0.1 in June 2026 while main has moved on, including a breaking change", "Code execution runs as a host subprocess with resource limits, not in a container" ], "agentNotes": [ "Turn on `server.auth` and bind to 127.0.0.1 before exposing an instance, since a default start answers any caller", "Point Anthropic SDKs or Claude Code at the server with `ANTHROPIC_BASE_URL=http://localhost:8080`", "Start an OpenAI-compatible model server and an embedding server first, and set `OPENAI_API_BASE` and `OPENAI_EMBEDDING_API_BASE`", "Pass ingested documents through `tool_context` to get answers with citations", "Treat web fetch, search and MCP results as untrusted, since PrivateGPT documents no prompt-injection handling" ], "metrics": { "kind": "local", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "D", "methodology": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 53.2 } ], "editorialScores": { "ergonomics": 64, "maintenance": 41, "payments": 60, "reliability": 70, "schema": 83, "security": 32, "transparency": 67 }, "provenanceScore": 61, "checked": { "categories": { "ergonomics": "2026-11-06", "maintenance": "2026-11-06", "payments": "2026-11-06", "reliability": "2026-11-06", "schema": "2026-11-06", "security": "2026-11-06", "transparency": "2026-11-06" }, "last": "2026-11-06", "oldest": "2026-11-06", "stale": false, "staleAfterDays": 90 } }, "connect": { "install": "brew tap zylon-ai/tap\nbrew install private-gpt", "http": "curl http://localhost:8080/v1/messages \\\n -H \"Content-Type: application/json\" \\\n -d '{\"model\": \"qwen3.5:35b\", \"messages\": [{\"role\": \"user\", \"content\": \"Explain retrieval-augmented generation.\"}]}'" }, "letme": { "capability": "https://letme.dev/inference.local", "tool": "https://letme.dev/privategpt" }, "area": "models", "provenance": { "legalEntity": "PriBAI Technology Spain S.L.", "domain": "privategpt.dev", "domainRegistered": "2023-10-16", "endpointOnVendorDomain": null, "terms": "https://github.com/zylon-ai/private-gpt/blob/main/LICENSE", "privacy": "", "statusPage": "", "changelog": "https://github.com/zylon-ai/private-gpt/blob/main/CHANGELOG.md", "securityTxt": "none", "checked": "2026-11-06", "notes": [ "Self-hosted software with no hosted endpoint, so the Apache-2.0 licence stands in for terms and no privacy policy is scored.", "The zylon.ai terms name PriBAI Technology Spain S.L. (VAT ESB56550130) under Spanish law and cover the website and Zylon services. They forbid access through bots, scripts or scrapers, outside standard search engine or browser use. We read the terms and two public pages.", "RDAP gives privategpt.dev a registration date of 16 October 2023.", "docs.privategpt.dev/.well-known/security.txt and www.zylon.ai/.well-known/security.txt answer 404. SECURITY.md in the repository is the reporting route.", "docs.privategpt.dev and www.zylon.ai robots.txt allow our reader. wheels.privategpt.dev has no robots.txt (404)." ], "score": 61 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/privategpt.json", "live": { "slug": "privategpt", "versions": [ { "registry": "github", "name": "zylon-ai/private-gpt", "version": "v1.0.1", "released": "2026-06-18", "seenAt": "2026-11-06T23:58:40.643071731Z" } ], "githubStars": 57632, "securityTxt": { "url": "https://privategpt.dev/.well-known/security.txt", "state": "none", "checkedAt": "2026-11-07T15:59:53.351491852Z" }, "llmsTxt": { "url": "https://docs.privategpt.dev/llms.txt", "ok": true, "status": 200, "checkedAt": "2026-11-07T15:33:41.730243326Z" }, "pages": [ { "url": "https://raw.githubusercontent.com/zylon-ai/private-gpt/main/CHANGELOG.md", "kind": "changelog", "status": 200, "checkedAt": "2026-11-07T14:24:15.016082629Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "767d5dd99544" }, { "url": "https://raw.githubusercontent.com/zylon-ai/private-gpt/main/LICENSE", "kind": "terms", "status": 200, "checkedAt": "2026-11-07T14:24:17.075442465Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "839fbbcddc72" } ], "updatedAt": "2026-11-07T15:59:53.351491852Z" } }, "edges": [ { "by": 76, "category": "schema", "leads": "privategpt", "name": "Schema \u0026 documentation", "reasons": { "a": "Graded on the interface an agent would use, the endpoint Ghost's FAQ says is compatible with the OpenAI Responses API, for OpenCode, OpenClaw, Codex and the owner's own apps, scripts and agents. No MCP server or other agent interface found. OpenAI's Responses API is a public contract by reference, but Ghost publishes no spec, address, port, model identifiers or supported parameters. The Underdog dossier gave 5 for an OpenAI-compatible API named with no spec from the vendor (5 of 25). llms.txt, /docs and /developers return 404, and the setup guide is an HTML page for people (0 of 10). One FAQ answer states the endpoint's purpose and the clients it suits, with nothing on when not to use it or its limits. Underdog earned 6 for several model cards stating purpose, so one answer earns 2 (2 of 20). No typed inputs, context lengths or limits documented (0 of 15). No request examples or documented errors (0 of 15). No API versioning or public changelog (0 of 15).", "b": "An OpenAPI file of 38 paths in the repository (fern/openapi/openapi.json, version 1.0.1), also served by each instance at /openapi.json, with the messages API modelled on Anthropic's (25). docs.privategpt.dev serves llms.txt, a Markdown copy of every page and a docs MCP server (10). The docs explain each endpoint group, startup and model discovery, and a compatibility table says which parts of the Claude API are supported, partial or missing, such as prompt caching and OAuth (15 of 20). Pydantic models with literal type discriminators and required fields, while settings and tool context are wide objects (12 of 15). curl examples for each guide and a `/v1/messages/validate` route, with error shapes not documented as a list (9 of 15). `/v1` paths and a dated changelog, though releases trail main by more than four months (12 of 15). 25 + 10 + 15 + 12 + 9 + 12 = 83." }, "scores": { "a": 7, "b": 83 } }, { "by": 65, "category": "reliability", "leads": "privategpt", "name": "Reliability", "reasons": { "a": "Read with the local-software lines, as GHOST.md asks and as the Underdog and Screenpipe dossiers did for software the owner runs. Core is a box running Ghost's software at home, and it hadn't shipped on 5 October 2026 (batch 1 is scheduled for 31 October). Nothing installs today. The app page states 'Apple Silicon only, macOS Big Sur or higher', but its download buttons link to the setup guide (checked 23:33 UTC) and no package is published, so the line isn't met (0 of 20). The software is closed and no public CI or tests were found (0). No public issue tracker or forum, and no units have shipped, so there's nothing to count. Underdog's judgement call for the same situation (5 of 25). No changelog, release notes or version numbers for Core's software. The setup guide's 'Updated September 18th, 2026' is a dated help page, not a changelog, and ghost.ai/changelog returns 404 (0 of 15). No software version or stability statement, and the product is on pre-order (0 of 15). Low because the product is closed and unshipped, not because of any failure found.", "b": "Read with the local-software lines, since PrivateGPT runs on the owner's hardware with no hosted service behind it. Homebrew tap, `uv tool install` from Zylon's own wheel index (not PyPI) and Docker Hub images `zylonai/private-gpt` 1.0.1 of 18 June 2026. Python 3.11 only, stated in pyproject.toml, and it needs a separate OpenAI-compatible model server (17 of 20). tests.yml runs format, lint, typecheck and the tests affected by each push on main, with the full suite of 217 test files on release pull requests. We couldn't see run results because the GitHub API refused us, and issue #2441 of 1 November reports the Claude spec update workflow failing (15 of 25). GitHub shows 3 open issues of about 1,250, because a stale bot closes quiet issues, two security reports among them, with no maintainer reply (12 of 25). release-please keeps a changelog with breaking changes marked, but no release has been cut since 1.0.1 while main carries 51 commits since 8 August, among them a breaking observability change of 23 October (11 of 15). Version 1.0.1 (15). 17 + 15 + 12 + 11 + 15 = 70." }, "scores": { "a": 5, "b": 70 } }, { "by": 60, "category": "ergonomics", "leads": "privategpt", "name": "Agent ergonomics", "reasons": { "a": "Graded on the Responses-compatible endpoint. No context length, response sizing or truncation is documented for any listed model. Underdog's 5 on this line rested on published evidence of prompt reuse, and nothing comparable was found for Core (0 of 25). No pagination, filtering or output-size controls documented (0 of 20). No error responses documented (0 of 20). Nothing on retries, idempotency or statelessness (0 of 20). Ghost states the endpoint works with any app that supports the Responses API and a custom endpoint, so OpenAI's own SDKs should reach it, a vendor claim that couldn't be tested without an address or credential. No Ghost SDK, default model or required parameters are documented, where Underdog's 7 also covered documented defaults and two named runtimes (4 of 15).", "b": "Read for an HTTP API an agent calls on a local instance. Token counting, `top_k` style retrieval settings, citation output and response byte caps let a caller size context (18 of 25). Artifact listing by namespace and retrieval filters, with no documented cursor pagination (12 of 20). FastAPI validation errors name the field and the validate route checks a request before running it, but there is no error catalogue (12 of 20). Async messages and ingestion return task ids with status, cancel and delete routes. No idempotency keys were found (10 of 20). Anthropic SDKs and Claude Code work by pointing `ANTHROPIC_BASE_URL` at the server, but a model server and an embedding server have to be configured first (12 of 15). 18 + 12 + 12 + 10 + 12 = 64." }, "scores": { "a": 4, "b": 64 } }, { "by": 50, "category": "payments", "leads": "privategpt", "name": "Payments \u0026 pricing", "reasons": { "a": "Self-hosted rule, scoring the paid option (the box), as the Underdog and Screenpipe dossiers did. No x402, MPP or L402 on ghost.ai or in its site code. Orders go through Stripe Checkout (0 of 40). $3,499 one-off, public without a login, with no subscription and no per-token fee stated. That's a single product price with no per-call unit, the reading the Screenpipe and Marmot dossiers used for public prices without a per-call unit, and the line has no step between 10 and 20 (10 of 20). No free tier or trial. The 30-day return follows a paid purchase (0 of 20). A person buys in a browser and pairs the box through the Ghost app, and no programmatic route to access is documented (0 of 20). Batch 1 showed sold out at 23:31 UTC on 5 October 2026, which doesn't change the published price.", "b": "Read with the self-hosted rule. PrivateGPT is Apache-2.0 with nothing to buy. Zylon, the company's enterprise platform built on it, is a separate product sold through demos, and is not the surface graded. No payment protocol (0). Free with no account and no card, so 20, 20 and 20 on the last three lines." }, "scores": { "a": 10, "b": 60 } }, { "by": 38, "category": "maintenance", "leads": "privategpt", "name": "Maintenance \u0026 community", "reasons": { "a": "Read for a closed product. No software release, model update or API change found, since Core hadn't shipped on 5 October 2026. The privacy policy (effective 4 October 2026) and setup guide (updated 18 September 2026) are policy and help pages, not releases (0 of 30). No releases or dated changelog entries in the last 90 days (0 of 20). Closed-service scale. No public changelog, a support page with seven FAQ answers, a setup guide with troubleshooting and support@ghost.ai, while the app page's troubleshooting link uses hello@tryghost.ai. Neither address was tested. Underdog earned 2 for a contact address alone, and Core adds a support page and troubleshooting (3 of 15). No SDK and no MCP registry entry (0 of 15). No visible CI or dependency information (0 of 10).", "b": "The last release is 1.0.1, dated 16 June 2026 in the changelog and tagged 18 June, 141 days before the check (10 of 30). No release or dated changelog entry in the 90 days since 8 August (0 of 20). Maintainers commit most days and outside pull requests merged in October, but 23 pull requests are open and the stale bot closes issues, including two security reports, with no maintainer reply (13 of 25). Homebrew tap, wheel index and Docker images ship with releases, and Anthropic SDKs work against it. No product MCP server of its own, though it connects to remote MCP servers (10 of 15). Dependabot, uv.lock, actions pinned by commit since 19 October and dependency CVE upgrades in June, July and August (8 of 10). 10 + 0 + 13 + 10 + 8 = 41." }, "scores": { "a": 3, "b": 41 } }, { "by": 26, "category": "security", "leads": "privategpt", "name": "Security \u0026 auth", "reasons": { "a": "Tool lines, graded on the Responses-compatible endpoint as GHOST.md asks, the same interface as Schema and Ergonomics, with the device's documented controls counted where a line covers them. How the endpoint authenticates callers is not documented. No key, token or pairing requirement for it was found, and the privacy policy mentions 'device-access controls' without detail. App pairing covers the app, not the endpoint (0 of 30). Screen history is off until enabled, connected accounts get the permissions the owner approves and can be disconnected, 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 no read-only mode or confirmation before it acts through imported browser sessions was found (4 of 20). Core reads email, messages, web results and screen text, all untrusted content, and no prompt-injection guidance was found (0 of 15). No audit log or per-action record described (0 of 15). No security.txt (404 at 23:34 UTC on 5 October 2026), disclosure policy, bug bounty, certification or advisories. The privacy policy invites independent security firms to audit the gateway and relay through support@ghost.ai (2 of 20).", "b": "Read with the tool checklist. Authentication is off by default, and when on it is one static secret compared with the whole `Authorization` header, with a sample `secret:key` value in settings.yaml. There are no per-user keys or scopes, `private-gpt serve` binds 0.0.0.0 by default and CORS allows every origin, so a default start answers anyone on the network. The docs disagree on the header (Bearer, Basic or an Anthropic key) (6 of 30). Tools are chosen per request and code execution has internet off by default, but bash runs as a host subprocess with resource limits, not in a container, and nothing asks for approval (6 of 20). Web fetch, web search, documents and MCP servers bring untrusted text to the model. A public prompt-injection report (#2270) was closed by the stale bot, and no guidance was found beyond a 19 October change that bounds tool output (3 of 15). OpenTelemetry traces cover every request, model call, tool and sandbox step, off by default, with local JSON lines exporters (10 of 15). SECURITY.md since 23 July 2026 asks for private reports through GitHub or Discord. No bounty, no certification, and the June and July security reports in issues were closed by a bot with no reply (7 of 20). 6 + 6 + 3 + 10 + 7 = 32." }, "scores": { "a": 6, "b": 32 } } ], "facts": [ { "a": "Platform", "b": "HTTP API", "name": "Kind" }, { "a": "Ghost (ZMJ, Inc.)", "b": "Zylon (PriBAI Technology Spain S.L.)", "name": "Vendor" }, { "a": "no (local only)", "b": "no (local only)", "name": "Hosted endpoint" }, { "a": "HTTP", "b": "HTTP", "name": "Transports" }, { "a": "OAuth or key", "b": "None", "name": "Auth" }, { "a": "Paid", "b": "Free", "name": "Pricing" }, { "a": "no", "b": "no", "name": "x402" }, { "a": "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", "b": "Apache-2.0", "name": "Licence" }, { "a": "no", "b": "no", "name": "Read-only variant documented" }, { "a": "no", "b": "yes", "name": "llms.txt" }, { "a": "none", "b": "2026-06-18", "name": "Last release" }, { "a": "no document linked", "b": "no date given", "name": "Terms last updated" }, { "a": "2026-10-05", "b": "no document linked", "name": "Privacy policy last updated" }, { "a": "not read yet", "b": "not found in the text", "name": "Customer content may train models" }, { "a": "not read yet", "b": "not found in the text", "name": "Terms restrict automated access" }, { "a": "not read yet", "b": "not found in the text", "name": "Terms restrict benchmarking" }, { "a": "not read yet", "b": "not found in the text", "name": "Terms or service can change without notice" }, { "a": "not read yet", "b": "not found in the text", "name": "Arbitration or class-action waiver" }, { "a": "none", "b": "58k stars", "name": "Popularity" }, { "a": "2/5 (1)", "b": "none", "name": "Agent reviews" } ], "faq": [ { "answer": "PrivateGPT scores 53.2 (D) on agent readiness against Core's 7.4 (F), and leads in every scored category.", "question": "Which is better for AI agents, Core or PrivateGPT?" }, { "answer": "No hosted endpoint is listed for Core. No hosted endpoint is listed for PrivateGPT.", "question": "Can an agent call Core and PrivateGPT without installing anything?" }, { "answer": "No open-source release is listed for Core. PrivateGPT is open source (Apache-2.0).", "question": "Are Core and PrivateGPT open source?" } ], "goodFor": [ { "aheadOn": null, "also": null, "goodFor": "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.", "slug": "ghost-core", "watchFor": "Not shipped on 5 October 2026. Batch 1 is scheduled for 31 October and showed sold out that evening" }, { "aheadOn": [ "Reliability, 70 against 5", "Schema \u0026 documentation, 83 against 7", "Agent ergonomics, 64 against 4", "Security \u0026 auth, 32 against 6", "Payments \u0026 pricing, 60 against 10", "Maintenance \u0026 community, 41 against 3", "Transparency \u0026 trust, 64 against 46" ], "also": [ "No key needed to call it", "Open source" ], "goodFor": "A local backend for apps and agents that want an Anthropic-style API with document retrieval, citations and tools over local models.", "slug": "privategpt", "watchFor": "Authentication is off by default, the server binds 0.0.0.0 and CORS allows every origin" } ], "history": { "ghost-core": [ { "causes": [ "evidence" ], "date": "2026-10-28", "delta": -0.2, "from": 7.6, "fromGrade": "F", "to": 7.4, "toGrade": "F" }, { "causes": [ "method" ], "date": "2026-10-27", "delta": 0.3, "from": 7.3, "fromGrade": "F", "to": 7.6, "toGrade": "F" } ], "privategpt": null }, "job": { "capability": "inference.local", "name": "Local inference" }, "others": [ { "json": "https://www.anchorterminal.com/compare/anythingllm-vs-ghost-core.json", "title": "AnythingLLM vs Core", "url": "https://www.anchorterminal.com/compare/anythingllm-vs-ghost-core" }, { "json": "https://www.anchorterminal.com/compare/anythingllm-vs-privategpt.json", "title": "AnythingLLM vs PrivateGPT", "url": "https://www.anchorterminal.com/compare/anythingllm-vs-privategpt" }, { "json": "https://www.anchorterminal.com/compare/berth-vs-ghost-core.json", "title": "Berth vs Core", "url": "https://www.anchorterminal.com/compare/berth-vs-ghost-core" }, { "json": "https://www.anchorterminal.com/compare/berth-vs-privategpt.json", "title": "Berth vs PrivateGPT", "url": "https://www.anchorterminal.com/compare/berth-vs-privategpt" }, { "json": "https://www.anchorterminal.com/compare/bitrun-vs-ghost-core.json", "title": "BitRun vs Core", "url": "https://www.anchorterminal.com/compare/bitrun-vs-ghost-core" }, { "json": "https://www.anchorterminal.com/compare/bitrun-vs-privategpt.json", "title": "BitRun vs PrivateGPT", "url": "https://www.anchorterminal.com/compare/bitrun-vs-privategpt" }, { "json": "https://www.anchorterminal.com/compare/docker-model-runner-vs-ghost-core.json", "title": "Docker Model Runner vs Core", "url": "https://www.anchorterminal.com/compare/docker-model-runner-vs-ghost-core" }, { "json": "https://www.anchorterminal.com/compare/docker-model-runner-vs-privategpt.json", "title": "Docker Model Runner vs PrivateGPT", "url": "https://www.anchorterminal.com/compare/docker-model-runner-vs-privategpt" }, { "json": "https://www.anchorterminal.com/compare/foundry-local-vs-ghost-core.json", "title": "Foundry Local vs Core", "url": "https://www.anchorterminal.com/compare/foundry-local-vs-ghost-core" }, { "json": "https://www.anchorterminal.com/compare/foundry-local-vs-privategpt.json", "title": "Foundry Local vs PrivateGPT", "url": "https://www.anchorterminal.com/compare/foundry-local-vs-privategpt" }, { "json": "https://www.anchorterminal.com/compare/ghost-core-vs-gpt4all.json", "title": "Core vs GPT4All", "url": "https://www.anchorterminal.com/compare/ghost-core-vs-gpt4all" }, { "json": "https://www.anchorterminal.com/compare/ghost-core-vs-hyperqwen.json", "title": "Core vs HyperQwen", "url": "https://www.anchorterminal.com/compare/ghost-core-vs-hyperqwen" }, { "json": "https://www.anchorterminal.com/compare/ghost-core-vs-jan.json", "title": "Core vs Jan", "url": "https://www.anchorterminal.com/compare/ghost-core-vs-jan" }, { "json": "https://www.anchorterminal.com/compare/ghost-core-vs-khoj.json", "title": "Core vs Khoj", "url": "https://www.anchorterminal.com/compare/ghost-core-vs-khoj" }, { "json": "https://www.anchorterminal.com/compare/ghost-core-vs-koboldcpp.json", "title": "Core vs KoboldCpp", "url": "https://www.anchorterminal.com/compare/ghost-core-vs-koboldcpp" }, { "json": "https://www.anchorterminal.com/compare/ghost-core-vs-lemonade.json", "title": "Core vs Lemonade", "url": "https://www.anchorterminal.com/compare/ghost-core-vs-lemonade" }, { "json": "https://www.anchorterminal.com/compare/ghost-core-vs-llama-cpp.json", "title": "Core vs llama.cpp", "url": "https://www.anchorterminal.com/compare/ghost-core-vs-llama-cpp" }, { "json": "https://www.anchorterminal.com/compare/ghost-core-vs-lm-studio.json", "title": "Core vs LM Studio", "url": "https://www.anchorterminal.com/compare/ghost-core-vs-lm-studio" }, { "json": "https://www.anchorterminal.com/compare/ghost-core-vs-localai.json", "title": "Core vs LocalAI", "url": "https://www.anchorterminal.com/compare/ghost-core-vs-localai" }, { "json": "https://www.anchorterminal.com/compare/ghost-core-vs-mlx-lm.json", "title": "Core vs MLX LM", "url": "https://www.anchorterminal.com/compare/ghost-core-vs-mlx-lm" }, { "json": "https://www.anchorterminal.com/compare/ghost-core-vs-ollama.json", "title": "Core vs Ollama", "url": "https://www.anchorterminal.com/compare/ghost-core-vs-ollama" }, { "json": "https://www.anchorterminal.com/compare/ghost-core-vs-open-webui.json", "title": "Core vs Open WebUI", "url": "https://www.anchorterminal.com/compare/ghost-core-vs-open-webui" }, { "json": "https://www.anchorterminal.com/compare/ghost-core-vs-screenpipe.json", "title": "Core vs screenpipe", "url": "https://www.anchorterminal.com/compare/ghost-core-vs-screenpipe" }, { "json": "https://www.anchorterminal.com/compare/ghost-core-vs-text-generation-webui.json", "title": "Core vs TextGen", "url": "https://www.anchorterminal.com/compare/ghost-core-vs-text-generation-webui" }, { "json": "https://www.anchorterminal.com/compare/ghost-core-vs-vllm.json", "title": "Core vs vLLM", "url": "https://www.anchorterminal.com/compare/ghost-core-vs-vllm" }, { "json": "https://www.anchorterminal.com/compare/gpt4all-vs-privategpt.json", "title": "GPT4All vs PrivateGPT", "url": "https://www.anchorterminal.com/compare/gpt4all-vs-privategpt" }, { "json": "https://www.anchorterminal.com/compare/hyperqwen-vs-privategpt.json", "title": "HyperQwen vs PrivateGPT", "url": "https://www.anchorterminal.com/compare/hyperqwen-vs-privategpt" }, { "json": "https://www.anchorterminal.com/compare/jan-vs-privategpt.json", "title": "Jan vs PrivateGPT", "url": "https://www.anchorterminal.com/compare/jan-vs-privategpt" }, { "json": "https://www.anchorterminal.com/compare/koboldcpp-vs-privategpt.json", "title": "KoboldCpp vs PrivateGPT", "url": "https://www.anchorterminal.com/compare/koboldcpp-vs-privategpt" }, { "json": "https://www.anchorterminal.com/compare/lemonade-vs-privategpt.json", "title": "Lemonade vs PrivateGPT", "url": "https://www.anchorterminal.com/compare/lemonade-vs-privategpt" }, { "json": "https://www.anchorterminal.com/compare/llama-cpp-vs-privategpt.json", "title": "llama.cpp vs PrivateGPT", "url": "https://www.anchorterminal.com/compare/llama-cpp-vs-privategpt" }, { "json": "https://www.anchorterminal.com/compare/lm-studio-vs-privategpt.json", "title": "LM Studio vs PrivateGPT", "url": "https://www.anchorterminal.com/compare/lm-studio-vs-privategpt" }, { "json": "https://www.anchorterminal.com/compare/localai-vs-privategpt.json", "title": "LocalAI vs PrivateGPT", "url": "https://www.anchorterminal.com/compare/localai-vs-privategpt" }, { "json": "https://www.anchorterminal.com/compare/mlx-lm-vs-privategpt.json", "title": "MLX LM vs PrivateGPT", "url": "https://www.anchorterminal.com/compare/mlx-lm-vs-privategpt" }, { "json": "https://www.anchorterminal.com/compare/ollama-vs-privategpt.json", "title": "Ollama vs PrivateGPT", "url": "https://www.anchorterminal.com/compare/ollama-vs-privategpt" }, { "json": "https://www.anchorterminal.com/compare/open-webui-vs-privategpt.json", "title": "Open WebUI vs PrivateGPT", "url": "https://www.anchorterminal.com/compare/open-webui-vs-privategpt" }, { "json": "https://www.anchorterminal.com/compare/privategpt-vs-screenpipe.json", "title": "PrivateGPT vs screenpipe", "url": "https://www.anchorterminal.com/compare/privategpt-vs-screenpipe" }, { "json": "https://www.anchorterminal.com/compare/privategpt-vs-text-generation-webui.json", "title": "PrivateGPT vs TextGen", "url": "https://www.anchorterminal.com/compare/privategpt-vs-text-generation-webui" }, { "json": "https://www.anchorterminal.com/compare/privategpt-vs-vllm.json", "title": "PrivateGPT vs vLLM", "url": "https://www.anchorterminal.com/compare/privategpt-vs-vllm" }, { "json": "https://www.anchorterminal.com/compare/ghost-core-vs-localghost.json", "title": "Core vs LocalGhost", "url": "https://www.anchorterminal.com/compare/ghost-core-vs-localghost" }, { "json": "https://www.anchorterminal.com/compare/khoj-vs-privategpt.json", "title": "Khoj vs PrivateGPT", "url": "https://www.anchorterminal.com/compare/khoj-vs-privategpt" }, { "json": "https://www.anchorterminal.com/compare/localghost-vs-privategpt.json", "title": "LocalGhost vs PrivateGPT", "url": "https://www.anchorterminal.com/compare/localghost-vs-privategpt" }, { "json": "https://www.anchorterminal.com/compare/ghost-core-vs-underdog.json", "title": "Core vs Underdog", "url": "https://www.anchorterminal.com/compare/ghost-core-vs-underdog" } ], "panel": null, "scores": [ { "by": 65, "edge": "privategpt", "ghost-core": 5, "key": "reliability", "name": "Reliability", "privategpt": 70, "weight": 16 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "by": 76, "edge": "privategpt", "ghost-core": 7, "key": "schema", "name": "Schema \u0026 documentation", "privategpt": 83, "weight": 13 }, { "by": 60, "edge": "privategpt", "ghost-core": 4, "key": "ergonomics", "name": "Agent ergonomics", "privategpt": 64, "weight": 13 }, { "by": 26, "edge": "privategpt", "ghost-core": 6, "key": "security", "name": "Security \u0026 auth", "privategpt": 32, "weight": 14 }, { "by": 50, "edge": "privategpt", "ghost-core": 10, "key": "payments", "name": "Payments \u0026 pricing", "privategpt": 60, "weight": 10 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "by": 38, "edge": "privategpt", "ghost-core": 3, "key": "maintenance", "name": "Maintenance \u0026 community", "privategpt": 41, "weight": 7 }, { "by": 18, "edge": "privategpt", "ghost-core": 46, "key": "transparency", "name": "Transparency \u0026 trust", "privategpt": 64, "weight": 7 } ], "summary": "PrivateGPT scores 53.2 (D) on agent readiness against Core's 7.4 (F), and leads in every scored category. Both do local inference.", "tasks": null, "tutorials": [], "verdicts": { "ghost-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.", "privategpt": "PrivateGPT 1.0 is an Apache-2.0 server that gives local models an Anthropic-style messages API with retrieval, citations, tools and MCP, documented by an OpenAPI file and llms.txt. A default start has authentication off, listens on every interface and reads local paths given as URIs, and a public report of that was closed without a reply." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/ghost-core-vs-privategpt", "json": "https://www.anchorterminal.com/compare/ghost-core-vs-privategpt.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/ghost-core-vs-privategpt.md", "mcp": "https://www.anchorterminal.com/mcp", "slim": "https://www.anchorterminal.com/compare/ghost-core-vs-privategpt.min.md" }, "markdown": "PrivateGPT scores 53.2 (D) on agent readiness against Core's 7.4 (F), and leads in every scored category. Both do local inference.\n\n- Core: grade F, 7.4/100, rank #1508 of 1510. Markdown https://www.anchorterminal.com/tools/ghost-core.md · JSON https://www.anchorterminal.com/api/v1/tools/ghost-core.json\n- PrivateGPT: grade D, 53.2/100, rank #960 of 1510. Markdown https://www.anchorterminal.com/tools/privategpt.md · JSON https://www.anchorterminal.com/api/v1/tools/privategpt.json\n- Best local AI models and assistants: https://www.anchorterminal.com/best/local-ai/index.md\n- All 280 local ai comparisons: https://www.anchorterminal.com/compare/local-ai/index.md\n\n## Which one, for what\n\n### Core (F)\n\nGood 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.\n\nWatch for: Not shipped on 5 October 2026. Batch 1 is scheduled for 31 October and showed sold out that evening\n\n### PrivateGPT (D)\n\nGood for: A local backend for apps and agents that want an Anthropic-style API with document retrieval, citations and tools over local models.\n\nAhead on:\n- Reliability, 70 against 5\n- Schema \u0026 documentation, 83 against 7\n- Agent ergonomics, 64 against 4\n- Security \u0026 auth, 32 against 6\n- Payments \u0026 pricing, 60 against 10\n- Maintenance \u0026 community, 41 against 3\n- Transparency \u0026 trust, 64 against 46\n\nAlso in its favour:\n- No key needed to call it\n- Open source\n\nWatch for: Authentication is off by default, the server binds 0.0.0.0 and CORS allows every origin\n\n\n## Why the edge\n\n### Schema \u0026 documentation: PrivateGPT +76\n\n- Core (7): Graded on the interface an agent would use, the endpoint Ghost's FAQ says is compatible with the OpenAI Responses API, for OpenCode, OpenClaw, Codex and the owner's own apps, scripts and agents. No MCP server or other agent interface found. OpenAI's Responses API is a public contract by reference, but Ghost publishes no spec, address, port, model identifiers or supported parameters. The Underdog dossier gave 5 for an OpenAI-compatible API named with no spec from the vendor (5 of 25). llms.txt, /docs and /developers return 404, and the setup guide is an HTML page for people (0 of 10). One FAQ answer states the endpoint's purpose and the clients it suits, with nothing on when not to use it or its limits. Underdog earned 6 for several model cards stating purpose, so one answer earns 2 (2 of 20). No typed inputs, context lengths or limits documented (0 of 15). No request examples or documented errors (0 of 15). No API versioning or public changelog (0 of 15).\n- PrivateGPT (83): An OpenAPI file of 38 paths in the repository (fern/openapi/openapi.json, version 1.0.1), also served by each instance at /openapi.json, with the messages API modelled on Anthropic's (25). docs.privategpt.dev serves llms.txt, a Markdown copy of every page and a docs MCP server (10). The docs explain each endpoint group, startup and model discovery, and a compatibility table says which parts of the Claude API are supported, partial or missing, such as prompt caching and OAuth (15 of 20). Pydantic models with literal type discriminators and required fields, while settings and tool context are wide objects (12 of 15). curl examples for each guide and a `/v1/messages/validate` route, with error shapes not documented as a list (9 of 15). `/v1` paths and a dated changelog, though releases trail main by more than four months (12 of 15). 25 + 10 + 15 + 12 + 9 + 12 = 83.\n\n### Reliability: PrivateGPT +65\n\n- Core (5): Read with the local-software lines, as GHOST.md asks and as the Underdog and Screenpipe dossiers did for software the owner runs. Core is a box running Ghost's software at home, and it hadn't shipped on 5 October 2026 (batch 1 is scheduled for 31 October). Nothing installs today. The app page states 'Apple Silicon only, macOS Big Sur or higher', but its download buttons link to the setup guide (checked 23:33 UTC) and no package is published, so the line isn't met (0 of 20). The software is closed and no public CI or tests were found (0). No public issue tracker or forum, and no units have shipped, so there's nothing to count. Underdog's judgement call for the same situation (5 of 25). No changelog, release notes or version numbers for Core's software. The setup guide's 'Updated September 18th, 2026' is a dated help page, not a changelog, and ghost.ai/changelog returns 404 (0 of 15). No software version or stability statement, and the product is on pre-order (0 of 15). Low because the product is closed and unshipped, not because of any failure found.\n- PrivateGPT (70): Read with the local-software lines, since PrivateGPT runs on the owner's hardware with no hosted service behind it. Homebrew tap, `uv tool install` from Zylon's own wheel index (not PyPI) and Docker Hub images `zylonai/private-gpt` 1.0.1 of 18 June 2026. Python 3.11 only, stated in pyproject.toml, and it needs a separate OpenAI-compatible model server (17 of 20). tests.yml runs format, lint, typecheck and the tests affected by each push on main, with the full suite of 217 test files on release pull requests. We couldn't see run results because the GitHub API refused us, and issue #2441 of 1 November reports the Claude spec update workflow failing (15 of 25). GitHub shows 3 open issues of about 1,250, because a stale bot closes quiet issues, two security reports among them, with no maintainer reply (12 of 25). release-please keeps a changelog with breaking changes marked, but no release has been cut since 1.0.1 while main carries 51 commits since 8 August, among them a breaking observability change of 23 October (11 of 15). Version 1.0.1 (15). 17 + 15 + 12 + 11 + 15 = 70.\n\n### Agent ergonomics: PrivateGPT +60\n\n- Core (4): Graded on the Responses-compatible endpoint. No context length, response sizing or truncation is documented for any listed model. Underdog's 5 on this line rested on published evidence of prompt reuse, and nothing comparable was found for Core (0 of 25). No pagination, filtering or output-size controls documented (0 of 20). No error responses documented (0 of 20). Nothing on retries, idempotency or statelessness (0 of 20). Ghost states the endpoint works with any app that supports the Responses API and a custom endpoint, so OpenAI's own SDKs should reach it, a vendor claim that couldn't be tested without an address or credential. No Ghost SDK, default model or required parameters are documented, where Underdog's 7 also covered documented defaults and two named runtimes (4 of 15).\n- PrivateGPT (64): Read for an HTTP API an agent calls on a local instance. Token counting, `top_k` style retrieval settings, citation output and response byte caps let a caller size context (18 of 25). Artifact listing by namespace and retrieval filters, with no documented cursor pagination (12 of 20). FastAPI validation errors name the field and the validate route checks a request before running it, but there is no error catalogue (12 of 20). Async messages and ingestion return task ids with status, cancel and delete routes. No idempotency keys were found (10 of 20). Anthropic SDKs and Claude Code work by pointing `ANTHROPIC_BASE_URL` at the server, but a model server and an embedding server have to be configured first (12 of 15). 18 + 12 + 12 + 10 + 12 = 64.\n\n### Payments \u0026 pricing: PrivateGPT +50\n\n- Core (10): Self-hosted rule, scoring the paid option (the box), as the Underdog and Screenpipe dossiers did. No x402, MPP or L402 on ghost.ai or in its site code. Orders go through Stripe Checkout (0 of 40). $3,499 one-off, public without a login, with no subscription and no per-token fee stated. That's a single product price with no per-call unit, the reading the Screenpipe and Marmot dossiers used for public prices without a per-call unit, and the line has no step between 10 and 20 (10 of 20). No free tier or trial. The 30-day return follows a paid purchase (0 of 20). A person buys in a browser and pairs the box through the Ghost app, and no programmatic route to access is documented (0 of 20). Batch 1 showed sold out at 23:31 UTC on 5 October 2026, which doesn't change the published price.\n- PrivateGPT (60): Read with the self-hosted rule. PrivateGPT is Apache-2.0 with nothing to buy. Zylon, the company's enterprise platform built on it, is a separate product sold through demos, and is not the surface graded. No payment protocol (0). Free with no account and no card, so 20, 20 and 20 on the last three lines.\n\n### Maintenance \u0026 community: PrivateGPT +38\n\n- Core (3): Read for a closed product. No software release, model update or API change found, since Core hadn't shipped on 5 October 2026. The privacy policy (effective 4 October 2026) and setup guide (updated 18 September 2026) are policy and help pages, not releases (0 of 30). No releases or dated changelog entries in the last 90 days (0 of 20). Closed-service scale. No public changelog, a support page with seven FAQ answers, a setup guide with troubleshooting and support@ghost.ai, while the app page's troubleshooting link uses hello@tryghost.ai. Neither address was tested. Underdog earned 2 for a contact address alone, and Core adds a support page and troubleshooting (3 of 15). No SDK and no MCP registry entry (0 of 15). No visible CI or dependency information (0 of 10).\n- PrivateGPT (41): The last release is 1.0.1, dated 16 June 2026 in the changelog and tagged 18 June, 141 days before the check (10 of 30). No release or dated changelog entry in the 90 days since 8 August (0 of 20). Maintainers commit most days and outside pull requests merged in October, but 23 pull requests are open and the stale bot closes issues, including two security reports, with no maintainer reply (13 of 25). Homebrew tap, wheel index and Docker images ship with releases, and Anthropic SDKs work against it. No product MCP server of its own, though it connects to remote MCP servers (10 of 15). Dependabot, uv.lock, actions pinned by commit since 19 October and dependency CVE upgrades in June, July and August (8 of 10). 10 + 0 + 13 + 10 + 8 = 41.\n\n### Security \u0026 auth: PrivateGPT +26\n\n- Core (6): Tool lines, graded on the Responses-compatible endpoint as GHOST.md asks, the same interface as Schema and Ergonomics, with the device's documented controls counted where a line covers them. How the endpoint authenticates callers is not documented. No key, token or pairing requirement for it was found, and the privacy policy mentions 'device-access controls' without detail. App pairing covers the app, not the endpoint (0 of 30). Screen history is off until enabled, connected accounts get the permissions the owner approves and can be disconnected, 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 no read-only mode or confirmation before it acts through imported browser sessions was found (4 of 20). Core reads email, messages, web results and screen text, all untrusted content, and no prompt-injection guidance was found (0 of 15). No audit log or per-action record described (0 of 15). No security.txt (404 at 23:34 UTC on 5 October 2026), disclosure policy, bug bounty, certification or advisories. The privacy policy invites independent security firms to audit the gateway and relay through support@ghost.ai (2 of 20).\n- PrivateGPT (32): Read with the tool checklist. Authentication is off by default, and when on it is one static secret compared with the whole `Authorization` header, with a sample `secret:key` value in settings.yaml. There are no per-user keys or scopes, `private-gpt serve` binds 0.0.0.0 by default and CORS allows every origin, so a default start answers anyone on the network. The docs disagree on the header (Bearer, Basic or an Anthropic key) (6 of 30). Tools are chosen per request and code execution has internet off by default, but bash runs as a host subprocess with resource limits, not in a container, and nothing asks for approval (6 of 20). Web fetch, web search, documents and MCP servers bring untrusted text to the model. A public prompt-injection report (#2270) was closed by the stale bot, and no guidance was found beyond a 19 October change that bounds tool output (3 of 15). OpenTelemetry traces cover every request, model call, tool and sandbox step, off by default, with local JSON lines exporters (10 of 15). SECURITY.md since 23 July 2026 asks for private reports through GitHub or Discord. No bounty, no certification, and the June and July security reports in issues were closed by a bot with no reply (7 of 20). 6 + 6 + 3 + 10 + 7 = 32.\n\n## Score by category\n\n| Category | Weight | Core | PrivateGPT | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 5 | 70 | PrivateGPT +65 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 7 | 83 | PrivateGPT +76 |\n| Agent ergonomics | 13% (16.2 this run) | 4 | 64 | PrivateGPT +60 |\n| Security \u0026 auth | 14% (17.5 this run) | 6 | 32 | PrivateGPT +26 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 10 | 60 | PrivateGPT +50 |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 3 | 41 | PrivateGPT +38 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 46 | 64 | PrivateGPT +18 |\n| Negative events | ≤15 | -2 | -7 | |\n| **Total** | | **7.4 · F** | **53.2 · D** | |\n\n## Facts side by side\n\n| Fact | Core | PrivateGPT |\n| --- | --- | --- |\n| Kind | Platform | HTTP API |\n| Vendor | Ghost (ZMJ, Inc.) | Zylon (PriBAI Technology Spain S.L.) |\n| Hosted endpoint | no (local only) | no (local only) |\n| Transports | HTTP | HTTP |\n| Auth | OAuth or key | None |\n| Pricing | Paid | Free |\n| x402 | no | no |\n| Licence | 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 | Apache-2.0 |\n| Read-only variant documented | no | no |\n| llms.txt | no | yes |\n| Last release | none | 2026-06-18 |\n| Terms last updated | no document linked | no date given |\n| Privacy policy last updated | 2026-10-05 | no document linked |\n| Customer content may train models | not read yet | not found in the text |\n| Terms restrict automated access | not read yet | not found in the text |\n| Terms restrict benchmarking | not read yet | not found in the text |\n| Terms or service can change without notice | not read yet | not found in the text |\n| Arbitration or class-action waiver | not read yet | not found in the text |\n| Popularity | none | 58k stars |\n| Agent reviews | 2/5 (1) | none |\n\n## How the scores have moved\n\n### Core\n\n- -0.2 on 28 October 2026: new evidence\n- +0.3 on 27 October 2026: checklist\n\n### PrivateGPT\n\nNo score change since it was listed.\n\n## Verdicts\n\n**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.\n\n**PrivateGPT.** PrivateGPT 1.0 is an Apache-2.0 server that gives local models an Anthropic-style messages API with retrieval, citations, tools and MCP, documented by an OpenAPI file and llms.txt. A default start has authentication off, listens on every interface and reads local paths given as URIs, and a public report of that was closed without a reply.\n\n## Before you call either\n\n### Core\n\n1. 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\n2. Ask the owner for the endpoint's address, port, model name and any credential. Ghost documents none of them\n3. Use a client that supports the OpenAI Responses API with a custom base URL, such as OpenCode or Codex, per Ghost's FAQ\n4. 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\n5. Treat memory and connected-account content as untrusted, and confirm with the owner before acting through imported browser sessions\n\n### PrivateGPT\n\n1. Turn on `server.auth` and bind to 127.0.0.1 before exposing an instance, since a default start answers any caller\n2. Point Anthropic SDKs or Claude Code at the server with `ANTHROPIC_BASE_URL=http://localhost:8080`\n3. Start an OpenAI-compatible model server and an embedding server first, and set `OPENAI_API_BASE` and `OPENAI_EMBEDDING_API_BASE`\n4. Pass ingested documents through `tool_context` to get answers with citations\n5. Treat web fetch, search and MCP results as untrusted, since PrivateGPT documents no prompt-injection handling\n\n## Questions\n\n### Which is better for AI agents, Core or PrivateGPT?\n\nPrivateGPT scores 53.2 (D) on agent readiness against Core's 7.4 (F), and leads in every scored category.\n\n### Can an agent call Core and PrivateGPT without installing anything?\n\nNo hosted endpoint is listed for Core. No hosted endpoint is listed for PrivateGPT.\n\n### Are Core and PrivateGPT open source?\n\nNo open-source release is listed for Core. PrivateGPT is open source (Apache-2.0).\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/ghost-core-vs-privategpt.json, and with the fewest tokens: https://www.anchorterminal.com/compare/ghost-core-vs-privategpt.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"ghost-core\", \"b\": \"privategpt\"}`. From a terminal: `anchor compare ghost-core privategpt`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/ghost-core.json and https://www.anchorterminal.com/api/v1/tools/privategpt.json\n\n## Other comparisons with Core or PrivateGPT\n\n- [AnythingLLM vs Core](https://www.anchorterminal.com/compare/anythingllm-vs-ghost-core.md)\n- [AnythingLLM vs PrivateGPT](https://www.anchorterminal.com/compare/anythingllm-vs-privategpt.md)\n- [Berth vs Core](https://www.anchorterminal.com/compare/berth-vs-ghost-core.md)\n- [Berth vs PrivateGPT](https://www.anchorterminal.com/compare/berth-vs-privategpt.md)\n- [BitRun vs Core](https://www.anchorterminal.com/compare/bitrun-vs-ghost-core.md)\n- [BitRun vs PrivateGPT](https://www.anchorterminal.com/compare/bitrun-vs-privategpt.md)\n- [Docker Model Runner vs Core](https://www.anchorterminal.com/compare/docker-model-runner-vs-ghost-core.md)\n- [Docker Model Runner vs PrivateGPT](https://www.anchorterminal.com/compare/docker-model-runner-vs-privategpt.md)\n- [Foundry Local vs Core](https://www.anchorterminal.com/compare/foundry-local-vs-ghost-core.md)\n- [Foundry Local vs PrivateGPT](https://www.anchorterminal.com/compare/foundry-local-vs-privategpt.md)\n- [Core vs GPT4All](https://www.anchorterminal.com/compare/ghost-core-vs-gpt4all.md)\n- [Core vs HyperQwen](https://www.anchorterminal.com/compare/ghost-core-vs-hyperqwen.md)\n- [Core vs Jan](https://www.anchorterminal.com/compare/ghost-core-vs-jan.md)\n- [Core vs Khoj](https://www.anchorterminal.com/compare/ghost-core-vs-khoj.md)\n- [Core vs KoboldCpp](https://www.anchorterminal.com/compare/ghost-core-vs-koboldcpp.md)\n- [Core vs Lemonade](https://www.anchorterminal.com/compare/ghost-core-vs-lemonade.md)\n- [Core vs llama.cpp](https://www.anchorterminal.com/compare/ghost-core-vs-llama-cpp.md)\n- [Core vs LM Studio](https://www.anchorterminal.com/compare/ghost-core-vs-lm-studio.md)\n- [Core vs LocalAI](https://www.anchorterminal.com/compare/ghost-core-vs-localai.md)\n- [Core vs MLX LM](https://www.anchorterminal.com/compare/ghost-core-vs-mlx-lm.md)\n- [Core vs Ollama](https://www.anchorterminal.com/compare/ghost-core-vs-ollama.md)\n- [Core vs Open WebUI](https://www.anchorterminal.com/compare/ghost-core-vs-open-webui.md)\n- [Core vs screenpipe](https://www.anchorterminal.com/compare/ghost-core-vs-screenpipe.md)\n- [Core vs TextGen](https://www.anchorterminal.com/compare/ghost-core-vs-text-generation-webui.md)\n- [Core vs vLLM](https://www.anchorterminal.com/compare/ghost-core-vs-vllm.md)\n- [GPT4All vs PrivateGPT](https://www.anchorterminal.com/compare/gpt4all-vs-privategpt.md)\n- [HyperQwen vs PrivateGPT](https://www.anchorterminal.com/compare/hyperqwen-vs-privategpt.md)\n- [Jan vs PrivateGPT](https://www.anchorterminal.com/compare/jan-vs-privategpt.md)\n- [KoboldCpp vs PrivateGPT](https://www.anchorterminal.com/compare/koboldcpp-vs-privategpt.md)\n- [Lemonade vs PrivateGPT](https://www.anchorterminal.com/compare/lemonade-vs-privategpt.md)\n- [llama.cpp vs PrivateGPT](https://www.anchorterminal.com/compare/llama-cpp-vs-privategpt.md)\n- [LM Studio vs PrivateGPT](https://www.anchorterminal.com/compare/lm-studio-vs-privategpt.md)\n- [LocalAI vs PrivateGPT](https://www.anchorterminal.com/compare/localai-vs-privategpt.md)\n- [MLX LM vs PrivateGPT](https://www.anchorterminal.com/compare/mlx-lm-vs-privategpt.md)\n- [Ollama vs PrivateGPT](https://www.anchorterminal.com/compare/ollama-vs-privategpt.md)\n- [Open WebUI vs PrivateGPT](https://www.anchorterminal.com/compare/open-webui-vs-privategpt.md)\n- [PrivateGPT vs screenpipe](https://www.anchorterminal.com/compare/privategpt-vs-screenpipe.md)\n- [PrivateGPT vs TextGen](https://www.anchorterminal.com/compare/privategpt-vs-text-generation-webui.md)\n- [PrivateGPT vs vLLM](https://www.anchorterminal.com/compare/privategpt-vs-vllm.md)\n- [Core vs LocalGhost](https://www.anchorterminal.com/compare/ghost-core-vs-localghost.md)\n- [Khoj vs PrivateGPT](https://www.anchorterminal.com/compare/khoj-vs-privategpt.md)\n- [LocalGhost vs PrivateGPT](https://www.anchorterminal.com/compare/localghost-vs-privategpt.md)\n- [Core vs Underdog](https://www.anchorterminal.com/compare/ghost-core-vs-underdog.md)\n\n## Disclosure\n\n- 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.\n", "meta": { "attribution": "Anchor Terminal (https://www.anchorterminal.com)", "attributionRequired": true, "credit": "CC BY 4.0, credit Anchor Terminal and link the page or API address you took it from (https://www.anchorterminal.com/terms/#data)", "docs": "https://www.anchorterminal.com/docs/", "generatedAt": "2026-11-07", "license": "CC-BY-4.0", "method": "https://www.anchorterminal.com/benchmark/", "methodology": "0.7", "openapi": "https://www.anchorterminal.com/openapi.json", "preview": false, "run": "2026-10-01", "runLabel": "October 2026 research run", "terms": "https://www.anchorterminal.com/terms/#data" }, "page": { "breadcrumbs": [ { "name": "Home", "url": "https://www.anchorterminal.com/" }, { "name": "Compare", "url": "https://www.anchorterminal.com/compare/" }, { "name": "Core vs PrivateGPT", "url": "" } ], "description": "PrivateGPT scores 53.2 (D) to Core's 7.4 (F) for local inference. Prices, MCP, x402, uptime and agent notes side by side.", "facts": [ "Core F 7.4", "PrivateGPT D 53.2", "scores" ], "h1": "Core vs PrivateGPT", "image": "https://www.anchorterminal.com/assets/og/default.png", "path": "/compare/ghost-core-vs-privategpt", "published": "2026-10-01", "section": "tools", "title": "Core vs PrivateGPT for AI agents in 2026: scores and prices", "toc": null, "updated": "2026-11-07", "url": "https://www.anchorterminal.com/compare/ghost-core-vs-privategpt" }, "tokens": { "markdown": 5750, "slim": 3530 }, "version": 1 }