{ "schemaVersion": 1, "origin": "https://onequill.dev", "exportGenerated": "2026-10-07T14:23:01.311Z", "sourceReviewSnapshot": "2026-10-07", "purpose": "Read and search public OneQuill content directly over HTTP; no computer-use interface is required.", "affiliation": "OneQuill develops OneVir.", "documents": [ { "title": "About OneQuill · Software that does exactly what it says", "description": "OneQuill is an independent software company in Essen, Germany. We turn complex technology into tools people can run, understand and trust.", "url": "https://onequill.dev/about", "markdown": "https://onequill.dev/text/about.md", "type": "Website page", "published": null, "modified": null, "sourceReviewed": null, "topic": null, "tags": [] }, { "title": "Contact OneQuill · Enquiries, sales, support and company", "description": "Contact OneQuill for general enquiries, product walkthroughs, commercial licences, partnerships, OneVir support, and company matters.", "url": "https://onequill.dev/contact", "markdown": "https://onequill.dev/text/contact.md", "type": "Website page", "published": null, "modified": null, "sourceReviewed": null, "topic": null, "tags": [] }, { "title": "OneQuill · Powerful technology, under your control", "description": "OneQuill builds software for enterprise AI. OneVir is the governed execution layer for private and hybrid AI, with one policy, security, cost and audit boundary.", "url": "https://onequill.dev/", "markdown": "https://onequill.dev/text/home.md", "type": "Website page", "published": null, "modified": null, "sourceReviewed": null, "topic": null, "tags": [] }, { "title": "Impressum · OneQuill", "description": "Operator and company information for OneQuill, Essen, Germany.", "url": "https://onequill.dev/legal", "markdown": "https://onequill.dev/text/legal.md", "type": "Website page", "published": null, "modified": null, "sourceReviewed": null, "topic": null, "tags": [] }, { "title": "OneVir licensing · Free for non-commercial and non-production use · OneQuill", "description": "OneVir is licensed by OneQuill under the Business Source License 1.1. Non-commercial use is free, including in production. Development, testing and evaluation are free for everyone. Only commercial production use requires a paid licence.", "url": "https://onequill.dev/licensing", "markdown": "https://onequill.dev/text/licensing.md", "type": "Website page", "published": null, "modified": null, "sourceReviewed": null, "topic": null, "tags": [] }, { "title": "Privacy · OneQuill", "description": "How the OneQuill website handles your data: no cookies, no analytics, no third-party requests. Privacy contact: contact@onequill.dev.", "url": "https://onequill.dev/privacy", "markdown": "https://onequill.dev/text/privacy.md", "type": "Website page", "published": null, "modified": null, "sourceReviewed": null, "topic": null, "tags": [] }, { "title": "AI gateway and inference education centre · OneQuill", "description": "Six practical guides, 55 provider profiles and 16 source-linked cases for AI gateway and inference evaluation.", "url": "https://onequill.dev/resources", "markdown": "https://onequill.dev/text/resources.md", "type": "Collection", "published": null, "modified": null, "sourceReviewed": null, "topic": null, "tags": [] }, { "title": "OneVir support · OneQuill", "description": "Get help with OneVir: contact support@onequill.dev or help@onequill.dev, and learn what to include for a fast answer.", "url": "https://onequill.dev/support", "markdown": "https://onequill.dev/text/support.md", "type": "Website page", "published": null, "modified": null, "sourceReviewed": null, "topic": null, "tags": [] }, { "title": "agentgateway: a patched release can still need a policy setting · OneQuill", "description": "Patch status is a release-and-configuration claim. Record the environment setting, accepted resources and cross-namespace authorisation evidence beside the version number.", "url": "https://onequill.dev/resources/agentgateway-namespace-isolation", "markdown": "https://onequill.dev/resources/agentgateway-namespace-isolation.md", "type": "Case study", "published": "2026-10-07", "modified": "2026-10-07", "sourceReviewed": "2026-10-07", "topic": "security", "tags": [ "security", "agentgateway", "security-advisory" ] }, { "title": "AI gateway budgets and scaling: measure the whole request · OneQuill", "description": "Evaluate token accounting, concurrent spend reservations, retries, regional counters and inference capacity with practical evidence requests.", "url": "https://onequill.dev/resources/ai-gateway-budgets-and-scaling", "markdown": "https://onequill.dev/resources/ai-gateway-budgets-and-scaling.md", "type": "Guide", "published": "2026-10-07", "modified": "2026-10-07", "sourceReviewed": "2026-10-07", "topic": "budgets", "tags": [ "budgets", "AI gateway", "client education" ] }, { "title": "AI gateway privacy: follow data through every layer · OneQuill", "description": "Map prompts, logs, caches, providers and fallback before comparing data residency, retention and zero-data-retention claims.", "url": "https://onequill.dev/resources/ai-gateway-privacy", "markdown": "https://onequill.dev/resources/ai-gateway-privacy.md", "type": "Guide", "published": "2026-10-07", "modified": "2026-10-07", "sourceReviewed": "2026-10-07", "topic": "privacy", "tags": [ "privacy", "AI gateway", "client education" ] }, { "title": "AI gateway reliability: define failure before adding fallback · OneQuill", "description": "Understand buffering limits, stream interruption, circuit breakers, failover and recovery without losing data policy or request meaning.", "url": "https://onequill.dev/resources/ai-gateway-reliability", "markdown": "https://onequill.dev/resources/ai-gateway-reliability.md", "type": "Guide", "published": "2026-10-07", "modified": "2026-10-07", "sourceReviewed": "2026-10-07", "topic": "reliability", "tags": [ "reliability", "AI gateway", "client education" ] }, { "title": "AI gateway security: protect the boundaries that matter · OneQuill", "description": "Understand gateway authentication, administration, outbound requests and tool policy through source-linked cases and practical evaluation questions.", "url": "https://onequill.dev/resources/ai-gateway-security", "markdown": "https://onequill.dev/resources/ai-gateway-security.md", "type": "Guide", "published": "2026-10-07", "modified": "2026-10-07", "sourceReviewed": "2026-10-07", "topic": "security", "tags": [ "security", "AI gateway", "client education" ] }, { "title": "AI gateway supply chain: trust the artifact you actually run · OneQuill", "description": "Evaluate package provenance, pinned images, model assets, release fixes and incident response using carefully scoped vendor evidence.", "url": "https://onequill.dev/resources/ai-gateway-supply-chain", "markdown": "https://onequill.dev/resources/ai-gateway-supply-chain.md", "type": "Guide", "published": "2026-10-07", "modified": "2026-10-07", "sourceReviewed": "2026-10-07", "topic": "supply-chain", "tags": [ "supply-chain", "AI gateway", "client education" ] }, { "title": "AI governance rules for gateways and local inference · OneQuill", "description": "A global AI governance reference covering the EU AI Act, GDPR, ISO 42001, NIST AI RMF, OSFI E-23 and OWASP, with official sources and gateway design implications.", "url": "https://onequill.dev/resources/ai-governance-rules", "markdown": "https://onequill.dev/resources/ai-governance-rules.md", "type": "Research reference", "published": "2026-10-07", "modified": "2026-10-07", "sourceReviewed": "2026-10-07", "topic": null, "tags": [ "EU AI Act", "GDPR", "ISO 27001", "ISO 42001", "ISO 23894", "NIST AI RMF", "OSFI E-23", "OWASP", "AI security", "LLM gateway", "local inference", "private AI", "California SB 53", "CCPA", "Colorado", "HIPAA", "COPPA", "DORA", "China", "South Korea", "India", "Brazil", "Canada", "Singapore", "Japan", "Australia", "Africa", "Middle East" ] }, { "title": "Bifrost: management APIs are an execution boundary · OneQuill", "description": "An API key that permits inference should not automatically permit plugin installation or process registration. Test administration with the credentials used by an ordinary client, including after a proxy or ingress is added.", "url": "https://onequill.dev/resources/bifrost-management-api-boundaries", "markdown": "https://onequill.dev/resources/bifrost-management-api-boundaries.md", "type": "Case study", "published": "2026-10-07", "modified": "2026-10-07", "sourceReviewed": "2026-10-07", "topic": "security", "tags": [ "security", "bifrost", "security-advisory" ] }, { "title": "Envoy AI Gateway: one message, two interpretations · OneQuill", "description": "Protocol compatibility includes security semantics. Evaluate ambiguous input handling and rejection behaviour as well as successful tool calls. A parser repair should be verified on the exact path that enforces tool policy.", "url": "https://onequill.dev/resources/envoy-ai-gateway-mcp-message-smuggling", "markdown": "https://onequill.dev/resources/envoy-ai-gateway-mcp-message-smuggling.md", "type": "Case study", "published": "2026-10-07", "modified": "2026-10-07", "sourceReviewed": "2026-10-07", "topic": "security", "tags": [ "security", "envoy-ai-gateway", "security-advisory" ] }, { "title": "Envoy AI Gateway: enforce limits before buffering · OneQuill", "description": "A small per-request limit is not a complete capacity model. Multiply buffering by admitted concurrency and account for protocol expansion, such as decoding, before choosing a memory budget.", "url": "https://onequill.dev/resources/envoy-ai-gateway-mcp-request-limits", "markdown": "https://onequill.dev/resources/envoy-ai-gateway-mcp-request-limits.md", "type": "Case study", "published": "2026-10-07", "modified": "2026-10-07", "sourceReviewed": "2026-10-07", "topic": "reliability", "tags": [ "reliability", "envoy-ai-gateway", "security-advisory" ] }, { "title": "GitLab AI Gateway: flow templates and sandbox assumptions · OneQuill", "description": "Ask what an author can cause a workflow runtime to execute, read and contact. A template language or sandbox needs a defined permission boundary and a plan for patching that runtime.", "url": "https://onequill.dev/resources/gitlab-ai-gateway-template-sandbox", "markdown": "https://onequill.dev/resources/gitlab-ai-gateway-template-sandbox.md", "type": "Case study", "published": "2026-10-07", "modified": "2026-10-07", "sourceReviewed": "2026-10-07", "topic": "security", "tags": [ "security", "gitlab", "security-advisory" ] }, { "title": "Kong: a streaming usage fix deserves billing regression tests · OneQuill", "description": "Use release notes as evaluation evidence without promoting every correction to a CVE. A billing test should include complete streams, disconnected streams, missing final events and retries.", "url": "https://onequill.dev/resources/kong-gemini-streaming-token-accounting", "markdown": "https://onequill.dev/resources/kong-gemini-streaming-token-accounting.md", "type": "Case study", "published": "2026-10-07", "modified": "2026-10-07", "sourceReviewed": "2026-10-07", "topic": "budgets", "tags": [ "budgets", "kong", "release-fix" ] }, { "title": "LiteLLM: package provenance and incident response · OneQuill", "description": "An upgrade removes a malicious artifact from the future path; it does not establish that previously accessible secrets are safe. Preserve artifact evidence, isolate affected environments and rotate credentials according to the incident investigation.", "url": "https://onequill.dev/resources/litellm-march-2026-package-incident", "markdown": "https://onequill.dev/resources/litellm-march-2026-package-incident.md", "type": "Case study", "published": "2026-10-07", "modified": "2026-10-07", "sourceReviewed": "2026-10-07", "topic": "supply-chain", "tags": [ "supply-chain", "litellm", "incident-report" ] }, { "title": "Running LLM inference in production: security, isolation and capacity · OneQuill", "description": "Evaluate vLLM, SGLang, Ollama and LM Studio across API exposure, model loading, execution location, isolation and workload-specific capacity.", "url": "https://onequill.dev/resources/llm-inference-security-and-operations", "markdown": "https://onequill.dev/resources/llm-inference-security-and-operations.md", "type": "Guide", "published": "2026-10-07", "modified": "2026-10-07", "sourceReviewed": "2026-10-07", "topic": "inference", "tags": [ "inference", "AI gateway", "client education", "vLLM", "SGLang", "Ollama", "LM Studio", "llmster", "inference security" ] }, { "title": "LM Studio: choose authentication, execution location and model lifecycle · OneQuill", "description": "Verify effective server settings, token permissions and execution location. Measure first-load and repeated-request behaviour under the model lifecycle settings your application actually uses.", "url": "https://onequill.dev/resources/lm-studio-network-authentication-and-lifecycle", "markdown": "https://onequill.dev/resources/lm-studio-network-authentication-and-lifecycle.md", "type": "Case study", "published": "2026-10-07", "modified": "2026-10-07", "sourceReviewed": "2026-10-07", "topic": "inference", "tags": [ "LM Studio", "LLM inference", "documented-behaviour" ] }, { "title": "New API: quota arithmetic is part of the trust boundary · OneQuill", "description": "Evaluate the ledger as a state transition: reserve, dispatch, settle or release. Concurrency, very large usage values, cancellation and repeated settlement should not create spendable credit.", "url": "https://onequill.dev/resources/new-api-quota-billing-overflow", "markdown": "https://onequill.dev/resources/new-api-quota-billing-overflow.md", "type": "Case study", "published": "2026-10-07", "modified": "2026-10-07", "sourceReviewed": "2026-10-07", "topic": "budgets", "tags": [ "budgets", "new-api", "security-advisory" ] }, { "title": "Ollama: model import is a separate memory and access boundary · OneQuill", "description": "Patch the affected path with artifact-level evidence, restrict model-management operations and keep the service on approved networks. A gateway access policy supports admission but cannot repair an inference runtime’s model loader.", "url": "https://onequill.dev/resources/ollama-model-import-memory-boundary", "markdown": "https://onequill.dev/resources/ollama-model-import-memory-boundary.md", "type": "Case study", "published": "2026-10-07", "modified": "2026-10-07", "sourceReviewed": "2026-10-07", "topic": "inference", "tags": [ "Ollama", "LLM inference", "security-advisory", "GHSA-x8qc-fggm-mpqg", "CVE-2026-7482" ] }, { "title": "OneVir control evidence and deployment responsibilities · OneQuill", "description": "Review six OneVir control topics, the evidence behind each finding, and what to verify for your release and deployment.", "url": "https://onequill.dev/resources/onevir-control-evidence", "markdown": "https://onequill.dev/resources/onevir-control-evidence.md", "type": "Evidence record", "published": "2026-10-07", "modified": "2026-10-07", "sourceReviewed": "2026-10-07", "topic": null, "tags": [ "OneVir", "privacy", "security", "budgets", "inference", "control evidence" ] }, { "title": "Portkey: custom-host routing and private-network access · OneQuill", "description": "A provider name in a route is only the start of the decision. Check the actual host and network destination at dispatch time. A tenant should not gain the gateway's access to internal services by changing an endpoint header.", "url": "https://onequill.dev/resources/portkey-custom-host-ssrf", "markdown": "https://onequill.dev/resources/portkey-custom-host-ssrf.md", "type": "Case study", "published": "2026-10-07", "modified": "2026-10-07", "sourceReviewed": "2026-10-07", "topic": "security", "tags": [ "security", "portkey", "security-advisory" ] }, { "title": "Publishing the education centre: templates, evidence and regular updates · OneQuill", "description": "A reusable publication workflow for source-linked guides, provider profiles and case studies, with drafts, corrections, review dates and search discovery.", "url": "https://onequill.dev/resources/resource-publishing", "markdown": "https://onequill.dev/resources/resource-publishing.md", "type": "Publishing guide", "published": "2026-10-07", "modified": "2026-10-07", "sourceReviewed": "2026-10-07", "topic": null, "tags": [ "publishing", "research", "templates", "SEO", "AI search" ] }, { "title": "SGLang: isolate worker channels and model-management paths · OneQuill", "description": "Keep worker channels isolated, separate inference from administration, approve model and adapter sources, and verify the exact release and enabled endpoint inventory. Treat patch statements for different findings independently.", "url": "https://onequill.dev/resources/sglang-worker-and-management-trust", "markdown": "https://onequill.dev/resources/sglang-worker-and-management-trust.md", "type": "Case study", "published": "2026-10-07", "modified": "2026-10-07", "sourceReviewed": "2026-10-07", "topic": "inference", "tags": [ "SGLang", "LLM inference", "security-advisory", "VU#665416", "CVE-2026-3059", "CVE-2026-3060", "CVE-2026-3989", "VU#281278", "CVE-2026-15969", "CVE-2026-15971", "CVE-2026-15974", "CVE-2026-15976", "CVE-2026-15977", "CVE-2026-15978" ] }, { "title": "vLLM: a GGUF kernel defect is distinct from cache policy · OneQuill", "description": "Per-request cache salting addresses cache reuse and timing inference between trust groups. It does not repair this kernel defect or establish process and GPU memory isolation by itself.", "url": "https://onequill.dev/resources/vllm-gguf-gpu-memory-isolation", "markdown": "https://onequill.dev/resources/vllm-gguf-gpu-memory-isolation.md", "type": "Case study", "published": "2026-10-07", "modified": "2026-10-07", "sourceReviewed": "2026-10-07", "topic": "inference", "tags": [ "inference", "vllm", "security-advisory" ] }, { "title": "vLLM: isolate KV-transfer and distributed communication · OneQuill", "description": "Map public API, model-management and cluster networks independently. Keep worker communication on trusted isolated networks and verify bind addresses, firewall rules and the backend actually in use.", "url": "https://onequill.dev/resources/vllm-kv-transfer-network-isolation", "markdown": "https://onequill.dev/resources/vllm-kv-transfer-network-isolation.md", "type": "Case study", "published": "2026-10-07", "modified": "2026-10-07", "sourceReviewed": "2026-10-07", "topic": "inference", "tags": [ "inference", "vllm", "security-advisory" ] }, { "title": "vLLM: model configuration and Python optimisation · OneQuill", "description": "Keep runtime optimisation and trust validation separate. vLLM's own performance or compilation levels are not the same setting as Python's -O flag.", "url": "https://onequill.dev/resources/vllm-model-loading-python-optimisation", "markdown": "https://onequill.dev/resources/vllm-model-loading-python-optimisation.md", "type": "Case study", "published": "2026-10-07", "modified": "2026-10-07", "sourceReviewed": "2026-10-07", "topic": "inference", "tags": [ "inference", "vllm", "security-advisory" ] }, { "title": "vLLM: input features need separate validation and capacity limits · OneQuill", "description": "Maintain an input-feature inventory. Limit decoded dimensions, frame counts, aggregate input size and concurrent work; disable unsupported input types rather than rely on the text-only request limit.", "url": "https://onequill.dev/resources/vllm-multimodal-input-validation", "markdown": "https://onequill.dev/resources/vllm-multimodal-input-validation.md", "type": "Case study", "published": "2026-10-07", "modified": "2026-10-07", "sourceReviewed": "2026-10-07", "topic": "inference", "tags": [ "inference", "vllm", "security-advisory" ] }, { "title": "AI gateway provider directory: products, scope and evaluation questions · OneQuill", "description": "Search 55 gateway, routing and inference offerings, including vLLM, SGLang, Ollama and LM Studio. Official sources and scoped evaluation questions.", "url": "https://onequill.dev/resources/ai-gateway-providers", "markdown": "https://onequill.dev/text/resources-ai-gateway-providers.md", "type": "Collection", "published": null, "modified": null, "sourceReviewed": null, "topic": null, "tags": [] }, { "title": "AI gateway and inference case studies: conditions and remediation · OneQuill", "description": "16 selected gateway and inference cases with deployment scope, response evidence, version differences and practical questions.", "url": "https://onequill.dev/resources/ai-gateway-case-studies", "markdown": "https://onequill.dev/text/resources-ai-gateway-case-studies.md", "type": "Collection", "published": null, "modified": null, "sourceReviewed": null, "topic": null, "tags": [] } ], "research": "https://onequill.dev/assets/downloads/ai-gateway-research.json", "downloads": { "worksheetPDF": "https://onequill.dev/assets/downloads/ai-gateway-evaluation-worksheet.pdf", "worksheetMarkdown": "https://onequill.dev/assets/downloads/ai-gateway-evaluation-worksheet.md" }, "feeds": { "rss": "https://onequill.dev/resources/feed.xml", "sitemap": "https://onequill.dev/sitemap.xml", "fullText": "https://onequill.dev/llms-full.txt" }, "relatedSites": [ { "url": "https://onevir.onequill.dev/", "index": "https://onevir.onequill.dev/llms.txt", "scope": "Product website, separate deployment" } ] }