onyx-dot-app

Stars and mentions

Last 30 days, Oct 4 – Nov 2

GitHub stars579
mentions13
014284256Oct 4Oct 18Nov 2
UTC days · repositories onyx-dot-app owns2 repositories

Package downloads

Cumulative recorded downloads · since 2026-04-08

crates.io—
PyPI2M
0506.9K1M1.5M2MOct 4Oct 18Nov 2
Oct 28crates.io: 0/1 packages observed · PyPI: 1/2 packages observed

Across 3 known packages in repositories onyx-dot-app owns. Cumulative totals include recorded downloads before the selected range. Missing observations leave gaps; totals may be incomplete. PyPI excludes known mirrors.

Top repositories

onyx-dot-app’s repositories ranked by new stars, as on trending.

Loading

Contributes to

Repositories outside onyx-dot-app’s account where onyx-dot-app opened or reviewed pull requests in the past 365 days.

Who noticed onyx-dot-app

Everyone who starred or forked onyx-dot-app’s repositories since the archive began in 2011.

Notable accounts

Ordered by the stars their own repositories have received.

Biggest fans

Accounts that starred the most of these repositories.

Breakout weeks

Each repository’s best week of new stars, with the release published around it.

Mentions

13posts
Nov 30 posts
  1. YouTube · · YouTube description · TechyMers · onyx-dot-app/onyx

    Don't build from scratch: 10 GitHub repos to use instead #coding #programming #developer Claude use karte ho? Ye 10 GitHub repos tumhare kaam aa sakte hain! 🤯 Ek short mein 10 useful repos: reverse engineering, coding, design, writing, research, scraping aur diagrams. 🔗 REPO LINKS 01 REA: morluto/rea 02 Ponytail: DietrichGebert/ponytail 03 Hallmark: Nutlope/hallmark 04 Humanizer: blader/humanizer 05 Onyx: onyx-dot-app/onyx 06 Impeccable: pbakaus/impeccable 07 UI/UX Pro Max: nextlevelbuilder/ui-ux-pro-max-skill 08 Last 30 Days: mvanhorn/last30days-skill 09 Scrapling: D4Vinci/Scrapling 10 Diagram Design: cathrynlavery/diagram-design ⚠️ Note: Ye alag-alag type ke tools hain (skills, framework, platform). Sabka install alag hota hai, isliye har repo ka README zaroor padho. REA sirf legal aur authorized use ke liye hai. 💬 Comment karo "REPOS" aur batao kaunsa repo sabse pehle try karoge! 👍 Like, Save aur Share karo apne tech friend ke saath. 🔔 TechyMers ko follow/subscribe karo more useful tech tips ke liye. #shorts #claude #github #aitools #TechyMers #claudeai #opensource #coding #techtips #hinglish #reality #ponytail #hallmark #ai agents #productivity #webscraping #uidesign

    26 likes · 14 comments · 569 views
  2. YouTube · · YouTube description · Wolf | AI Tools & Projects · onyx-dot-app/onyx

    Six routes to a team knowledge base | 6 open-source choices Knowledge bases need more than chatbots. Six options, with different use cases and adoption checks. RAGFlow, AnythingLLM, Haystack, MaxKB, WeKnora, Onyx. Explore the original cards: channel profile → AI Open Source Radar → Collections. Choose the collection for this task and inspect the project cards. useaistation.com Sources checked 23 Oct 2026. This is a project-selection guide, not hands-on testing or a live ranking. These are different choices, not a verified integrated stack. Software licenses, model weights, hardware and external service costs must be checked separately. Community/core and enterprise features may differ. Developer disclosure: we build AI Open Source Radar, not the featured projects. Narration: Microsoft free Aria neural voice. Project and License sources (observed branch references, subject to change): RAGFlow: infiniflow/ragflow License: raw.githubusercontent.com AnythingLLM: Mintplex-Labs/anything-llm License: raw.githubusercontent.com Haystack: deepset-ai/haystack License: raw.githubusercontent.com MaxKB: 1Panel-dev/MaxKB License: raw.githubusercontent.com WeKnora: Tencent/WeKnora License: raw.githubusercontent.com Onyx: onyx-dot-app/onyx License: raw.githubusercontent.com #OpenSource #AITools #RAG

    16 views
  3. Open Source AI Platform - AI Chat with advanced features that works with every LLM onyx-dot-app/onyx

    24 views
  4. YouTube · · YouTube description · The Solo Engineer · onyx-dot-app/onyx

    Enterprise AI Done Right: A Deep Dive into Onyx What is Onyx, and how can it help developers build enterprise AI applications? In this video, we explore Onyx, an open-source enterprise AI platform (32.9k GitHub stars), and break down its architecture, RAG pipeline, hybrid search, AI agents, MCP integration, deployment options, security considerations, and licensing — every claim verified against the repo and docs, with the real product UI on screen. In this technical walkthrough, you'll learn: - What Onyx is and how it differs from an LLM or vector database - How enterprise RAG works - How connectors, indexing, retrieval, and generation fit together - RAG vs. MCP: understanding the difference - How to evaluate enterprise search and custom AI agents - Security, privacy, deployment, and cost considerations - Onyx vs. building a custom RAG application CHAPTERS 0:00 Knowledge, everywhere 0:21 One assistant, with sources 0:38 Meet Onyx 1:06 What exactly is Onyx? 1:41 What Onyx is NOT 2:03 Layer 1: connectors 2:26 Layer 2: indexing 2:38 Layer 3: hybrid retrieval 3:01 Layer 4: AI orchestration 3:21 The honest note 3:41 RAG vs MCP 4:10 MCP in practice 4:52 Demo: ask with receipts 5:21 Demo: custom agents + MCP 5:45 The real evaluation 6:04 Who should use Onyx? 6:38 Deployment modes matter 6:55 Security: permissions 7:29 Privacy: data flows 7:47 Cost + licensing 8:10 Onyx vs building your own 8:43 How to decide 9:03 Final verdict 9:40 Your turn THE VERIFIED NUMBERS (snapshot Oct 23, 2026) - 32,895 GitHub stars · 4,618 forks · 195+ contributors · since Apr 2023 - 50+ applications supported via connectors (their count; we counted 56 official) - License: MIT (Expat) for the core; the ee/ directories carry the proprietary Onyx Enterprise License — so "open source" with an enterprise split, not plain MIT - Deployment: Docker Compose / Kubernetes, self-hosted or cloud; lightweight chat-only mode is not the same as a full indexing deployment HONEST NOTES: an indexed document is not a retrieved document, and a retrieved passage is not a correct answer — retrieval quality, source quality, permissions, and model behavior all matter. Self-hosting does not automatically keep data local if an external model provider is configured. Open source is not zero cost. Repository: onyx-dot-app/onyx Documentation: docs.onyx.app MCP: modelcontextprotocol.io Screenshots shown are Onyx's own product UI from their docs, used for review. Independent explainer — not affiliated with or sponsored by Onyx/DanswerAI. Subscribe to The Solo Engineer — Where Tech Meets Reality — for practical AI engineering, open-source projects, and production-level technical breakdowns. Would you build your own RAG pipeline from scratch, or start with a platform like Onyx? Tell me below. #OnyxAI #RAG #AIEngineering #OpenSource #MCP #EnterpriseAI #ArtificialIntelligence [de-DE] Onyx AI erklärt: RAG, Agents & MCP Was ist Onyx und wie kann es Entwicklern beim Erstellen von KI-Anwendungen für Unternehmen helfen? In diesem Video stellen wir Onyx vor, eine Open-Source-KI-Plattform für Unternehmen (32.900 GitHub-Sterne). Wir erläutern die Architektur, die RAG-Pipeline, die hybride Suche, KI-Agenten, die MCP-Integration, Bereitstellungsoptionen, Sicherheitsaspekte und die Lizenzierung – alle Angaben wurden anhand des Repositorys und der Dokumentation überprüft, und die Benutzeroberfläche des Produkts wird gezeigt. In diesem technischen Leitfaden erfahren Sie: - Was Onyx ist und wie es sich von einer LLM- oder Vektordatenbank unterscheidet - Wie Enterprise-RAG funktioniert - Wie Konnektoren, Indizierung, Abfrage und Generierung zusammenwirken - RAG vs. MCP: Die Unterschiede verstehen - Wie Sie Enterprise-Suche und benutzerdefinierte KI-Agenten evaluieren - Sicherheits-, Datenschutz-, Bereitstellungs- und Kostenaspekte - Onyx vs. Entwicklung einer benutzerdefinierten RAG-Anwendung KAPITEL 0:00 Wissen überall 0:21 Ein Assistent mit Quellen 0:38 Onyx kennenlernen 1:06 Was genau ist Onyx? 1:41 Was Onyx NICHT ist 2:03 Schicht 1: Konnektoren 2:26 Schicht 2: Indexierung 2:38 Schicht 3: Hybrider Retrieval 3:01 Schicht 4: KI-Orchestrierung 3:21 Ehrliche Anmerkungen 3:41 RAG vs. MCP 4:10 MCP in der Praxis 4:52 Demo: Fragen mit Belegen 5:21 Demo: Benutzerdefinierte Agenten + MCP 5:45 Die eigentliche Bewertung 6:04 Für wen ist Onyx geeignet? 6:38 Bereitstellungsmodi sind wichtig 6:55 Sicherheit: Berechtigungen 7:29 Datenschutz: Datenflüsse 7:47 Kosten + Lizenzierung 8:10 Onyx vs. Eigenentwicklung 8:43 Wie Sie sich entscheiden 9:03 Endergebnis 9:40 Ihre Meinung DIE VERIFIZIERTEN ZAHLEN (Stand: 23. Oktober 2026) - 32.895 GitHub-Sterne · 4.618 Forks · über 195 Mitwirkende · seit April 2023 - Über 50 Anwendungen werden über Konnektoren unterstützt (Angabe des Anbieters; wir haben 56 offizielle Anwendungen gezählt) - Lizenz: MIT (Expat) für den Kern; die ee/-Verzeichnisse enthalten die proprietäre Onyx Enterprise License – also „Open Source“ mit Enterprise-Abschnitt, nicht die reine MIT-Lizenz - Bereitstellung: Docker Compose / Kubernetes, selbst gehostet oder in der Cloud Der einfache Chat-Modus ist nicht mit einer vollständigen Indexierungsbereitstellung gleichzusetzen. Wichtiger Hinweis: Ein indexiertes Dokument ist kein abgerufenes Dokument, und ein abgerufener Textabschnitt ist keine korrekte Antwort – die Qualität der Suchergebnisse, die Qualität der Quelle, die Berechtigungen und das Modellverhalten spielen eine wichtige Rolle. Selbsthosting speichert Daten nicht automatisch lokal, wenn ein externer Modellanbieter konfiguriert ist. Open Source ist nicht kostenlos. Repository: onyx-dot-app/onyx Dokumentation: docs.onyx.app MCP: modelcontextprotocol.io Die gezeigten Screenshots stammen aus der Onyx-Produkt-UI (Dokumentation) und dienen der Veranschaulichung. Unabhängiger Beitrag – keine Verbindung zu Onyx/DanswerAI und nicht von diesen gesponsert. Abonnieren Sie „The Solo Engineer – Wo Technologie auf Realität trifft“ für praktische KI-Entwicklung, Open-Source-Projekte und technische Analysen auf Produktionsniveau. Würden Sie Ihre eigene RAG-Pipeline von Grund auf neu entwickeln oder mit einer Plattform wie Onyx beginnen? Schreibt es mir unten in die Kommentare. #OnyxAI #RAG #KI-Entwicklung #OpenSource #MCP #Unternehmens-KI #KünstlicheIntelligenz [es-US] Onyx AI explicado: RAG, agentes y MCP ¿Qué es Onyx y cómo puede ayudar a los desarrolladores a crear aplicaciones de IA empresariales? En este video, exploramos Onyx, una plataforma de IA empresarial de código abierto (32.900 estrellas en GitHub), y analizamos su arquitectura, el pipeline RAG, la búsqueda híbrida, los agentes de IA, la integración con MCP, las opciones de implementación, las consideraciones de seguridad y las licencias. Verificamos cada afirmación con el repositorio y la documentación, y mostramos la interfaz de usuario real del producto en pantalla. En este tutorial técnico, aprenderá: - Qué es Onyx y en qué se diferencia de una base de datos LLM o vectorial - Cómo funciona RAG empresarial - Cómo se integran los conectores, la indexación, la recuperación y la generación - RAG vs. MCP: la diferencia - Cómo evaluar la búsqueda empresarial y los agentes de IA personalizados - Consideraciones sobre seguridad, privacidad, implementación y costos - Onyx vs. la creación de una aplicación RAG personalizada CAPÍTULOS 0:00 Conocimiento en todas partes 0:21 Un asistente con recursos 0:38 Conozca Onyx 1:06 ¿Qué es exactamente Onyx? 1:41 Lo que Onyx NO es 2:03 Capa 1: conectores 2:26 Capa 2: indexación 2:38 Capa 3: recuperación híbrida 3:01 Capa 4: orquestación de IA 3:21 La verdad 3:41 RAG vs. MCP 4:10 MCP en la práctica 4:52 Demostración: preguntar con recibos 5:21 Demostración: agentes personalizados + MCP 5:45 La evaluación real 6:04 ¿Quién debería usar Onyx? 6:38 Importancia de los modos de implementación 6:55 Seguridad: permisos 7:29 Privacidad: flujos de datos 7:47 Costo + licencias 8:10 Onyx vs. crear tu propia solución 8:43 Cómo decidir 9:03 Veredicto final 9:40 Tu turno CIFRAS VERIFICADAS (instantánea del 23 de octubre de 2026) - 32.895 estrellas en GitHub · 4.618 bifurcaciones · Más de 195 colaboradores · desde abril de 2023 - Más de 50 aplicaciones compatibles mediante conectores (según su recuento; nosotros contamos 56 oficiales) - Licencia: MIT (Expat) para el núcleo; los directorios ee/ contienen la licencia propietaria Onyx Enterprise License, por lo que es de código abierto con una división empresarial, no una licencia MIT simple. - Implementación: Docker Compose / Kubernetes, autoalojado o en la nube; El modo ligero de chat no es lo mismo que una implementación de indexación completa. NOTAS IMPORTANTES: Un documento indexado no es un documento recuperado, y un fragmento recuperado no es una respuesta correcta. La calidad de la recuperación, la calidad de la fuente, los permisos y el comportamiento del modelo son factores cruciales. El autoalojamiento no mantiene automáticamente los datos localmente si se configura un proveedor de modelos externo. El software de código abierto no es gratuito. Repositorio: onyx-dot-app/onyx Documentación: docs.onyx.app MCP: modelcontextprotocol.io Las capturas de pantalla mostradas corresponden a la interfaz de usuario del producto Onyx, extraída de su documentación, y se utilizan con fines de revisión. Explicación independiente: no afiliada ni patrocinada por Onyx/DanswerAI. Suscríbete a The Solo Engineer — Donde la tecnología se encuentra con la realidad — para obtener información práctica sobre ingeniería de IA, proyectos de código abierto y análisis técnicos a nivel de producción. ¿Desarrollarías tu propio pipeline RAG desde cero o empezarías con una plataforma como Onyx? Cuéntame abajo. #OnyxAI #RAG #IngenieríaDeIA #CódigoAbierto #MCP #IAEmpresarial #InteligenciaArtificial [fr-FR] Onyx AI expliqué : RAG, agents et MCP Qu'est-ce qu'Onyx et comment peut-il aider les développeurs à créer des applications d'IA d'entreprise ? Dans cette vidéo, nous explorons Onyx, une plateforme d'IA d'entreprise open source (32 900 étoiles sur GitHub), et analysons son architecture, son pipeline RAG, sa recherche hybride, ses agents d'IA, son intégration MCP, ses options de déploiement, ses considérations de sécurité et sa licence. Chaque affirmation est vérifiée à partir du dépôt et de la documentation, avec l'interface utilisateur réelle du produit affichée à l'écran. Dans cette présentation technique, vous découvrirez : - Ce qu'est Onyx et en quoi il diffère d'une base de données LLM ou vectorielle - Le fonctionnement de la recherche en ligne (RAG) en entreprise - L'articulation des connecteurs, de l'indexation, de la récupération et de la génération - RAG vs. MCP : comprendre la différence - Comment évaluer la recherche d'entreprise et les agents d'IA personnalisés - Les aspects liés à la sécurité, la confidentialité, le déploiement et les coûts - Onyx vs. le développement d'une application RAG personnalisée CHAPITRES 0:00 Le savoir, partout 0:21 Un assistant, avec des sources 0:38 Présentation d'Onyx 1:06 Qu'est-ce qu'Onyx exactement ? 1:41 Ce qu'Onyx n'est PAS 2:03 Couche 1 : connecteurs 2:26 Couche 2 : indexation 2:38 Couche 3 : recherche hybride 3:01 Couche 4 : orchestration de l'IA 3:21 Note honnête 3:41 RAG vs MCP 4:10 MCP en pratique 4:52 Démo : requête avec reçus 5:21 Démo : agents personnalisés + MCP 5:45 L'évaluation réelle 6:04 À qui s'adresse Onyx ? 6:38 L'importance des modes de déploiement 6:55 Sécurité : permissions 7:29 Confidentialité : flux de données 7:47 Coût et licences 8:10 Onyx ou développement maison ? 8:43 Comment choisir ? 9:03 Verdict final 9:40 À vous de jouer ! LES CHIFFRES VÉRIFIÉS (instantané du 23 octobre 2026) - 32 895 étoiles sur GitHub · 4 618 forks · Plus de 195 contributeurs · depuis avril 2023 - Plus de 50 applications prises en charge via des connecteurs (leur décompte ; nous en avons compté 56 officielles) - Licence : MIT (Expat) pour le noyau ; les répertoires ee/ sont sous licence propriétaire Onyx Enterprise — il s'agit donc d'un logiciel « open source » avec une version entreprise, et non d'une licence MIT classique. - Déploiement : Docker Compose / Kubernetes, auto-hébergé ou cloud. Le mode conversation léger est différent d'un déploiement d'indexation complet. Remarque importante : un document indexé n'est pas un document récupéré, et un passage récupéré ne constitue pas une réponse correcte. La qualité de la récupération, la qualité de la source, les permissions et le comportement du modèle sont autant d'éléments essentiels. L'auto-hébergement ne garantit pas la conservation locale des données si un fournisseur de modèle externe est configuré. L'open source a un coût. Dépôt : onyx-dot-app/onyx Documentation : docs.onyx.app MCP : modelcontextprotocol.io Les captures d'écran présentées proviennent de l'interface utilisateur d'Onyx et sont issues de sa documentation. Explication indépendante — sans lien avec Onyx/DanswerAI, ni sponsorisée par eux. Abonnez-vous à The Solo Engineer — Là où la technologie rencontre la réalité — pour des conseils pratiques en ingénierie de l'IA, des projets open source et des analyses techniques de production. Préférez-vous créer votre propre pipeline RAG de A à Z ou utiliser une plateforme comme Onyx ? Dites-le-moi ci-dessous. #OnyxAI #RAG #IngénierieIA #OpenSource #MCP #IAEntreprise #IntelligenceArtificielle [hi] Onyx AI की व्याख्या: RAG, एजेंट्स और MCP ओनिक्स क्या है, और यह डेवलपर्स को एंटरप्राइज एआई एप्लिकेशन बनाने में कैसे मदद कर सकता है? इस वीडियो में, हम ओनिक्स, एक ओपन-सोर्स एंटरप्राइज एआई प्लेटफॉर्म (32.9k GitHub स्टार्स) का पता लगाते हैं, और इसकी वास्तुकला, RAG पाइपलाइन, हाइब्रिड सर्च, एआई एजेंट, MCP एकीकरण, परिनियोजन विकल्प, सुरक्षा संबंधी विचार और लाइसेंसिंग का विश्लेषण करते हैं — प्रत्येक दावे को रिपॉजिटरी और दस्तावेज़ों के आधार पर सत्यापित किया गया है, और स्क्रीन पर वास्तविक उत्पाद UI दिखाया गया है। इस तकनीकी विवरण में, आप सीखेंगे: - ओनिक्स क्या है और यह LLM या वेक्टर डेटाबेस से कैसे भिन्न है - एंटरप्राइज RAG कैसे काम करता है - कनेक्टर, इंडेक्सिंग, रिट्रीवल और जेनरेशन एक साथ कैसे काम करते हैं - RAG बनाम MCP: अंतर को समझना - एंटरप्राइज सर्च और कस्टम एआई एजेंट का मूल्यांकन कैसे करें - सुरक्षा, गोपनीयता, परिनियोजन और लागत संबंधी विचार - ओनिक्स बनाम कस्टम RAG एप्लिकेशन बनाना अध्याय 0:00 ज्ञान, सर्वत्र 0:21 एक सहायक, स्रोतों के साथ 0:38 ओनिक्स से मिलें 1:06 ओनिक्स वास्तव में क्या है? 1:41 ओनिक्स क्या नहीं है 2:03 लेयर 1: कनेक्टर्स 2:26 लेयर 2: इंडेक्सिंग 2:38 लेयर 3: हाइब्रिड रिट्रीवल 3:01 लेयर 4: एआई ऑर्केस्ट्रेशन 3:21 ईमानदार टिप्पणी 3:41 RAG बनाम MCP 4:10 व्यवहार में MCP 4:52 डेमो: रसीदों के साथ पूछें 5:21 डेमो: कस्टम एजेंट + MCP 5:45 वास्तविक मूल्यांकन 6:04 ओनिक्स का उपयोग किसे करना चाहिए? 6:38 परिनियोजन मोड महत्वपूर्ण हैं 6:55 सुरक्षा: अनुमतियाँ 7:29 गोपनीयता: डेटा प्रवाह 7:47 लागत + लाइसेंसिंग 8:10 ओनिक्स बनाम अपना खुद का निर्माण 8:43 निर्णय कैसे लें 9:03 अंतिम निर्णय 9:40 आपकी बारी सत्यापित आंकड़े (23 अक्टूबर, 2026 का स्नैपशॉट) - 32,895 GitHub स्टार · 4,618 फोर्क · 195+ योगदानकर्ता · अप्रैल 2023 से - कनेक्टर्स के माध्यम से 50+ एप्लिकेशन समर्थित (उनकी संख्या; हमने 56 आधिकारिक एप्लिकेशन गिने) - लाइसेंस: कोर के लिए MIT (Expat); ee/ निर्देशिकाओं में मालिकाना ओनिक्स एंटरप्राइज लाइसेंस है — इसलिए यह "ओपन सोर्स" है, लेकिन इसमें एंटरप्राइज विभाजन है, न कि केवल MIT - परिनियोजन: Docker Compose / Kubernetes, स्व-होस्टेड या क्लाउड; हल्का-फुल्का चैट-ओनली मोड, पूर्ण इंडेक्सिंग डिप्लॉयमेंट के समान नहीं है। महत्वपूर्ण बातें: इंडेक्स किया गया दस्तावेज़, प्राप्त किया गया दस्तावेज़ नहीं होता, और प्राप्त किया गया अंश, सही उत्तर नहीं होता — पुनर्प्राप्ति की गुणवत्ता, स्रोत की गुणवत्ता, अनुमतियाँ और मॉडल का व्यवहार, सभी मायने रखते हैं। यदि कोई बाहरी मॉडल प्रदाता कॉन्फ़िगर किया गया है, तो सेल्फ-होस्टिंग स्वचालित रूप से डेटा को स्थानीय रूप से नहीं रखती है। ओपन सोर्स का मतलब मुफ्त नहीं है। रिपॉजिटरी: onyx-dot-app/onyx दस्तावेज़ीकरण: docs.onyx.app MCP: modelcontextprotocol.io दिखाए गए स्क्रीनशॉट, समीक्षा के लिए उपयोग किए गए Onyx के दस्तावेज़ों से लिए गए उनके उत्पाद UI के हैं। यह एक स्वतंत्र व्याख्याता है — Onyx/DanswerAI से संबद्ध या प्रायोजित नहीं है। व्यावहारिक AI इंजीनियरिंग, ओपन-सोर्स प्रोजेक्ट्स और प्रोडक्शन-स्तर के तकनीकी विश्लेषण के लिए The Solo Engineer को सब्सक्राइब करें — जहाँ तकनीक वास्तविकता से मिलती है। क्या आप अपना खुद का RAG पाइपलाइन शुरू से बनाएंगे, या Onyx जैसे प्लेटफॉर्म से शुरुआत करेंगे? नीचे कमेंट करके बताएं। #OnyxAI #RAG #AIEngineering #OpenSource #MCP #EnterpriseAI #ArtificialIntelligence [id] Penjelasan Onyx AI: RAG, Agen & MCP Apa itu Onyx, dan bagaimana Onyx dapat membantu pengembang membangun aplikasi AI perusahaan? Dalam video ini, kita akan menjelajahi Onyx, platform AI perusahaan sumber terbuka (32,9 ribu bintang GitHub), dan menguraikan arsitekturnya, pipeline RAG, pencarian hibrida, agen AI, integrasi MCP, opsi penyebaran, pertimbangan keamanan, dan lisensi — setiap klaim diverifikasi terhadap repositori dan dokumentasi, dengan UI produk sebenarnya di layar. Dalam panduan teknis ini, Anda akan mempelajari: - Apa itu Onyx dan bagaimana perbedaannya dengan LLM atau basis data vektor - Bagaimana cara kerja RAG perusahaan - Bagaimana konektor, pengindeksan, pengambilan, dan pembuatan saling terkait - RAG vs. MCP: memahami perbedaannya - Bagaimana mengevaluasi pencarian perusahaan dan agen AI kustom - Pertimbangan keamanan, privasi, penyebaran, dan biaya - Onyx vs. membangun aplikasi RAG kustom BAB 0:00 Pengetahuan, di mana-mana 0:21 Satu asisten, dengan sumber 0:38 Mengenal Onyx 1:06 Apa sebenarnya Onyx? 1:41 Apa yang BUKAN Onyx 2:03 Lapisan 1: konektor 2:26 Lapisan 2: pengindeksan 2:38 Lapisan 3: pengambilan hibrida 3:01 Lapisan 4: orkestrasi AI 3:21 Catatan jujur 3:41 RAG vs MCP 4:10 MCP dalam praktik 4:52 Demo: bertanya dengan tanda terima 5:21 Demo: agen kustom + MCP 5:45 Evaluasi sebenarnya 6:04 Siapa yang harus menggunakan Onyx? 6:38 Mode penyebaran itu penting 6:55 Keamanan: izin 7:29 Privasi: alur data 7:47 Biaya + lisensi 8:10 Onyx vs membangun sendiri 8:43 Cara memutuskan 9:03 Keputusan akhir 9:40 Giliran Anda ANGKA TERVERIFIKASI (cuplikan 23 Okt 2026) - 32.895 bintang GitHub · 4.618 fork · 195+ kontributor · sejak Apr 2023 - 50+ aplikasi didukung melalui konektor (jumlah mereka; kami menghitung 56 resmi) - Lisensi: MIT (Ekspatriat) untuk inti; direktori ee/ membawa Lisensi Perusahaan Onyx yang bersifat eksklusif — jadi "sumber terbuka" dengan pemisahan perusahaan, bukan MIT biasa - Penyebaran: Docker Compose / Kubernetes, dihosting sendiri atau di cloud; Mode obrolan ringan saja tidak sama dengan penerapan pengindeksan penuh. CATATAN JUJUR: dokumen yang diindeks bukanlah dokumen yang diambil, dan bagian yang diambil bukanlah jawaban yang benar — kualitas pengambilan, kualitas sumber, izin, dan perilaku model semuanya penting. Hosting mandiri tidak secara otomatis menyimpan data secara lokal jika penyedia model eksternal dikonfigurasi. Sumber terbuka bukanlah tanpa biaya. Repositori: onyx-dot-app/onyx Dokumentasi: docs.onyx.app MCP: modelcontextprotocol.io Tangkapan layar yang ditampilkan adalah UI produk Onyx sendiri dari dokumentasi mereka, digunakan untuk tinjauan. Penjelasan independen — tidak berafiliasi dengan atau disponsori oleh Onyx/DanswerAI. Berlangganan The Solo Engineer — Tempat Teknologi Bertemu Realitas — untuk rekayasa AI praktis, proyek sumber terbuka, dan uraian teknis tingkat produksi. Apakah Anda akan membangun pipeline RAG Anda sendiri dari awal, atau memulai dengan platform seperti Onyx? Beri tahu saya di bawah. #OnyxAI #RAG #AIEngineering #OpenSource #MCP #EnterpriseAI #ArtificialIntelligence [it] Onyx AI spiegato: RAG, Agent e MCP Cos'è Onyx e come può aiutare gli sviluppatori a creare applicazioni di intelligenza artificiale per aziende? In questo video, esploriamo Onyx, una piattaforma open-source di intelligenza artificiale per aziende (32.900 stelle su GitHub), e analizziamo la sua architettura, la pipeline RAG, la ricerca ibrida, gli agenti IA, l'integrazione con MCP, le opzioni di implementazione, le considerazioni sulla sicurezza e le licenze: ogni affermazione è verificata rispetto al repository e alla documentazione, con l'interfaccia utente del prodotto reale mostrata sullo schermo. In questa guida tecnica, imparerai: - Cos'è Onyx e in cosa si differenzia da un database LLM o vettoriale - Come funziona RAG in ambito aziendale - Come si integrano connettori, indicizzazione, recupero e generazione - RAG vs. MCP: comprendere la differenza - Come valutare la ricerca aziendale e gli agenti AI personalizzati - Considerazioni su sicurezza, privacy, implementazione e costi - Onyx vs. creazione di un'applicazione RAG personalizzata CAPITOLI 0:00 La conoscenza, ovunque 0:21 Un unico assistente, con le sue fonti 0:38 Alla scoperta di Onyx 1:06 Cos'è esattamente Onyx? 1:41 Cosa NON è Onyx 2:03 Livello 1: connettori 2:26 Livello 2: indicizzazione 2:38 Livello 3: recupero ibrido 3:01 Livello 4: orchestrazione AI 3:21 La verità 3:41 RAG vs MCP 4:10 MCP in pratica 4:52 Demo: richiesta con ricevute 5:21 Demo: agenti personalizzati + MCP 5:45 La vera valutazione 6:04 Chi dovrebbe usare Onyx? 6:38 Le modalità di implementazione sono importanti 6:55 Sicurezza: permessi 7:29 Privacy: flussi di dati 7:47 Costo + licenze 8:10 Onyx vs. sviluppo interno 8:43 Come decidere 9:03 Verdetto finale 9:40 Ora tocca a te I NUMERI VERIFICATI (istantanea del 23 ottobre 2026) - 32.895 stelle su GitHub · 4.618 fork · oltre 195 collaboratori · da aprile 2023 - Oltre 50 applicazioni supportate tramite connettori (il loro conteggio; ne abbiamo contate 56 ufficiali) - Licenza: MIT (Expat) per il core; le directory ee/ contengono la licenza proprietaria Onyx Enterprise, quindi "open source" con una suddivisione enterprise, non semplice MIT - Implementazione: Docker Compose / Kubernetes, self-hosted o cloud; La modalità di sola chat leggera non è la stessa cosa di un'implementazione completa di indicizzazione. NOTE IMPORTANTI: un documento indicizzato non è un documento recuperato e un passaggio recuperato non è una risposta corretta: la qualità del recupero, la qualità della fonte, i permessi e il comportamento del modello sono tutti fattori importanti. L'hosting autonomo non mantiene automaticamente i dati in locale se è configurato un provider di modelli esterno. L'open source non è a costo zero. Repository: onyx-dot-app/onyx Documentazione: docs.onyx.app MCP: modelcontextprotocol.io Gli screenshot mostrati sono tratti dall'interfaccia utente del prodotto Onyx, presente nella loro documentazione, e utilizzati a scopo di analisi. Questo articolo è indipendente e non è affiliato o sponsorizzato da Onyx/DanswerAI. Iscriviti a The Solo Engineer — Dove la tecnologia incontra la realtà — per approfondimenti pratici sull'ingegneria dell'IA, progetti open source e analisi tecniche a livello di produzione. Costruiresti la tua pipeline RAG da zero o partiresti da una piattaforma come Onyx? Fammi sapere nei commenti qui sotto. #OnyxAI #RAG #AIEngineering #OpenSource #MCP #EnterpriseAI #ArtificialIntelligence [pt-BR] Onyx AI explicado: RAG, Agentes e MCP O que é o Onyx e como ele pode ajudar desenvolvedores a criar aplicativos de IA corporativos? Neste vídeo, exploramos o Onyx, uma plataforma de IA corporativa de código aberto (32,9 mil estrelas no GitHub), e detalhamos sua arquitetura, pipeline RAG, busca híbrida, agentes de IA, integração com MCP, opções de implantação, considerações de segurança e licenciamento — todas as afirmações verificadas no repositório e na documentação, com a interface do usuário real do produto na tela. Neste passo a passo técnico, você aprenderá: - O que é o Onyx e como ele difere de um banco de dados LLM ou vetorial - Como o RAG corporativo funciona - Como conectores, indexação, recuperação e geração se encaixam - RAG vs. MCP: entendendo a diferença - Como avaliar a busca corporativa e agentes de IA personalizados - Considerações sobre segurança, privacidade, implantação e custo - Onyx vs. criação de um aplicativo RAG personalizado CAPÍTULOS 0:00 Conhecimento, em todos os lugares 0:21 Um assistente, com fontes 0:38 Conheça o Onyx 1:06 O que exatamente é o Onyx? 1:41 O que o Onyx NÃO é 2:03 Camada 1: conectores 2:26 Camada 2: indexação 2:38 Camada 3: recuperação híbrida 3:01 Camada 4: orquestração de IA 3:21 A verdade nua e crua 3:41 RAG vs MCP 4:10 MCP na prática 4:52 Demonstração: pergunte com recibos 5:21 Demonstração: agentes personalizados + MCP 5:45 A avaliação real 6:04 Quem deve usar o Onyx? 6:38 Modos de implantação importam 6:55 Segurança: permissões 7:29 Privacidade: fluxos de dados 7:47 Custo + licenciamento 8:10 Onyx vs. construir sua própria solução 8:43 Como decidir 9:03 Veredito final 9:40 Sua vez OS NÚMEROS VERIFICADOS (instantâneo de 23 de outubro de 2026) - 32.895 estrelas no GitHub · 4.618 forks · mais de 195 colaboradores · desde abril de 2023 - Mais de 50 aplicativos suportados por meio de conectores (contagem deles; contamos 56 oficialmente) - Licença: MIT (Expat) para o núcleo; os diretórios ee/ contêm a licença proprietária Onyx Enterprise — portanto, "código aberto" com uma divisão empresarial, não apenas MIT - Implantação: Docker Compose / Kubernetes, auto-hospedado ou em nuvem; O modo de chat simplificado não é o mesmo que uma implementação completa de indexação. NOTAS SINCERAS: um documento indexado não é um documento recuperado, e uma passagem recuperada não é uma resposta correta — a qualidade da recuperação, a qualidade da fonte, as permissões e o comportamento do modelo são fatores importantes. A hospedagem própria não mantém automaticamente os dados locais se um provedor de modelo externo estiver configurado. Código aberto não é gratuito. Repositório: onyx-dot-app/onyx Documentação: docs.onyx.app MCP: modelcontextprotocol.io As capturas de tela mostradas são da própria interface do usuário do produto Onyx, retiradas de sua documentação e usadas para fins de revisão. Explicação independente — não afiliada ou patrocinada pela Onyx/DanswerAI. Inscreva-se no The Solo Engineer — Onde a Tecnologia Encontra a Realidade — para obter informações práticas sobre engenharia de IA, projetos de código aberto e análises técnicas de nível de produção. Você construiria seu próprio pipeline RAG do zero ou começaria com uma plataforma como o Onyx? Conte-me nos comentários. #OnyxAI #RAG #EngenhariaDeIA #CódigoAberto #MCP #IAEmpresarial #InteligênciaArtificial

    6 likes · 1 comment · 111 views
  5. YouTube · · YouTube description · AI & Tech Today · onyx-dot-app/onyx

    3 Trending GitHub Repos: Agents as Teammates, Company Context & Context-Window X-Ray Three repositories trending on GitHub, explained in plain language: what each one does, who should try it, how to get started, and what to watch out for. This time, all three are about agent context: Multica, a board where coding agents take issues like teammates; Onyx, a self-hosted layer that gives chat and agents your company's knowledge; and dsh-context, a DeepSeek Harness plugin that shows exactly what an agent is carrying in its context window. ⏱ Chapters 0:00 Intro & this week in dev tools 1:47 Multica: coding agents as teammates 4:43 Onyx: self-hosted company context 7:44 dsh-context: inside the context window 11:01 Summary 📦 Repos 1. multica-ai/multica – Multica / Index Labs (Go & TypeScript · Multica License: Apache 2.0 + additional conditions) multica-ai/multica Download: multica.ai Security model: multica.ai Self-hosting: github.com/multica-ai/multica/blob/main/SELF_HOST… 2. onyx-dot-app/onyx – Onyx / DanswerAI (Python · MIT core) onyx-dot-app/onyx Docs: docs.onyx.app Resource requirements: docs.onyx.app 3. bowenliang123/dsh-context – bowenliang123 (TypeScript · Apache-2.0) bowenliang123/dsh-context npm: npmjs.com DeepSeek Harness: deepseek.com 📰 News mentioned • Agentic AI Foundation adds Agent Skills, Open Responses, OpenEnv and OpenSandbox (Oct 22): linuxfoundation.org • GitHub package firewall in public preview (Oct 20): github.blog Star counts are as of 23 October 2026. Performance and resource claims are as reported in each project's README and docs. Summaries are simplified; see the repos for full details. Images: • Repo page screenshots: github.com/multica-ai/multica, github.com/onyx-dot-app/onyx, github.com/bowenliang123/dsh-context · screenshot • Onyx architecture diagram: github.com/onyx-dot-app/onyx/blob/main/docs/asset… · MIT • dsh-context Context Trend: github.com/bowenliang123/dsh-context/blob/main/do… · Apache-2.0 If you found this useful, like and subscribe for the next round of trending repos. #GitHub #OpenSource #AIAgents #DeveloperTools #ContextEngineering

    19 views
  6. YouTube · · YouTube description · Next Horizon · onyx-dot-app/onyx

    Onyx: instant answers from any internal document with every LLM Open Source AI Platform - AI Chat with advanced features that works with every LLM onyx-dot-app/onyx on GitHub: onyx-dot-app/onyx This week's round-up: youtube.com Trending today. This video describes what the project says it does — it is not a review or a recommendation. ▶ More like this: youtube.com Subscribe for a new open source project every day. #Shorts #GitHub #OpenSource #python #onyx #chat #features #works #coding #programming #developer #software #devtools #sourcecode #tech [ar] Onyx: إجابات فورية من أي مستند داخلي مع كل نماذج اللغات الكبيرة (LLMs) منصة ذكاء اصطناعي مفتوحة المصدر - دردشة ذكاء اصطناعي بميزات متقدمة تعمل مع جميع أنظمة إدارة التعلم onyx-dot-app/onyx على GitHub: onyx-dot-app/onyx ملخص هذا الأسبوع: youtube.com الأكثر رواجًا اليوم. يشرح هذا الفيديو وظائف المشروع المعلنة، وليس مراجعة أو توصية. ▶ المزيد من هذا النوع: youtube.com اشترك لتصلك مشاريع مفتوحة المصدر جديدة كل يوم. #Shorts #GitHub #OpenSource #python #onyx #chat #features #works #coding #programming #developer #software #devtools #sourcecode #tech [bn] Onyx: যেকোনো ইন্টারনাল ডকুমেন্ট এবং সব LLM থেকে তাৎক্ষণিক উত্তর ওপেন সোর্স এআই প্ল্যাটফর্ম - উন্নত বৈশিষ্ট্য সহ এআই চ্যাট যা প্রতিটি এলএলএম (LLM)-এর সাথে কাজ করে গিটহাবে (GitHub) onyx-dot-app/onyx: onyx-dot-app/onyx এই সপ্তাহের সারসংক্ষেপ: youtube.com আজকের ট্রেন্ডিং। এই ভিডিওটি বর্ণনা করে যে প্রকল্পটি কী করতে পারে — এটি কোনো পর্যালোচনা বা সুপারিশ নয়। ▶ এই ধরনের আরও ভিডিও: youtube.com প্রতিদিন একটি নতুন ওপেন সোর্স প্রকল্পের জন্য সাবস্ক্রাইব করুন। #Shorts #GitHub #OpenSource #python #onyx #chat #features #works #coding #programming #developer #software #devtools #sourcecode #tech [de-DE] Onyx: Sofortige Antworten aus jedem internen Dokument mit jedem LLM Open-Source-KI-Plattform – KI-Chat mit erweiterten Funktionen, kompatibel mit allen LLM-Systemen onyx-dot-app/onyx auf GitHub: onyx-dot-app/onyx Wochenrückblick: youtube.com Heute im Trend. Dieses Video beschreibt die Projektbeschreibung – es ist keine Rezension oder Empfehlung. ▶ Ähnliche Videos: youtube.com Abonniere unseren Kanal für täglich neue Open-Source-Projekte. #Shorts #GitHub #OpenSource #Python #Onyx #Chat #Funktionen #Funktioniert #Programmieren #Entwickler #Software #Entwicklungstools #Quellcode #Technik [es-US] Onyx: respuestas instantáneas de cualquier documento interno con todos los LLM Plataforma de IA de código abierto: Chat con IA y funciones avanzadas compatible con cualquier LLM. onyx-dot-app/onyx en GitHub: onyx-dot-app/onyx Resumen de esta semana: youtube.com Tendencia del día. Este video describe las funciones del proyecto; no es una reseña ni una recomendación. ▶ Más contenido similar: youtube.com Suscríbete para descubrir un nuevo proyecto de código abierto cada día. #Shorts #GitHub #OpenSource #python #onyx #chat #features #works #coding #programming #developer #software #devtools #sourcecode #tech [fr-FR] Onyx : des réponses instantanées depuis n'importe quel document interne avec tous les LLM Plateforme d'IA open source - Chat IA avec des fonctionnalités avancées, compatible avec tous les LLM onyx-dot-app/onyx sur GitHub : onyx-dot-app/onyx Récapitulatif de la semaine : youtube.com À la une aujourd'hui. Cette vidéo décrit le fonctionnement du projet ; il ne s'agit ni d'un test ni d'une recommandation. ▶ Plus de vidéos similaires : youtube.com Abonnez-vous pour découvrir un nouveau projet open source chaque jour. #Shorts #GitHub #OpenSource #python #onyx #chat #features #works #coding #programming #developer #software #devtools #sourcecode #tech [hi] Onyx: हर इंटरनल डॉक्यूमेंट से तुरंत जवाब, हर LLM के साथ ओपन सोर्स एआई प्लेटफॉर्म - उन्नत सुविधाओं से लैस एआई चैट, जो हर एलएलएम के साथ काम करता है ओनिक्स-डॉट-ऐप/ओनिक्स GitHub पर: onyx-dot-app/onyx इस सप्ताह का सारांश: youtube.com आज का ट्रेंडिंग। यह वीडियो प्रोजेक्ट के कार्यों का वर्णन करता है - यह कोई समीक्षा या अनुशंसा नहीं है। ▶ इस तरह के और वीडियो: youtube.com हर दिन एक नए ओपन सोर्स प्रोजेक्ट के लिए सब्सक्राइब करें। #Shorts #GitHub #OpenSource #python #onyx #chat #features #works #coding #programming #developer #software #devtools #sourcecode #tech [id] Onyx: jawaban instan dari dokumen internal apa pun dengan setiap LLM Platform AI Sumber Terbuka - Obrolan AI dengan fitur canggih yang kompatibel dengan setiap LLM onyx-dot-app/onyx di GitHub: onyx-dot-app/onyx Ringkasan minggu ini: youtube.com Sedang tren hari ini. Video ini menjelaskan apa yang diklaim proyek ini — ini bukan ulasan atau rekomendasi. ▶ Lebih banyak seperti ini: youtube.com Berlangganan untuk proyek sumber terbuka baru setiap hari. #Shorts #GitHub #OpenSource #python #onyx #chat #features #works #coding #programming #developer #software #devtools #sourcecode #tech [it] Onyx: risposte istantanee da qualsiasi documento interno con ogni LLM Piattaforma AI Open Source - Chat AI con funzionalità avanzate compatibile con tutti i LLM onyx-dot-app/onyx su GitHub: onyx-dot-app/onyx Riepilogo della settimana: youtube.com Tendenze di oggi. Questo video descrive le funzionalità dichiarate del progetto, non è una recensione né una raccomandazione. ▶ Altri video simili: youtube.com Iscriviti per scoprire un nuovo progetto open source ogni giorno. #Shorts #GitHub #OpenSource #python #onyx #chat #features #works #coding #programming #developer #software #devtools #sourcecode #tech [iw] Onyx: תשובות מיידיות מכל מסמך פנימי עם כל מודל שפה גדול (LLM) פלטפורמת בינה מלאכותית בקוד פתוח - צ'אט בינה מלאכותית עם תכונות מתקדמות שעובדות עם כל תואר שני במשפטים onyx-dot-app/onyx ב-GitHub: onyx-dot-app/onyx סיכום השבוע: youtube.com בטרנדים היום. סרטון זה מתאר מה הפרויקט אומר שהוא עושה - זו אינה סקירה או המלצה. ▶ עוד כמו זה: youtube.com הירשמו לפרויקט קוד פתוח חדש בכל יום. #Shorts #GitHub #OpenSource #python #onyx #chat #features #works #coding #programming #developer #software #devtools #sourcecode #tech [ja] Onyx:あらゆる社内ドキュメントから瞬時に回答、全LLMに対応 オープンソースAIプラットフォーム - あらゆるLLMに対応する高度な機能を備えたAIチャット GitHubのonyx-dot-app/onyx: onyx-dot-app/onyx 今週のまとめ: youtube.com 本日のトレンド。この動画はプロジェクトの説明であり、レビューや推奨ではありません。 ▶ 類似動画はこちら: youtube.com 毎日新しいオープンソースプロジェクトを紹介するチャンネル登録はこちら。 #Shorts #GitHub #OpenSource #python #onyx #chat #features #works #coding #programming #developer #software #devtools #sourcecode #tech [ko] Onyx: 모든 LLM을 활용해 사내 문서에서 즉시 답변 찾기 오픈 소스 AI 플랫폼 - 모든 LLM과 호환되는 고급 기능을 갖춘 AI 채팅 onyx-dot-app/onyx (GitHub: onyx-dot-app/onyx) 이번 주 요약: youtube.com 오늘의 인기 영상입니다. 이 영상은 프로젝트의 기능을 설명하는 영상이며, 리뷰나 추천이 아닙니다. ▶ 더 많은 영상 보기: youtube.com 매일 새로운 오픈 소스 프로젝트를 받아보시려면 구독하세요. #Shorts #GitHub #OpenSource #python #onyx #chat #features #works #coding #programming #developer #software #devtools #sourcecode #tech [ml] Onyx: ഏത് ഇന്റേണൽ ഡോക്യുമെന്റിൽ നിന്നും ഏത് LLM ഉപയോഗിച്ചും തൽക്ഷണ ഉത്തരങ്ങൾ ഓപ്പൺ സോഴ്‌സ് AI പ്ലാറ്റ്‌ഫോം - എല്ലാ LLM-ലും പ്രവർത്തിക്കുന്ന വിപുലമായ സവിശേഷതകളുള്ള AI ചാറ്റ് GitHub-ലെ onyx-dot-app/onyx: onyx-dot-app/onyx ഈ ആഴ്ചയിലെ സംഗ്രഹം: youtube.com ഇന്ന് ട്രെൻഡുചെയ്യുന്നു. പ്രോജക്റ്റ് എന്താണ് പറയുന്നതെന്ന് ഈ വീഡിയോ വിവരിക്കുന്നു - ഇത് ഒരു അവലോകനമോ ശുപാർശയോ അല്ല. ▶ ഇതുപോലുള്ള കൂടുതൽ: youtube.com എല്ലാ ദിവസവും ഒരു പുതിയ ഓപ്പൺ സോഴ്‌സ് പ്രോജക്റ്റിനായി സബ്‌സ്‌ക്രൈബുചെയ്യുക. #ഷോർട്ട്‌സ് #GitHub #OpenSource #python #onyx #chat #features #works #coding #programming #developer #software #devtools #sourcecode #tech [nl-NL] Onyx: directe antwoorden uit elk intern document met elke LLM Open Source AI-platform - AI-chat met geavanceerde functies die werkt met elke LLM onyx-dot-app/onyx op GitHub: onyx-dot-app/onyx Het overzicht van deze week: youtube.com Trending vandaag. Deze video beschrijft wat het project doet — het is geen recensie of aanbeveling. ▶ Meer zoals dit: youtube.com Abonneer je voor een nieuw open source-project elke dag. #Shorts #GitHub #OpenSource #python #onyx #chat #features #works #coding #programming #developer #software #devtools #sourcecode #tech [pa] Onyx: ਹਰ LLM ਦੇ ਨਾਲ ਕਿਸੇ ਵੀ ਅੰਦਰੂਨੀ ਦਸਤਾਵੇਜ਼ ਤੋਂ ਤੁਰੰਤ ਜਵਾਬ ਓਪਨ ਸੋਰਸ ਏਆਈ ਪਲੇਟਫਾਰਮ - ਐਡਵਾਂਸਡ ਵਿਸ਼ੇਸ਼ਤਾਵਾਂ ਦੇ ਨਾਲ ਏਆਈ ਚੈਟ ਜੋ ਹਰ ਐਲਐਲਐਮ ਨਾਲ ਕੰਮ ਕਰਦੀ ਹੈ onyx-dot-app/onyx on GitHub: onyx-dot-app/onyx ਇਸ ਹਫ਼ਤੇ ਦਾ ਸੰਖੇਪ: youtube.com ਅੱਜ ਟ੍ਰੈਂਡਿੰਗ। ਇਹ ਵੀਡੀਓ ਦੱਸਦਾ ਹੈ ਕਿ ਪ੍ਰੋਜੈਕਟ ਕੀ ਕਹਿੰਦਾ ਹੈ ਕਿ ਇਹ ਕੀ ਕਰਦਾ ਹੈ — ਇਹ ਕੋਈ ਸਮੀਖਿਆ ਜਾਂ ਸਿਫ਼ਾਰਸ਼ ਨਹੀਂ ਹੈ। ▶ ਇਸ ਤਰ੍ਹਾਂ ਦੇ ਹੋਰ: youtube.com ਹਰ ਰੋਜ਼ ਇੱਕ ਨਵੇਂ ਓਪਨ ਸੋਰਸ ਪ੍ਰੋਜੈਕਟ ਲਈ ਗਾਹਕ ਬਣੋ। #Shorts #GitHub #OpenSource #python #onyx #chat #features #works #coding #programming #developer #software #devtools #sourcecode #tech [pl] Onyx: natychmiastowe odpowiedzi z dowolnego dokumentu wewnętrznego przy użyciu dowolnego modelu LLM Platforma Open Source AI – czat AI z zaawansowanymi funkcjami, który działa z każdym programem LLM onyx-dot-app/onyx na GitHubie: onyx-dot-app/onyx Podsumowanie tygodnia: youtube.com Dzisiejsze trendy. Ten film opisuje, co projekt obiecuje — nie jest to recenzja ani rekomendacja. ▶ Więcej na ten temat: youtube.com Subskrybuj, aby każdego dnia otrzymywać informacje o nowym projekcie open source. #Shorts #GitHub #OpenSource #python #onyx #chat #features #works #coding #programming #developer #software #devtools #sourcecode #tech [pt-BR] Onyx: respostas instantâneas de qualquer documento interno com todos os LLMs Plataforma de IA de código aberto - Chat com IA e recursos avançados que funciona com qualquer LLM onyx-dot-app/onyx no GitHub: onyx-dot-app/onyx Resumo desta semana: youtube.com Em alta hoje. Este vídeo descreve o que o projeto faz — não é uma avaliação ou recomendação. ▶ Mais vídeos como este: youtube.com Inscreva-se para receber um novo projeto de código aberto todos os dias. #Shorts #GitHub #OpenSource #python #onyx #chat #features #works #coding #programming #developer #software #devtools #sourcecode #tech [ru] Onyx: мгновенные ответы из любого внутреннего документа с использованием любой LLM Платформа с открытым исходным кодом для ИИ — чат с ИИ и расширенными функциями, работающий с любым LLM onyx-dot-app/onyx на GitHub: onyx-dot-app/onyx Обзор этой недели: youtube.com Тренды сегодня. В этом видео описывается, что, по заявлению проекта, он делает — это не обзор и не рекомендация. ▶ Больше подобного: youtube.com Подписывайтесь, чтобы получать новый проект с открытым исходным кодом каждый день. #Shorts #GitHub #OpenSource #python #onyx #chat #features #works #coding #programming #developer #software #devtools #sourcecode #tech [ta] Onyx: அனைத்து LLM-களுடன் எந்தவொரு உள் ஆவணத்திலிருந்தும் உடனடி பதில்கள் திறந்த மூல AI தளம் - ஒவ்வொரு LLM-உடனும் செயல்படும் மேம்பட்ட அம்சங்களைக் கொண்ட AI அரட்டை GitHub-இல் உள்ள onyx-dot-app/onyx: onyx-dot-app/onyx இந்த வாரத் தொகுப்பு: youtube.com இன்று பிரபலமாக உள்ளது. இந்த வீடியோ, இந்தத் திட்டம் என்ன செய்வதாகக் கூறுகிறதோ அதை விவரிக்கிறது — இது ஒரு விமர்சனமோ அல்லது பரிந்துரையோ அல்ல. ▶ இது போன்ற மேலும் பல: youtube.com ஒவ்வொரு நாளும் ஒரு புதிய திறந்த மூலத் திட்டத்திற்காக சப்ஸ்கிரைப் செய்யுங்கள். #Shorts #GitHub #OpenSource #python #onyx #chat #features #works #coding #programming #developer #software #devtools #sourcecode #tech [te] Onyx: అన్ని అంతర్గత పత్రాల నుండి మరియు ప్రతి LLMతో తక్షణ సమాధానాలు ఓపెన్ సోర్స్ AI ప్లాట్‌ఫామ్ - ప్రతి LLMతో పనిచేసే అధునాతన ఫీచర్లతో కూడిన AI చాట్ GitHubలో onyx-dot-app/onyx: onyx-dot-app/onyx ఈ వారం రౌండప్: youtube.com ఈరోజు ట్రెండింగ్. ఈ వీడియో, ప్రాజెక్ట్ ఏమి చేస్తుందో వివరిస్తుంది — ఇది సమీక్ష లేదా సిఫార్సు కాదు. ▶ ఇలాంటివి మరిన్ని: youtube.com ప్రతిరోజూ ఒక కొత్త ఓపెన్ సోర్స్ ప్రాజెక్ట్ కోసం సబ్‌స్క్రయిబ్ చేసుకోండి. #Shorts #GitHub #OpenSource #python #onyx #chat #features #works #coding #programming #developer #software #devtools #sourcecode #tech [uk] Onyx: миттєві відповіді з будь-якого внутрішнього документа з будь-якою LLM Платформа штучного інтелекту з відкритим кодом – чат на основі штучного інтелекту з розширеними функціями, який працює з кожним LLM onyx-dot-app/onyx на GitHub: onyx-dot-app/onyx Огляд цього тижня: youtube.com Тренди сьогодні. Це відео описує, що саме робить проект, – це не огляд і не рекомендація. ▶ Більше схожих відео: youtube.com Підпишіться на новий проект з відкритим кодом щодня. #Шорти #GitHub #ВідкритийКод #python #onyx #чат #функції #робота #кодування #програмування #розробник #програмне забезпечення #інструментирозробки #вихіднийкод #технології

    4 likes · 1 comment · 114 views
  7. Huge props to @onyx_dot_app for building such a robust and flexible AI platform. Seriously slick workflow for wrangling every LLM in one place 🚀 🔗 项目地址:onyx-dot-app/onyx

    1 like · 8 views
  8. [GitHub Repo] Onyx: Open Source AI Platform - AI Chat with advanced features that works with every LLM onyx-dot-app/onyx #MachineLearning #ChatGPT t.co

    2 likes · 218 views
  9. Reduce API surface for BLAKE2 to match OpenSSL semantics This is an updated version of the original post which reduces the scope of the work on BLAKE2. I originally wanted to remove non-standard parameters to BLAKE2 to make the module more maintainable in the future as well as SIMD support, but I am planning to only remove SIMD support for now. I still think it's wrong to use tree-hashing with BLAKE2 since BLAKE3 exists and should be used instead. Nonetheless, after looking at the deprecation PRs (gh-160374 and gh-160375) and the long period this would require to actually remove the code, I don't think it's really worth it. It would at least reduce the impact to downstream users almost to zero. Instead, I suggest that we soft-deprecate the interface for tree hashing in the docs and suggest BLAKE3 instead. ---- Original post: I want to reduce BLAKE2 in hashlib to a minimal API matching OpenSSL. More precisely, BLAKE2 is kept without SIMD and matches the API of OpenSSL's BLAKE2 (digest, MAC): data and digest_size for the hash, and salt/person with a key. Tree hashing, salt/person without a key, and HMAC-BLAKE2 will be deprecated in 3.16 and removed in 3.21. If necessary, the deprecation period will be extended to a few more releases but I really want to get rid of the annoying API surface. BLAKE2 is already a keyed hash function, it doesn't make sense to use HMAC on top of it, despite some libraries using the HMAC-BLAKE2 HACL* sources for that (see gh-138114). In an ideal world, I would remove BLAKE2 and recommend BLAKE3 or SHA-based alternatives. Note that currently (and likely in the future), there are no plans to add BLAKE3 to hashlib (see gh-83479). For a fast secure hash, BLAKE3 is available as the blake3 package. It is maintained by the BLAKE3 authors, has a hashlib-like API, supports keyed hashing and key derivation, and has wheels for all major platforms. Maintenance pain BLAKE2 has been in hashlib since 3.6, first as a custom module with our own implementation, then as a wrapper around the vendored HACL* sources (support for HACL* HMAC was added in 3.14, together with support for BLAKE2 despite numerous shortcomings on some platforms). BLAKE2 has the largest API in hashlib (key, salt, person and seven tree-hashing parameters). Most of its maintenance cost comes from the SIMD code: it needs per-platform compiler flags and CPU detection as well as dedicated code paths for the vectorized versions, is only enabled on (some) x86-64, and usually breaks on non-Tier-1 platforms: - gh-123748: macOS universal2 builds failed (SIMD256 compiles for x86-64 but not ARM64); - gh-124304: SIMD had to be disabled on older Android versions; - gh-126458: SIMD support wrongly detected under WASI; - gh-128134: missing aligned_alloc check on older macOS; - gh-130213: older toolchains failed without the SIMD flags; - gh-133042: duplicate symbols when cross-compiling for Emscripten (still unfixed); - gh-138114: HMAC-BLAKE2 does not properly use the SIMD implementations (still unfixed). The module also needed several correctness fixes (gh-152851, gh-155830, gh-155835). Impact GitHub code search (excluding forks, CPython copies and vendored site-packages) finds about 34,000 Python files using hashlib.blake2b, 4,800 using hashlib.blake2s, and 300 using hashlib.new("blake2b") or hashlib.new("blake2s"). 62 of the 500 most-starred active Python repositories on GitHub use BLAKE2, e.g. PyTorch, Transformers, Home Assistant, Sentry, Streamlit, Gradio and Airflow. Of 1,753 sampled call sites (1,420 repositories), 1,649 (1,336 repositories) only use digest_size, 59 (51 repositories) use key, and 45 (38 repositories) use salt or person without a key. None use tree hashing. Most of them only need a fast hash, for which SHA-2, SHA-3 or BLAKE3 also work. This includes: - projects that store digests, such as Home Assistant (cache filenames), Mathesar (database identifiers) and Onyx (search-index IDs); - projects that depend on the exact BLAKE2 output, such as networkx (graph hashes), LangChain (indexing), apprise and a minisign verifier (BLAKE2b-512 signatures), copyparty (client checksums); - projects that use keyed BLAKE2 such as agno (MinHash) and openai-python (Bedrock helper); or - projects such as PyPI or Poetry for checksums, Warehouse for storage and publishing (though it looks like a legacy API), or python-tuf. One popular project affected by this change would be ComfyUI (which uses person without a key). In particular, I don't expect too much of downstream breakage (considering the long deprecation period) but I would appreciate if anyone against this proposal could explain why SIMD BLAKE2 should be kept (note that I already plan to remove SIMD support in 3.16 without a deprecation notice as it created too many issues, while exposing the OpenSSL implementation). Note that projects can rely on nacl.hash.blake2b (PyNaCl does not offer a 2s version) or PyCryptodome for blake2b and blake2s. AFAIK, there is no PyPI packages providing the tree-hashing feature but the latter is neither standardized by an RFC nor used in the wild. ---- > AI disclosure: Opus 5.5 was used for collecting and classifying data.

    4 likes · 1 comment
  10. Onyx - The context layer powered by all your apps. onyx-dot-app/onyx So, how does this affect the future of Claude?

    6 views
Trending awards, every completed day and week
Gold
01st place finishes
Silver
02nd place finishes
Bronze
03rd place finishes
Awarded repositories
0Owned by onyx-dot-app now

No trending awards yet

None of the repositories onyx-dot-app owns has finished in the top three of a completed trending day or week, by stars, forks or PR authors. See who is trending now.

A repository earns an award for finishing first, second or third in a completed trending day or week, ranked by new stars, new forks or pull request authors. Awards follow a repository through renames and transfers and count toward its current owner. Weeks run Monday to Sunday, UTC.