{ "data": { "a": { "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": 954, "ranked": true, "rankOf": 1486, "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" } }, "answer": "PrivateGPT scores 53.2 (D) on agent readiness against vLLM's 48.4 (D), and leads in 2 of 7 scored categories. vLLM leads on security \u0026 auth, maintenance \u0026 community and transparency \u0026 trust.", "b": { "slug": "vllm", "name": "vLLM", "vendor": "vLLM project (PyTorch Foundation)", "vendorUrl": "https://vllm.ai", "kind": "http-api", "category": "local-ai", "summary": "vLLM is an open-source inference and serving engine for open-weight language models. `vllm serve` runs an HTTP server with OpenAI-compatible, Anthropic Messages, embedding, reranking and transcription routes on the owner's own GPUs or CPUs.", "url": "https://www.anchorterminal.com/tools/vllm", "markdownUrl": "https://www.anchorterminal.com/tools/vllm.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/vllm.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/vllm.json", "dns": "vllm.grade.anchorterminal.com", "repo": "https://github.com/vllm-project/vllm", "license": "Apache-2.0", "transports": [ "http" ], "packages": [ { "registry": "pypi", "name": "vllm" }, { "registry": "oci", "name": "vllm/vllm-openai" } ], "auth": "none", "authNotes": "No credential by default. `--api-key` (one or several keys) or `VLLM_API_KEY` turns on a Bearer check for paths under `/v1`, `/v2`, `/inference` and `/cohere` only, so `/invocations`, `/pooling`, `/classify`, `/score`, `/rerank` and control routes such as `/pause` stay open. Keys have no scopes and change with a restart. The key is read from the `Authorization` header, never the query string. gRPC has no authentication (https://github.com/vllm-project/vllm/blob/main/docs/usage/security.md).", "pricing": "free", "pricingNotes": "Free under Apache-2.0, with no account, key or card. Nothing is sold by the project. You pay for your own hardware and electricity.", "priceSummary": "Free · OSS", "where": "local", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in the docs or the source (checked 2026-10-09).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": 93444, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-10-09" }, "docsUrl": "https://docs.vllm.ai/en/stable/", "capabilities": [ "inference.local", "inference.open-weights", "embed.text", "rerank", "speech.stt", "inference.decision", "agent.mcp-client" ], "tags": [ "open-source", "local", "self-hosted", "free", "no-card", "openai-compatible", "docker", "pre-1.0", "telemetry-default-on" ], "lastRelease": "2026-11-01", "graded": true, "anchor": { "graded": true, "score": 48.4, "grade": "D", "agentReady": false, "rank": 1117, "ranked": true, "rankOf": 1486, "categoryRank": 15, "methodology": "0.7", "run": "2026-10-01", "scores": { "ergonomics": 64, "maintenance": 88, "payments": 60, "reliability": 59, "schema": 68, "security": 50, "transparency": 71 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-11-04" }, "negative": -15, "negativeNotes": [ "2025-11-20 to 2026-10-28. Counted one by one from OSV's list of vllm records on PyPI, which on 4 November 2026 shows 61 GitHub advisories published in the 12 months before (2 Critical, 16 High, 40 Moderate, 3 Low), beside 91 PyPI advisory-database records that weren't counted. All but one (GHSA-98f3-hwg4-4rf7, Moderate) show a fix. By this run's values, the two fixed Criticals over two months old (GHSA-4r2x-xpjr-7cvv, video decoding code execution, 2 February; GHSA-94f4-hr76-p5j6, Host header bypass of the API key, 16 June) cost 1 each, twelve fixed Highs over two months old 1 each, and four fixed Highs under two months (GHSA-gx7p-2j49-hfq4, 23 October; GHSA-h3rc-6mm3-gc2m, 27 October; GHSA-h3rc-j82p-2c3h and GHSA-6757-hggm-hp2w, 28 October) 2 each. 2 + 12 + 8 = 22 before any Moderate is counted, held at the -15 floor (grouped, the 9 October reading took -6). https://osv.dev/list?q=vllm\u0026ecosystem=PyPI; https://github.com/vllm-project/vllm/security/advisories" ], "verdict": "Apache-2.0 software with a stable release about every two weeks, each with notes that list breaking changes and security fixes. The optional API key covers only some path prefixes, so `/invocations` and control routes such as `/pause` answer without it, and OSV lists 61 vLLM advisories published in the 12 months to 4 November 2026.", "bestFor": "An owner with a GPU server who wants many concurrent requests against one open-weight model behind OpenAI or Anthropic compatible routes.", "strengths": [ "OpenAI chat, completions, responses and embeddings, Anthropic `/v1/messages`, Cohere embed and rerank, transcription and `/v1/systemone` from one server", "Apache-2.0, with a written three-stage deprecation policy and release notes that carry a breaking changes section", "Eight stable releases in the 90 days to 4 November 2026, from v0.27.0 on 10 August to v0.33.0 on 1 November", "A 650-line security guide names every route the API key does and does not protect, and the limits of multi-tenant use", "Usage statistics are documented field by field, with `VLLM_NO_USAGE_STATS`, `DO_NOT_TRACK` or a file as opt-outs" ], "weaknesses": [ "`--api-key` guards only the `/v1`, `/v2`, `/inference` and `/cohere` prefixes. `/invocations`, `/pooling`, `/classify`, `/score`, `/rerank`, `/pause` and `/update_weights` answer without it", "No key by default, the server binds every interface when `--host` is unset, and CORS allows any origin", "61 GitHub advisories for vllm on OSV from the 12 months to 4 November 2026, two of them critical, most of them remote crashes or resource exhaustion", "Pre-1.0 (0.33.0), with breaking changes in each fortnightly release and compatibility kept for a limited number of minor versions", "Usage statistics are sent to stats.vllm.ai by default, and no privacy policy or retention period for them was found" ], "agentNotes": [ "Put a reverse proxy that allowlists routes in front of the server. `--api-key` leaves `/invocations` and the control routes open", "Pass `--host 127.0.0.1` for single-machine use. With no `--host` the server listens on every interface", "Set `VLLM_NO_USAGE_STATS=1` or `DO_NOT_TRACK=1` before starting if nothing should be sent to stats.vllm.ai", "Start with `--enable-auto-tool-choice` and the `--tool-call-parser` for the model before sending tools. Tool calling is off without them", "Send `max_tokens` on every request, and read the breaking changes section of the release notes before upgrading a minor version" ], "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": 48.4 } ], "editorialScores": { "ergonomics": 64, "maintenance": 88, "payments": 60, "reliability": 59, "schema": 68, "security": 50, "transparency": 80 }, "provenanceScore": 61, "checked": { "categories": { "ergonomics": "2026-11-04", "maintenance": "2026-11-04", "payments": "2026-11-04", "reliability": "2026-11-04", "schema": "2026-11-04", "security": "2026-11-04", "transparency": "2026-11-04" }, "last": "2026-11-04", "lastMoved": "2026-11-04", "oldest": "2026-11-04", "stale": false, "staleAfterDays": 90 } }, "connect": { "install": "uv pip install vllm --torch-backend=auto\nvllm serve Qwen/Qwen2.5-1.5B-Instruct # listens on port 8000", "http": "curl http://localhost:8000/v1/chat/completions \\\n -H \"Content-Type: application/json\" \\\n -d '{\n \"model\": \"Qwen/Qwen2.5-1.5B-Instruct\",\n \"messages\": [\n {\"role\": \"system\", \"content\": \"You are a helpful assistant.\"},\n {\"role\": \"user\", \"content\": \"Who won the world series in 2020?\"}\n ]\n }'", "claudeCode": "ANTHROPIC_BASE_URL=http://localhost:8000 \\\nANTHROPIC_API_KEY=dummy \\\nANTHROPIC_AUTH_TOKEN=dummy \\\nANTHROPIC_DEFAULT_OPUS_MODEL=my-model \\\nANTHROPIC_DEFAULT_SONNET_MODEL=my-model \\\nANTHROPIC_DEFAULT_HAIKU_MODEL=my-model \\\nclaude" }, "letme": { "capability": "https://letme.dev/inference.local", "tool": "https://letme.dev/vllm" }, "area": "models", "provenance": { "legalEntity": "The Linux Foundation (vLLM is a PyTorch Foundation project)", "domain": "vllm.ai", "domainRegistered": "", "endpointOnVendorDomain": null, "terms": "", "privacy": "", "statusPage": "", "changelog": "https://github.com/vllm-project/vllm/releases", "securityTxt": "none", "checked": "2026-10-09", "notes": [ "vllm.ai links no terms and no privacy policy, and its footer reads © 2026 vLLM. The project publishes none for the software or for stats.vllm.ai, so the Apache-2.0 licence stands in for terms.", "pytorch.org/projects/vllm/ lists vLLM among PyTorch Foundation projects and says UC Berkeley contributed it to the Linux Foundation in July 2024. The Linux Foundation's policies are linked from that page and are not specific to vLLM.", "vllm.ai/.well-known/security.txt and docs.vllm.ai/.well-known/security.txt return 404. SECURITY.md asks for private reports through GitHub.", "There's no shared hosted endpoint. The server runs on the owner's hardware. The software posts usage statistics to stats.vllm.ai unless turned off." ], "score": 61 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/vllm.json", "live": { "slug": "vllm", "versions": [ { "registry": "github", "name": "vllm-project/vllm", "version": "v0.33.0rc3", "released": "2026-11-02", "seenAt": "2026-11-07T00:16:07.577627449Z" }, { "registry": "pypi", "name": "vllm", "version": "0.33.0", "released": "2026-11-02", "seenAt": "2026-11-07T00:16:07.395308523Z" } ], "githubStars": 96478, "pypiWeekly": 716557, "securityTxt": { "url": "https://vllm.ai/.well-known/security.txt", "state": "none", "checkedAt": "2026-11-07T16:01:37.179206185Z" }, "domain": { "domain": "vllm.ai", "registered": "2023-06-19", "source": "https://rdap.identitydigital.services/rdap/domain/vllm.ai", "checkedAt": "2026-11-01T14:25:04.602881936Z" }, "github": { "repo": "vllm-project/vllm", "checkedAt": "2026-11-02T09:36:45.633133581Z", "stars": 96116, "archived": false, "issuesEnabled": true, "pushedAt": "2026-11-02T07:57:03Z", "openIssues": 2749, "openPRs": 7022, "issuesOpened90d": 2489, "issuesClosed90d": 1807, "prsMerged90d": 4861, "ci": { "branch": "main", "runs": 50, "success": 39, "failure": 6, "other": 5, "latest": "success", "latestAt": "2026-11-02T08:00:22Z" }, "advisories": [ { "ghsa": "GHSA-894j-wg8m-63h8", "severity": "medium", "published": "2026-10-27T22:24:06Z" }, { "ghsa": "GHSA-w4cg-mhc7-mgw3", "severity": "medium", "published": "2026-10-27T22:22:44Z" }, { "ghsa": "GHSA-vxqj-p4gw-9h4c", "severity": "medium", "published": "2026-10-27T22:22:11Z" }, { "ghsa": "GHSA-9g3c-x747-c6wr", "severity": "medium", "published": "2026-10-27T22:20:43Z" }, { "ghsa": "GHSA-5q78-j82c-2vr2", "severity": "medium", "published": "2026-10-27T22:18:41Z" }, { "ghsa": "GHSA-m9fg-w9qh-67pc", "severity": "medium", "published": "2026-10-27T22:14:15Z" }, { "ghsa": "GHSA-vvpg-rrww-wpmh", "cve": "CVE-2026-115917", "severity": "low", "published": "2026-10-20T07:37:49Z" }, { "ghsa": "GHSA-8397-8qf6-f2gm", "cve": "CVE-2026-115913", "severity": "medium", "published": "2026-10-20T07:37:27Z" }, { "ghsa": "GHSA-gq5q-89c7-vhvx", "cve": "CVE-2026-115914", "severity": "medium", "published": "2026-10-20T07:37:11Z" }, { "ghsa": "GHSA-h3rc-j82p-2c3h", "cve": "CVE-2026-115915", "severity": "high", "published": "2026-10-20T07:36:56Z" }, { "ghsa": "GHSA-6757-hggm-hp2w", "cve": "CVE-2026-115912", "severity": "high", "published": "2026-10-20T07:36:30Z" }, { "ghsa": "GHSA-frvg-qw88-hww9", "cve": "CVE-2026-94624", "severity": "medium", "published": "2026-10-20T07:35:45Z" }, { "ghsa": "GHSA-q97c-p368-75c4", "cve": "CVE-2026-115916", "severity": "medium", "published": "2026-10-20T07:35:17Z" }, { "ghsa": "GHSA-x567-49g5-p4cf", "cve": "CVE-2026-115918", "severity": "medium", "published": "2026-10-20T07:34:11Z" }, { "ghsa": "GHSA-542m-9234-8gvf", "cve": "CVE-2026-115911", "severity": "medium", "published": "2026-10-20T07:33:26Z" }, { "ghsa": "GHSA-w9r6-29q4-pvpr", "severity": "medium", "published": "2026-10-09T08:27:08Z" }, { "ghsa": "GHSA-4m6g-h9mv-wqjc", "severity": "high", "published": "2026-10-09T08:24:22Z" }, { "ghsa": "GHSA-34qw-q2h2-jp3m", "severity": "medium", "published": "2026-10-09T08:21:43Z" }, { "ghsa": "GHSA-mm38-5g96-7j6x", "severity": "high", "published": "2026-10-09T08:12:07Z" }, { "ghsa": "GHSA-vfp2-c8pq-v6h6", "severity": "high", "published": "2026-10-09T07:58:03Z" }, { "ghsa": "GHSA-r45p-7qwx-qwjw", "severity": "medium", "published": "2026-10-09T07:55:16Z" }, { "ghsa": "GHSA-w2v2-5662-8v5q", "severity": "medium", "published": "2026-10-09T07:49:41Z" }, { "ghsa": "GHSA-6pgw-f3pv-4h8q", "severity": "medium", "published": "2026-10-09T07:47:33Z" }, { "ghsa": "GHSA-rwfw-xvg3-3937", "severity": "medium", "published": "2026-10-09T07:47:04Z" }, { "ghsa": "GHSA-8c65-hq7q-r7jm", "severity": "high", "published": "2026-10-09T07:34:18Z" }, { "ghsa": "GHSA-rhcx-5729-88vg", "severity": "high", "published": "2026-10-09T06:39:02Z" }, { "ghsa": "GHSA-6cxc-2vcg-w5qc", "severity": "low", "published": "2026-10-06T20:45:08Z" }, { "ghsa": "GHSA-p92p-rxj5-7p2x", "cve": "CVE-2026-114050", "severity": "medium", "published": "2026-10-06T07:10:22Z" }, { "ghsa": "GHSA-rh6f-3x46-j33q", "severity": "medium", "published": "2026-10-06T07:08:41Z" }, { "ghsa": "GHSA-h3rc-6mm3-gc2m", "severity": "high", "published": "2026-10-06T07:06:53Z" }, { "ghsa": "GHSA-gx7p-2j49-hfq4", "severity": "high", "published": "2026-10-06T07:04:54Z" }, { "ghsa": "GHSA-823j-m4cj-hmjf", "cve": "CVE-2026-114052", "severity": "high", "published": "2026-10-06T06:59:51Z" }, { "ghsa": "GHSA-4xqp-c3mv-qff7", "severity": "medium", "published": "2026-10-06T06:58:15Z" }, { "ghsa": "GHSA-ph3r-5jfg-f84f", "cve": "CVE-2026-105753", "severity": "medium", "published": "2026-09-28T07:37:56Z" }, { "ghsa": "GHSA-m52c-39rh-f3gp", "severity": "medium", "published": "2026-09-28T07:35:57Z" }, { "ghsa": "GHSA-935w-9g4m-p28p", "cve": "CVE-2026-105752", "severity": "low", "published": "2026-09-28T07:34:45Z" }, { "ghsa": "GHSA-x6mc-67gf-chw4", "cve": "CVE-2026-105758", "severity": "medium", "published": "2026-09-23T10:25:42Z" }, { "ghsa": "GHSA-5fj9-pfhr-6j48", "cve": "CVE-2026-105759", "severity": "medium", "published": "2026-09-23T10:23:16Z" }, { "ghsa": "GHSA-58v5-2m8f-94pr", "cve": "CVE-2026-105760", "severity": "medium", "published": "2026-09-23T10:20:52Z" }, { "ghsa": "GHSA-ph72-cqr5-qpp7", "cve": "CVE-2026-105754", "severity": "medium", "published": "2026-09-23T10:17:44Z" }, { "ghsa": "GHSA-85xf-c7hm-whqw", "cve": "CVE-2026-105757", "severity": "medium", "published": "2026-09-23T10:16:15Z" }, { "ghsa": "GHSA-2phq-3phc-84px", "cve": "CVE-2026-105755", "severity": "medium", "published": "2026-09-23T10:15:01Z" }, { "ghsa": "GHSA-2823-qmq8-rwvj", "cve": "CVE-2026-105756", "severity": "medium", "published": "2026-09-23T10:12:17Z" }, { "ghsa": "GHSA-hhv2-872h-628q", "severity": "medium", "published": "2026-09-12T14:47:49Z" }, { "ghsa": "GHSA-v5gm-qgmv-gc6c", "severity": "medium", "published": "2026-09-12T14:45:55Z" }, { "ghsa": "GHSA-qff2-492f-9fm4", "severity": "medium", "published": "2026-09-12T14:43:57Z" }, { "ghsa": "GHSA-3mqx-f33v-vgp9", "severity": "medium", "published": "2026-09-12T08:56:01Z" }, { "ghsa": "GHSA-j682-9xp5-rrf3", "cve": "CVE-2026-100649", "severity": "low", "published": "2026-09-12T08:54:27Z" }, { "ghsa": "GHSA-p6g9-7v3x-m8mv", "severity": "medium", "published": "2026-09-12T08:52:51Z" }, { "ghsa": "GHSA-jcq2-4gch-5qhf", "cve": "CVE-2026-100648", "severity": "medium", "published": "2026-09-12T08:51:06Z" }, { "ghsa": "GHSA-wpww-v874-ph2p", "cve": "CVE-2026-100647", "severity": "medium", "published": "2026-09-12T08:49:34Z" }, { "ghsa": "GHSA-25q3-v2hm-8vpf", "cve": "CVE-2026-93592", "severity": "high", "published": "2026-09-03T18:08:31Z" }, { "ghsa": "GHSA-8pw2-6jv3-mj5j", "cve": "CVE-2026-69147", "severity": "medium", "published": "2026-08-28T18:09:24Z" }, { "ghsa": "GHSA-3c86-2m5g-59q7", "cve": "CVE-2026-90553", "severity": "high", "published": "2026-08-28T18:05:36Z" }, { "ghsa": "GHSA-936p-m5pv-vvjf", "cve": "CVE-2026-90554", "severity": "medium", "published": "2026-08-28T18:04:03Z" }, { "ghsa": "GHSA-99f2-hwrc-gvq8", "cve": "CVE-2026-90555", "severity": "medium", "published": "2026-08-28T18:03:19Z" }, { "ghsa": "GHSA-hcwq-8wjf-3gcr", "cve": "CVE-2026-57173", "severity": "medium", "published": "2026-08-23T07:21:14Z" }, { "ghsa": "GHSA-4hhp-h66f-j5j7", "cve": "CVE-2026-73560", "severity": "medium", "published": "2026-08-13T15:46:24Z" }, { "ghsa": "GHSA-cqm8-jxg6-fqfq", "cve": "CVE-2026-78684", "severity": "medium", "published": "2026-08-11T06:42:07Z" }, { "ghsa": "GHSA-7m6h-x95x-82q5", "cve": "CVE-2026-73558", "severity": "medium", "published": "2026-08-11T06:40:00Z" }, { "ghsa": "GHSA-pr7f-p5mw-fc87", "cve": "CVE-2026-73557", "severity": "medium", "published": "2026-07-27T09:21:25Z" }, { "ghsa": "GHSA-48jh-3gj7-fg8v", "cve": "CVE-2026-73556", "severity": "medium", "published": "2026-07-27T09:20:51Z" }, { "ghsa": "GHSA-hwrm-c4cx-rf4j", "cve": "CVE-2026-73555", "severity": "low", "published": "2026-07-27T09:19:03Z" }, { "ghsa": "GHSA-8737-qx52-hjff", "cve": "CVE-2026-71486", "severity": "medium", "published": "2026-07-27T09:18:41Z" }, { "ghsa": "GHSA-87x5-vmc3-756j", "cve": "CVE-2026-73559", "severity": "medium", "published": "2026-07-27T09:17:18Z" }, { "ghsa": "GHSA-v82g-2437-67m2", "cve": "CVE-2026-55646", "severity": "medium", "published": "2026-07-02T07:53:16Z" }, { "ghsa": "GHSA-rwxx-mrjm-wc2m", "cve": "CVE-2026-55574", "severity": "medium", "published": "2026-07-02T07:51:56Z" }, { "ghsa": "GHSA-8wr5-jm2h-8r4f", "cve": "CVE-2026-54234", "severity": "high", "published": "2026-07-02T07:50:33Z" }, { "ghsa": "GHSA-33cg-gxv8-3p8g", "cve": "CVE-2026-55514", "severity": "medium", "published": "2026-07-02T07:12:18Z" }, { "ghsa": "GHSA-q8gq-377p-jq3r", "cve": "CVE-2026-41523", "severity": "high", "published": "2026-06-14T08:08:23Z" }, { "ghsa": "GHSA-6pr9-rp53-2pmc", "cve": "CVE-2026-54233", "severity": "medium", "published": "2026-06-11T12:57:00Z" }, { "ghsa": "GHSA-hgg8-fqqc-vfmw", "cve": "CVE-2026-54236", "severity": "medium", "published": "2026-06-11T12:41:26Z" }, { "ghsa": "GHSA-5jv2-g5wq-cmr4", "cve": "CVE-2026-53923", "severity": "medium", "published": "2026-06-11T12:39:47Z" }, { "ghsa": "GHSA-8jr5-v98p-w75m", "cve": "CVE-2026-12491", "severity": "medium", "published": "2026-06-11T12:37:26Z" }, { "ghsa": "GHSA-7h4p-rffg-7823", "cve": "CVE-2026-54235", "severity": "medium", "published": "2026-06-11T12:35:05Z" }, { "ghsa": "GHSA-3ww4-5jv9-j5gm", "cve": "CVE-2026-47155", "severity": "medium", "published": "2026-06-10T14:11:37Z" }, { "ghsa": "GHSA-jrf6-vqxq-pjv2", "cve": "CVE-2026-54232", "severity": "high", "published": "2026-06-09T15:00:23Z" }, { "ghsa": "GHSA-94f4-hr76-p5j6", "cve": "CVE-2026-48746", "severity": "critical", "published": "2026-06-02T16:12:56Z" }, { "ghsa": "GHSA-83vm-p52w-f9pw", "cve": "CVE-2026-44223", "severity": "medium", "published": "2026-04-28T20:03:19Z" }, { "ghsa": "GHSA-hpv8-x276-m59f", "cve": "CVE-2026-44222", "severity": "medium", "published": "2026-04-27T18:00:06Z" }, { "ghsa": "GHSA-pf3h-qjgv-vcpr", "cve": "CVE-2026-34753", "severity": "medium", "published": "2026-04-03T15:23:37Z" }, { "ghsa": "GHSA-pq5c-rjhq-qp7p", "cve": "CVE-2026-34755", "severity": "medium", "published": "2026-04-03T15:10:39Z" }, { "ghsa": "GHSA-3mwp-wvh9-7528", "cve": "CVE-2026-34756", "severity": "medium", "published": "2026-04-03T14:49:03Z" }, { "ghsa": "GHSA-6c4r-fmh3-7rh8", "cve": "CVE-2026-34760", "severity": "medium", "published": "2026-03-30T20:26:30Z" }, { "ghsa": "GHSA-7972-pg2x-xr59", "cve": "CVE-2026-27893", "severity": "high", "published": "2026-03-26T23:48:23Z" }, { "ghsa": "GHSA-v359-jj2v-j536", "cve": "CVE-2026-25960", "severity": "medium", "published": "2026-03-09T17:58:39Z" }, { "ghsa": "GHSA-4r2x-xpjr-7cvv", "cve": "CVE-2026-22778", "severity": "critical", "published": "2026-02-02T14:58:53Z" }, { "ghsa": "GHSA-qh4c-xf7m-gxfc", "cve": "CVE-2026-24779", "severity": "high", "published": "2026-01-27T15:10:43Z" }, { "ghsa": "GHSA-2pc9-4j83-qjmr", "cve": "CVE-2026-22807", "severity": "high", "published": "2026-01-21T15:50:41Z" }, { "ghsa": "GHSA-wv77-2vpf-vmmg", "cve": "CVE-2025-62372", "severity": "medium", "published": "2026-01-21T13:36:26Z" }, { "ghsa": "GHSA-grg2-63fw-f2qr", "cve": "CVE-2026-22773", "severity": "medium", "published": "2026-01-09T19:48:58Z" }, { "ghsa": "GHSA-mcmc-2m55-j8jj", "severity": "high", "published": "2026-01-08T17:02:04Z" }, { "ghsa": "GHSA-8fr4-5q9j-m8gm", "cve": "CVE-2025-66448", "severity": "high", "published": "2025-12-01T19:39:22Z" }, { "ghsa": "GHSA-69j4-grxj-j64p", "cve": "CVE-2025-62426", "severity": "medium", "published": "2025-11-20T19:11:08Z" }, { "ghsa": "GHSA-mrw7-hf4f-83pf", "cve": "CVE-2025-62164", "severity": "high", "published": "2025-11-20T19:03:26Z" }, { "ghsa": "GHSA-pmqf-x6x8-p7qw", "cve": "CVE-2025-62372", "severity": "medium", "published": "2025-11-20T18:58:11Z" }, { "ghsa": "GHSA-6fvq-23cw-5628", "cve": "CVE-2025-61620", "severity": "medium", "published": "2025-10-07T00:24:34Z" }, { "ghsa": "GHSA-3f6c-7fw2-ppm4", "cve": "CVE-2025-6242", "severity": "high", "published": "2025-10-07T00:20:45Z" }, { "ghsa": "GHSA-wr9h-g72x-mwhm", "cve": "CVE-2025-59425", "severity": "high", "published": "2025-10-07T00:18:47Z" }, { "ghsa": "GHSA-79j6-g2m3-jgfw", "cve": "CVE-2025-9141", "severity": "high", "published": "2025-08-20T23:25:39Z" } ] }, "updatedAt": "2026-11-07T16:01:37.179206185Z" } }, "edges": [ { "by": 47, "category": "maintenance", "leads": "vllm", "name": "Maintenance \u0026 community", "reasons": { "a": "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.", "b": "v0.33.0 is tagged 1 November 2026 (30). Eight stable releases in the 90 days from 6 August, v0.27.0 (10 August), v0.27.1, v0.28.0, v0.29.0, v0.30.0, v0.31.0, v0.32.0 (17 October) and v0.33.0, with release candidates between them, dated from the tags in a clone (20). Per the 9 October check, not re-read on 4 November (GitHub's pages and API refuse this session): 2,592 open issues, and 42 of 48 bug reports from the week of 22 September had a comment by 9 October (19 of 25). The Python library ships in the same package as the server, and a Rust proto crate is tagged separately (proto-v0.6.0 is the newest). The server has no client library of its own (10 of 15). Dependabot runs weekly for pip and GitHub Actions, with pre-commit and Buildkite checks on each commit (9 of 10). 30 + 20 + 19 + 10 + 9 = 88." }, "scores": { "a": 41, "b": 88 } }, { "by": 18, "category": "security", "leads": "vllm", "name": "Security \u0026 auth", "reasons": { "a": "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.", "b": "Read with the tool checklist. Optional static keys from `--api-key` or `VLLM_API_KEY`, compared in constant time and read only from the `Authorization` header. They are off by default, have no scopes, and are checked only under `/v1`, `/v2`, `/inference` and `/cohere`, so `/invocations` runs the same inference without a key. With `--host` unset the server binds every interface, and gRPC has no authentication (10 of 30). Development routes, runtime LoRA loading, tool servers and endpoint plugins are off by default. `/pause`, `/abort_requests` and `/update_weights` answer without a key on generation servers, and there is no read-only mode (6 of 20). The security guide covers model-generated code in the demo code interpreter, allowed domains for media URLs, cache salting and the lack of tenant isolation (10 of 15). Access logs, `--enable-log-requests`, Prometheus `/metrics` and OpenTelemetry examples, with no per-key record (9 of 15). SECURITY.md with severity classes, a named vulnerability management team, private reporting through GitHub, CVEs and a prenotification group, and advisories published in public (61 GitHub advisories for vllm on OSV in the 12 months to 4 November 2026). No security.txt and no bounty found (15 of 20)." }, "scores": { "a": 32, "b": 50 } }, { "by": 15, "category": "schema", "leads": "privategpt", "name": "Schema \u0026 documentation", "reasons": { "a": "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.", "b": "The server is a FastAPI application with Pydantic request models, so a running instance serves its own OpenAPI document and Swagger page unless `--disable-fastapi-docs` is set, and the gRPC services have published proto files. No static OpenAPI file is published in the docs or the repository (15 of 25). docs.vllm.ai/llms.txt returns 404. vllm.ai/llms.txt lists site pages and blog posts, and the docs are Markdown files in the repository (5 of 10). The serving pages say which model types each route applies to, which OpenAI fields are ignored, and which routes must not be exposed (15 of 20). Typed request models, with structured outputs by JSON schema, choice, regex or grammar (12 of 15). Examples for most routes in the docs and the `examples` folder. The error shape (message, type, param, code) is defined in the source, and no error reference page was found (9 of 15). GitHub releases with full notes about every two weeks and vllm.ai/releases. The HTTP API has no version of its own beyond the `/v1` prefix (12 of 15)." }, "scores": { "a": 83, "b": 68 } }, { "by": 11, "category": "reliability", "leads": "privategpt", "name": "Reliability", "reasons": { "a": "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.", "b": "Read with the local-software lines, since vLLM runs on the owner's hardware with no hosted service. Installs from PyPI (`vllm`) and Docker images, with Linux and Python 3.11 to 3.14 stated in `pyproject.toml` at v0.33.0 (20). A public Buildkite pipeline (`.buildkite/test-pipeline.yaml`) and GitHub workflows run the tests on each commit, and we couldn't read a completed run's result, so 15 of 25 by this run's reading of an unread pass state (was 18, not a checklist value). Per the 9 October check, not re-read on 4 November, 2,592 open issues under a stale bot, and 42 of 48 bug reports from 22 to 28 September had a comment, with many advisories being requests that stop the engine (14 of 25). Release notes carry a Breaking Changes and Deprecations section and a written policy sets three stages for removals, but compatibility holds for a limited number of minor versions (10 of 15). Version 0.33.0, pre-1.0 (0). 20 + 15 + 14 + 10 + 0 = 59." }, "scores": { "a": 70, "b": 59 } }, { "by": 7, "category": "transparency", "leads": "vllm", "name": "Transparency \u0026 trust", "reasons": { "a": "Apache-2.0 (30). The OpenAPI description says no data leaves the execution environment, but the docs list cloud gateways as model providers and web search goes to outside services when enabled, and no privacy statement covers the software. Zylon's privacy policy covers its website (15 of 30). The 1.0 rewrite was marked as a breaking change in the changelog, and there is no deprecation policy (6 of 20). No telemetry to Zylon found in the source. OpenTelemetry tracing is off by default and its exporters write local files or to the owner's collector, documented on the observability page (16 of 20). 30 + 15 + 6 + 16 = 67.", "b": "The editorial half. Apache-2.0, all of it public (30). The usage statistics page lists what is collected, links the collecting code, keeps a local copy at `~/.config/vllm/usage_stats.json` and says a cleaned subset is published. No privacy policy, retention period or recipient list for stats.vllm.ai was found, and vllm.ai links no privacy policy (16 of 30). A written deprecation policy with three stages across minor releases, and breaking changes listed in each release's notes (17 of 20). Telemetry is disclosed with three opt-outs, `VLLM_NO_USAGE_STATS`, `DO_NOT_TRACK` and a file. It is on by default and reports every ten minutes. The fields in `usage_lib.py` at v0.33.0 are a random per-run UUID, hardware, platform, model architecture and five vLLM settings, which matches the page's anonymous claim (17 of 20)." }, "scores": { "a": 64, "b": 71 } } ], "facts": [ { "a": "HTTP API", "b": "HTTP API", "name": "Kind" }, { "a": "Zylon (PriBAI Technology Spain S.L.)", "b": "vLLM project (PyTorch Foundation)", "name": "Vendor" }, { "a": "no (local only)", "b": "no (local only)", "name": "Hosted endpoint" }, { "a": "HTTP", "b": "HTTP", "name": "Transports" }, { "a": "None", "b": "None", "name": "Auth" }, { "a": "Free", "b": "Free", "name": "Pricing" }, { "a": "no", "b": "no", "name": "x402" }, { "a": "Apache-2.0", "b": "Apache-2.0", "name": "Licence" }, { "a": "no", "b": "no", "name": "Read-only variant documented" }, { "a": "yes", "b": "no", "name": "llms.txt" }, { "a": "2026-06-18", "b": "2026-11-01", "name": "Last release" }, { "a": "no date given", "b": "no document linked", "name": "Terms last updated" }, { "a": "no document linked", "b": "no document linked", "name": "Privacy policy last updated" }, { "a": "not found in the text", "b": "not read yet", "name": "Customer content may train models" }, { "a": "not found in the text", "b": "not read yet", "name": "Terms restrict automated access" }, { "a": "not found in the text", "b": "not read yet", "name": "Terms restrict benchmarking" }, { "a": "not found in the text", "b": "not read yet", "name": "Terms or service can change without notice" }, { "a": "not found in the text", "b": "not read yet", "name": "Arbitration or class-action waiver" }, { "a": "58k stars", "b": "93k stars", "name": "Popularity" } ], "faq": [ { "answer": "PrivateGPT scores 53.2 (D) on agent readiness against vLLM's 48.4 (D), and leads in 2 of 7 scored categories. vLLM leads on security \u0026 auth, maintenance \u0026 community and transparency \u0026 trust.", "question": "Which is better for AI agents, PrivateGPT or vLLM?" }, { "answer": "Neither needs a key.", "question": "Do PrivateGPT and vLLM need an API key?" }, { "answer": "No hosted endpoint is listed for PrivateGPT. No hosted endpoint is listed for vLLM.", "question": "Can an agent call PrivateGPT and vLLM without installing anything?" }, { "answer": "Yes. PrivateGPT is open source (Apache-2.0). vLLM is open source (Apache-2.0).", "question": "Are PrivateGPT and vLLM open source?" } ], "goodFor": [ { "aheadOn": [ "Reliability, 70 against 59", "Schema \u0026 documentation, 83 against 68" ], "also": null, "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" }, { "aheadOn": [ "Security \u0026 auth, 50 against 32", "Maintenance \u0026 community, 88 against 41", "Transparency \u0026 trust, 71 against 64" ], "also": [ "Free to start without a card" ], "goodFor": "An owner with a GPU server who wants many concurrent requests against one open-weight model behind OpenAI or Anthropic compatible routes.", "slug": "vllm", "watchFor": "`--api-key` guards only the `/v1`, `/v2`, `/inference` and `/cohere` prefixes. `/invocations`, `/pooling`, `/classify`, `/score`, `/rerank`, `/pause` and `/update_weights` answer without it" } ], "history": { "privategpt": null, "vllm": [ { "causes": [ "security", "correction" ], "date": "2026-11-04", "delta": -9.6, "from": 58, "fromGrade": "C", "to": 48.4, "toGrade": "D" }, { "causes": [ "evidence" ], "date": "2026-10-28", "delta": 0.2, "from": 57.8, "fromGrade": "C", "to": 58, "toGrade": "C" }, { "causes": [ "evidence" ], "date": "2026-10-28", "delta": 0, "from": 57.8, "fromGrade": "C", "to": 57.8, "toGrade": "C" } ] }, "job": { "capability": "inference.local", "name": "Local inference" }, "others": [ { "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/anythingllm-vs-vllm.json", "title": "AnythingLLM vs vLLM", "url": "https://www.anchorterminal.com/compare/anythingllm-vs-vllm" }, { "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/berth-vs-vllm.json", "title": "Berth vs vLLM", "url": "https://www.anchorterminal.com/compare/berth-vs-vllm" }, { "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/bitrun-vs-vllm.json", "title": "BitRun vs vLLM", "url": "https://www.anchorterminal.com/compare/bitrun-vs-vllm" }, { "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/docker-model-runner-vs-vllm.json", "title": "Docker Model Runner vs vLLM", "url": "https://www.anchorterminal.com/compare/docker-model-runner-vs-vllm" }, { "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/foundry-local-vs-vllm.json", "title": "Foundry Local vs vLLM", "url": "https://www.anchorterminal.com/compare/foundry-local-vs-vllm" }, { "json": "https://www.anchorterminal.com/compare/ghost-core-vs-privategpt.json", "title": "Core vs PrivateGPT", "url": "https://www.anchorterminal.com/compare/ghost-core-vs-privategpt" }, { "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/gpt4all-vs-vllm.json", "title": "GPT4All vs vLLM", "url": "https://www.anchorterminal.com/compare/gpt4all-vs-vllm" }, { "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/hyperqwen-vs-vllm.json", "title": "HyperQwen vs vLLM", "url": "https://www.anchorterminal.com/compare/hyperqwen-vs-vllm" }, { "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/jan-vs-vllm.json", "title": "Jan vs vLLM", "url": "https://www.anchorterminal.com/compare/jan-vs-vllm" }, { "json": "https://www.anchorterminal.com/compare/khoj-vs-vllm.json", "title": "Khoj vs vLLM", "url": "https://www.anchorterminal.com/compare/khoj-vs-vllm" }, { "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/koboldcpp-vs-vllm.json", "title": "KoboldCpp vs vLLM", "url": "https://www.anchorterminal.com/compare/koboldcpp-vs-vllm" }, { "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/lemonade-vs-vllm.json", "title": "Lemonade vs vLLM", "url": "https://www.anchorterminal.com/compare/lemonade-vs-vllm" }, { "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/llama-cpp-vs-vllm.json", "title": "llama.cpp vs vLLM", "url": "https://www.anchorterminal.com/compare/llama-cpp-vs-vllm" }, { "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/lm-studio-vs-vllm.json", "title": "LM Studio vs vLLM", "url": "https://www.anchorterminal.com/compare/lm-studio-vs-vllm" }, { "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/localai-vs-vllm.json", "title": "LocalAI vs vLLM", "url": "https://www.anchorterminal.com/compare/localai-vs-vllm" }, { "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/mlx-lm-vs-vllm.json", "title": "MLX LM vs vLLM", "url": "https://www.anchorterminal.com/compare/mlx-lm-vs-vllm" }, { "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/ollama-vs-vllm.json", "title": "Ollama vs vLLM", "url": "https://www.anchorterminal.com/compare/ollama-vs-vllm" }, { "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/open-webui-vs-vllm.json", "title": "Open WebUI vs vLLM", "url": "https://www.anchorterminal.com/compare/open-webui-vs-vllm" }, { "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/screenpipe-vs-vllm.json", "title": "screenpipe vs vLLM", "url": "https://www.anchorterminal.com/compare/screenpipe-vs-vllm" }, { "json": "https://www.anchorterminal.com/compare/text-generation-webui-vs-vllm.json", "title": "TextGen vs vLLM", "url": "https://www.anchorterminal.com/compare/text-generation-webui-vs-vllm" }, { "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/underdog-vs-vllm.json", "title": "Underdog vs vLLM", "url": "https://www.anchorterminal.com/compare/underdog-vs-vllm" } ], "panel": null, "scores": [ { "by": 11, "edge": "privategpt", "key": "reliability", "name": "Reliability", "privategpt": 70, "vllm": 59, "weight": 16 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "by": 15, "edge": "privategpt", "key": "schema", "name": "Schema \u0026 documentation", "privategpt": 83, "vllm": 68, "weight": 13 }, { "by": 0, "edge": "", "key": "ergonomics", "name": "Agent ergonomics", "privategpt": 64, "vllm": 64, "weight": 13 }, { "by": 18, "edge": "vllm", "key": "security", "name": "Security \u0026 auth", "privategpt": 32, "vllm": 50, "weight": 14 }, { "by": 0, "edge": "", "key": "payments", "name": "Payments \u0026 pricing", "privategpt": 60, "vllm": 60, "weight": 10 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "by": 47, "edge": "vllm", "key": "maintenance", "name": "Maintenance \u0026 community", "privategpt": 41, "vllm": 88, "weight": 7 }, { "by": 7, "edge": "vllm", "key": "transparency", "name": "Transparency \u0026 trust", "privategpt": 64, "vllm": 71, "weight": 7 } ], "summary": "PrivateGPT scores 53.2 (D) on agent readiness against vLLM's 48.4 (D), and leads in 2 of 7 scored categories. vLLM leads on security \u0026 auth, maintenance \u0026 community and transparency \u0026 trust. Both do local inference.", "tasks": null, "tutorials": [], "verdicts": { "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.", "vllm": "Apache-2.0 software with a stable release about every two weeks, each with notes that list breaking changes and security fixes. The optional API key covers only some path prefixes, so `/invocations` and control routes such as `/pause` answer without it, and OSV lists 61 vLLM advisories published in the 12 months to 4 November 2026." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/privategpt-vs-vllm", "json": "https://www.anchorterminal.com/compare/privategpt-vs-vllm.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/privategpt-vs-vllm.md", "mcp": "https://www.anchorterminal.com/mcp", "slim": "https://www.anchorterminal.com/compare/privategpt-vs-vllm.min.md" }, "markdown": "PrivateGPT scores 53.2 (D) on agent readiness against vLLM's 48.4 (D), and leads in 2 of 7 scored categories. vLLM leads on security \u0026 auth, maintenance \u0026 community and transparency \u0026 trust. Both do local inference.\n\n- PrivateGPT: grade D, 53.2/100, rank #954 of 1486. Markdown https://www.anchorterminal.com/tools/privategpt.md · JSON https://www.anchorterminal.com/api/v1/tools/privategpt.json\n- vLLM: grade D, 48.4/100, rank #1117 of 1486. Markdown https://www.anchorterminal.com/tools/vllm.md · JSON https://www.anchorterminal.com/api/v1/tools/vllm.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### 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 59\n- Schema \u0026 documentation, 83 against 68\n\nWatch for: Authentication is off by default, the server binds 0.0.0.0 and CORS allows every origin\n\n### vLLM (D)\n\nGood for: An owner with a GPU server who wants many concurrent requests against one open-weight model behind OpenAI or Anthropic compatible routes.\n\nAhead on:\n- Security \u0026 auth, 50 against 32\n- Maintenance \u0026 community, 88 against 41\n- Transparency \u0026 trust, 71 against 64\n\nAlso in its favour:\n- Free to start without a card\n\nWatch for: `--api-key` guards only the `/v1`, `/v2`, `/inference` and `/cohere` prefixes. `/invocations`, `/pooling`, `/classify`, `/score`, `/rerank`, `/pause` and `/update_weights` answer without it\n\n\n## Why the edge\n\n### Maintenance \u0026 community: vLLM +47\n\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- vLLM (88): v0.33.0 is tagged 1 November 2026 (30). Eight stable releases in the 90 days from 6 August, v0.27.0 (10 August), v0.27.1, v0.28.0, v0.29.0, v0.30.0, v0.31.0, v0.32.0 (17 October) and v0.33.0, with release candidates between them, dated from the tags in a clone (20). Per the 9 October check, not re-read on 4 November (GitHub's pages and API refuse this session): 2,592 open issues, and 42 of 48 bug reports from the week of 22 September had a comment by 9 October (19 of 25). The Python library ships in the same package as the server, and a Rust proto crate is tagged separately (proto-v0.6.0 is the newest). The server has no client library of its own (10 of 15). Dependabot runs weekly for pip and GitHub Actions, with pre-commit and Buildkite checks on each commit (9 of 10). 30 + 20 + 19 + 10 + 9 = 88.\n\n### Security \u0026 auth: vLLM +18\n\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- vLLM (50): Read with the tool checklist. Optional static keys from `--api-key` or `VLLM_API_KEY`, compared in constant time and read only from the `Authorization` header. They are off by default, have no scopes, and are checked only under `/v1`, `/v2`, `/inference` and `/cohere`, so `/invocations` runs the same inference without a key. With `--host` unset the server binds every interface, and gRPC has no authentication (10 of 30). Development routes, runtime LoRA loading, tool servers and endpoint plugins are off by default. `/pause`, `/abort_requests` and `/update_weights` answer without a key on generation servers, and there is no read-only mode (6 of 20). The security guide covers model-generated code in the demo code interpreter, allowed domains for media URLs, cache salting and the lack of tenant isolation (10 of 15). Access logs, `--enable-log-requests`, Prometheus `/metrics` and OpenTelemetry examples, with no per-key record (9 of 15). SECURITY.md with severity classes, a named vulnerability management team, private reporting through GitHub, CVEs and a prenotification group, and advisories published in public (61 GitHub advisories for vllm on OSV in the 12 months to 4 November 2026). No security.txt and no bounty found (15 of 20).\n\n### Schema \u0026 documentation: PrivateGPT +15\n\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- vLLM (68): The server is a FastAPI application with Pydantic request models, so a running instance serves its own OpenAPI document and Swagger page unless `--disable-fastapi-docs` is set, and the gRPC services have published proto files. No static OpenAPI file is published in the docs or the repository (15 of 25). docs.vllm.ai/llms.txt returns 404. vllm.ai/llms.txt lists site pages and blog posts, and the docs are Markdown files in the repository (5 of 10). The serving pages say which model types each route applies to, which OpenAI fields are ignored, and which routes must not be exposed (15 of 20). Typed request models, with structured outputs by JSON schema, choice, regex or grammar (12 of 15). Examples for most routes in the docs and the `examples` folder. The error shape (message, type, param, code) is defined in the source, and no error reference page was found (9 of 15). GitHub releases with full notes about every two weeks and vllm.ai/releases. The HTTP API has no version of its own beyond the `/v1` prefix (12 of 15).\n\n### Reliability: PrivateGPT +11\n\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- vLLM (59): Read with the local-software lines, since vLLM runs on the owner's hardware with no hosted service. Installs from PyPI (`vllm`) and Docker images, with Linux and Python 3.11 to 3.14 stated in `pyproject.toml` at v0.33.0 (20). A public Buildkite pipeline (`.buildkite/test-pipeline.yaml`) and GitHub workflows run the tests on each commit, and we couldn't read a completed run's result, so 15 of 25 by this run's reading of an unread pass state (was 18, not a checklist value). Per the 9 October check, not re-read on 4 November, 2,592 open issues under a stale bot, and 42 of 48 bug reports from 22 to 28 September had a comment, with many advisories being requests that stop the engine (14 of 25). Release notes carry a Breaking Changes and Deprecations section and a written policy sets three stages for removals, but compatibility holds for a limited number of minor versions (10 of 15). Version 0.33.0, pre-1.0 (0). 20 + 15 + 14 + 10 + 0 = 59.\n\n### Transparency \u0026 trust: vLLM +7\n\n- PrivateGPT (64): Apache-2.0 (30). The OpenAPI description says no data leaves the execution environment, but the docs list cloud gateways as model providers and web search goes to outside services when enabled, and no privacy statement covers the software. Zylon's privacy policy covers its website (15 of 30). The 1.0 rewrite was marked as a breaking change in the changelog, and there is no deprecation policy (6 of 20). No telemetry to Zylon found in the source. OpenTelemetry tracing is off by default and its exporters write local files or to the owner's collector, documented on the observability page (16 of 20). 30 + 15 + 6 + 16 = 67.\n- vLLM (71): The editorial half. Apache-2.0, all of it public (30). The usage statistics page lists what is collected, links the collecting code, keeps a local copy at `~/.config/vllm/usage_stats.json` and says a cleaned subset is published. No privacy policy, retention period or recipient list for stats.vllm.ai was found, and vllm.ai links no privacy policy (16 of 30). A written deprecation policy with three stages across minor releases, and breaking changes listed in each release's notes (17 of 20). Telemetry is disclosed with three opt-outs, `VLLM_NO_USAGE_STATS`, `DO_NOT_TRACK` and a file. It is on by default and reports every ten minutes. The fields in `usage_lib.py` at v0.33.0 are a random per-run UUID, hardware, platform, model architecture and five vLLM settings, which matches the page's anonymous claim (17 of 20).\n\n## Score by category\n\n| Category | Weight | PrivateGPT | vLLM | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 70 | 59 | PrivateGPT +11 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 83 | 68 | PrivateGPT +15 |\n| Agent ergonomics | 13% (16.2 this run) | 64 | 64 | even |\n| Security \u0026 auth | 14% (17.5 this run) | 32 | 50 | vLLM +18 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 60 | 60 | even |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 41 | 88 | vLLM +47 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 64 | 71 | vLLM +7 |\n| Negative events | ≤15 | -7 | -15 | |\n| **Total** | | **53.2 · D** | **48.4 · D** | |\n\n## Facts side by side\n\n| Fact | PrivateGPT | vLLM |\n| --- | --- | --- |\n| Kind | HTTP API | HTTP API |\n| Vendor | Zylon (PriBAI Technology Spain S.L.) | vLLM project (PyTorch Foundation) |\n| Hosted endpoint | no (local only) | no (local only) |\n| Transports | HTTP | HTTP |\n| Auth | None | None |\n| Pricing | Free | Free |\n| x402 | no | no |\n| Licence | Apache-2.0 | Apache-2.0 |\n| Read-only variant documented | no | no |\n| llms.txt | yes | no |\n| Last release | 2026-06-18 | 2026-11-01 |\n| Terms last updated | no date given | no document linked |\n| Privacy policy last updated | no document linked | no document linked |\n| Customer content may train models | not found in the text | not read yet |\n| Terms restrict automated access | not found in the text | not read yet |\n| Terms restrict benchmarking | not found in the text | not read yet |\n| Terms or service can change without notice | not found in the text | not read yet |\n| Arbitration or class-action waiver | not found in the text | not read yet |\n| Popularity | 58k stars | 93k stars |\n\n## How the scores have moved\n\n### PrivateGPT\n\nNo score change since it was listed.\n\n### vLLM\n\n- -9.6 on 4 November 2026 (C to D): security, correction\n- +0.2 on 28 October 2026: new evidence\n- no change on 28 October 2026: new evidence\n\n## Verdicts\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**vLLM.** Apache-2.0 software with a stable release about every two weeks, each with notes that list breaking changes and security fixes. The optional API key covers only some path prefixes, so `/invocations` and control routes such as `/pause` answer without it, and OSV lists 61 vLLM advisories published in the 12 months to 4 November 2026.\n\n## Before you call either\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### vLLM\n\n1. Put a reverse proxy that allowlists routes in front of the server. `--api-key` leaves `/invocations` and the control routes open\n2. Pass `--host 127.0.0.1` for single-machine use. With no `--host` the server listens on every interface\n3. Set `VLLM_NO_USAGE_STATS=1` or `DO_NOT_TRACK=1` before starting if nothing should be sent to stats.vllm.ai\n4. Start with `--enable-auto-tool-choice` and the `--tool-call-parser` for the model before sending tools. Tool calling is off without them\n5. Send `max_tokens` on every request, and read the breaking changes section of the release notes before upgrading a minor version\n\n## Questions\n\n### Which is better for AI agents, PrivateGPT or vLLM?\n\nPrivateGPT scores 53.2 (D) on agent readiness against vLLM's 48.4 (D), and leads in 2 of 7 scored categories. vLLM leads on security \u0026 auth, maintenance \u0026 community and transparency \u0026 trust.\n\n### Do PrivateGPT and vLLM need an API key?\n\nNeither needs a key.\n\n### Can an agent call PrivateGPT and vLLM without installing anything?\n\nNo hosted endpoint is listed for PrivateGPT. No hosted endpoint is listed for vLLM.\n\n### Are PrivateGPT and vLLM open source?\n\nYes. PrivateGPT is open source (Apache-2.0). vLLM is open source (Apache-2.0).\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/privategpt-vs-vllm.json, and with the fewest tokens: https://www.anchorterminal.com/compare/privategpt-vs-vllm.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"privategpt\", \"b\": \"vllm\"}`. From a terminal: `anchor compare privategpt vllm`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/privategpt.json and https://www.anchorterminal.com/api/v1/tools/vllm.json\n\n## Other comparisons with PrivateGPT or vLLM\n\n- [AnythingLLM vs PrivateGPT](https://www.anchorterminal.com/compare/anythingllm-vs-privategpt.md)\n- [AnythingLLM vs vLLM](https://www.anchorterminal.com/compare/anythingllm-vs-vllm.md)\n- [Berth vs PrivateGPT](https://www.anchorterminal.com/compare/berth-vs-privategpt.md)\n- [Berth vs vLLM](https://www.anchorterminal.com/compare/berth-vs-vllm.md)\n- [BitRun vs PrivateGPT](https://www.anchorterminal.com/compare/bitrun-vs-privategpt.md)\n- [BitRun vs vLLM](https://www.anchorterminal.com/compare/bitrun-vs-vllm.md)\n- [Docker Model Runner vs PrivateGPT](https://www.anchorterminal.com/compare/docker-model-runner-vs-privategpt.md)\n- [Docker Model Runner vs vLLM](https://www.anchorterminal.com/compare/docker-model-runner-vs-vllm.md)\n- [Foundry Local vs PrivateGPT](https://www.anchorterminal.com/compare/foundry-local-vs-privategpt.md)\n- [Foundry Local vs vLLM](https://www.anchorterminal.com/compare/foundry-local-vs-vllm.md)\n- [Core vs PrivateGPT](https://www.anchorterminal.com/compare/ghost-core-vs-privategpt.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- [GPT4All vs vLLM](https://www.anchorterminal.com/compare/gpt4all-vs-vllm.md)\n- [HyperQwen vs PrivateGPT](https://www.anchorterminal.com/compare/hyperqwen-vs-privategpt.md)\n- [HyperQwen vs vLLM](https://www.anchorterminal.com/compare/hyperqwen-vs-vllm.md)\n- [Jan vs PrivateGPT](https://www.anchorterminal.com/compare/jan-vs-privategpt.md)\n- [Jan vs vLLM](https://www.anchorterminal.com/compare/jan-vs-vllm.md)\n- [Khoj vs vLLM](https://www.anchorterminal.com/compare/khoj-vs-vllm.md)\n- [KoboldCpp vs PrivateGPT](https://www.anchorterminal.com/compare/koboldcpp-vs-privategpt.md)\n- [KoboldCpp vs vLLM](https://www.anchorterminal.com/compare/koboldcpp-vs-vllm.md)\n- [Lemonade vs PrivateGPT](https://www.anchorterminal.com/compare/lemonade-vs-privategpt.md)\n- [Lemonade vs vLLM](https://www.anchorterminal.com/compare/lemonade-vs-vllm.md)\n- [llama.cpp vs PrivateGPT](https://www.anchorterminal.com/compare/llama-cpp-vs-privategpt.md)\n- [llama.cpp vs vLLM](https://www.anchorterminal.com/compare/llama-cpp-vs-vllm.md)\n- [LM Studio vs PrivateGPT](https://www.anchorterminal.com/compare/lm-studio-vs-privategpt.md)\n- [LM Studio vs vLLM](https://www.anchorterminal.com/compare/lm-studio-vs-vllm.md)\n- [LocalAI vs PrivateGPT](https://www.anchorterminal.com/compare/localai-vs-privategpt.md)\n- [LocalAI vs vLLM](https://www.anchorterminal.com/compare/localai-vs-vllm.md)\n- [MLX LM vs PrivateGPT](https://www.anchorterminal.com/compare/mlx-lm-vs-privategpt.md)\n- [MLX LM vs vLLM](https://www.anchorterminal.com/compare/mlx-lm-vs-vllm.md)\n- [Ollama vs PrivateGPT](https://www.anchorterminal.com/compare/ollama-vs-privategpt.md)\n- [Ollama vs vLLM](https://www.anchorterminal.com/compare/ollama-vs-vllm.md)\n- [Open WebUI vs PrivateGPT](https://www.anchorterminal.com/compare/open-webui-vs-privategpt.md)\n- [Open WebUI vs vLLM](https://www.anchorterminal.com/compare/open-webui-vs-vllm.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- [screenpipe vs vLLM](https://www.anchorterminal.com/compare/screenpipe-vs-vllm.md)\n- [TextGen vs vLLM](https://www.anchorterminal.com/compare/text-generation-webui-vs-vllm.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- [Underdog vs vLLM](https://www.anchorterminal.com/compare/underdog-vs-vllm.md)\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": "PrivateGPT vs vLLM", "url": "" } ], "description": "PrivateGPT scores 53.2 (D) to vLLM's 48.4 (D) for local inference. Prices, MCP, x402, uptime and agent notes side by side.", "facts": [ "PrivateGPT D 53.2", "vLLM D 48.4", "scores" ], "h1": "PrivateGPT vs vLLM", "image": "https://www.anchorterminal.com/assets/og/default.png", "path": "/compare/privategpt-vs-vllm", "published": "2026-10-01", "section": "tools", "title": "PrivateGPT vs vLLM for AI agents in 2026: scores and prices", "toc": null, "updated": "2026-11-07", "url": "https://www.anchorterminal.com/compare/privategpt-vs-vllm" }, "tokens": { "markdown": 5250, "slim": 3080 }, "version": 1 }