awesome-repositories.com
Blog
MCP
awesome-repositories.com

Entdecke die besten Open-Source-Repositories mit KI-gestützter Suche.

EntdeckenKuratierte SuchenOpen-Source-AlternativenSelf-hosted SoftwareBlogSitemap
ProjektMCP-ServerÜber unsRanking-MethodikPresse
RechtlichesDatenschutzAGB
© 2026 Bringes Technology SRL·VAT RO45896025·hello@awesome-repositories.com
·

12 Repos

Awesome GitHub RepositoriesThird-Party Model Integration

Mechanisms for importing external machine learning models and converting them into internal scoring expressions.

Distinct from Third Party Integrations: Candidates focus on generic API integrations or mobile libraries, not the conversion of ML models into search ranking expressions.

Explore 12 awesome GitHub repositories matching artificial intelligence & ml · Third-Party Model Integration. Refine with filters or upvote what's useful.

Awesome Third-Party Model Integration GitHub Repositories

Finde die besten Repos mit KI.Wir suchen mit KI nach den am besten passenden Repositories.
  • coaidev/coaiAvatar von coaidev

    coaidev/coai

    9,212Auf GitHub ansehen↗

    CoAI is an enterprise-grade, self-hostable AI gateway platform that unifies access to over 200 AI models from more than 35 providers through a single OpenAI-compatible API endpoint. It functions as a multi-tenant gateway, routing requests across providers with load balancing, automatic failover, and priority-based routing, while exposing standard OpenAI API endpoints for chat, image generation, model listing, and billing to enable seamless integration with existing tools and clients. The platform distinguishes itself through a comprehensive set of operational capabilities built around the gat

    Connects self-hosted or custom AI models alongside third-party providers for unified access.

    TypeScriptai-gatewayapichat
    Auf GitHub ansehen↗9,212
  • vespa-engine/vespaAvatar von vespa-engine

    vespa-engine/vespa

    6,961Auf GitHub ansehen↗

    Vespa is a distributed search engine, vector database, and machine learning ranking engine. It serves as an AI search platform designed to handle large-scale document indexing and complex query processing across a cluster of nodes, combining keyword retrieval with high-dimensional embedding storage for semantic similarity search. The platform distinguishes itself by integrating machine learning models directly into the search pipeline to perform real-time inference and ranking. It converts these models into ranking expressions to score and order results based on relevance, while providing a s

    Imports external machine learning models and converts them into ranking expressions to optimize search results.

    Java
    Auf GitHub ansehen↗6,961
  • open-compass/opencompassAvatar von open-compass

    open-compass/opencompass

    6,678Auf GitHub ansehen↗

    OpenCompass is an open-source framework for standardized benchmarking of large language models. It provides a configurable evaluation pipeline that supports both objective and subjective assessment, using a dual-engine architecture to handle closed-form answer comparison and open-ended response rating. The framework is designed as a modular platform where datasets, models, and metrics are composed through declarative YAML configuration files. The framework distinguishes itself through its extensible model integration layer, which supports custom models, HuggingFace models, and third-party API

    Supports integrating third-party, HuggingFace, and API-based models through a common subclassing interface.

    Pythonbenchmarkchatgptevaluation
    Auf GitHub ansehen↗6,678
  • kijai/comfyui-wanvideowrapperAvatar von kijai

    kijai/ComfyUI-WanVideoWrapper

    6,554Auf GitHub ansehen↗

    I've made everythign less reliant on torch.compile for VRAM efficiency, so things should work better even without it. Also figured workaround for some issues when using compile that made first run use drastically more VRAM, issue I battled with myself a lot.

    Loads and runs additional video generation models and techniques within a unified workflow.

    Python
    Auf GitHub ansehen↗6,554
  • awslabs/gluon-tsAvatar von awslabs

    awslabs/gluon-ts

    5,200Auf GitHub ansehen↗

    GluonTS ist ein Framework für probabilistische Zeitreihenprognosen, das darauf ausgelegt ist, zukünftige Werte als Wahrscheinlichkeitsverteilungen mit Konfidenzintervallen vorherzusagen. Es unterstützt sowohl das traditionelle Modelltraining als auch Zero-Shot-Forecasting, bei dem vortrainierte Modelle Vorhersagen für neue Serien ohne zusätzliches Training generieren. Das Projekt zeichnet sich durch die Integration einer Vielzahl von Prognoseansätzen in einen einheitlichen Workflow aus. Dies umfasst Deep-Learning-Architekturen wie rekurrente neuronale Netze und kausale Konvolutionen sowie die Integration externer statistischer Modelle, der Prophet-Bibliothek und R-Paketen. Das Toolkit bietet eine umfassende Oberfläche für das Zeitreihen-Data-Engineering, die Datensatzskalierung, -aufteilung und die Transformation roher Zeitdaten in Tensoren abdeckt. Es enthält zudem eine Suite von Evaluierungstools zur Messung von Prognosegenauigkeit und Unsicherheitsintervallen sowie Hilfsmittel zur Datensatzpersistenz unter Verwendung von Formaten wie Arrow und Parquet. Das Framework unterstützt die Bereitstellung von Prognosemodellen innerhalb der Cloud-Infrastruktur.

    Connects third-party time series libraries and statistical models to create a unified deep learning forecasting workflow.

    Python
    Auf GitHub ansehen↗5,200
  • yangjian102621/geekaiAvatar von yangjian102621

    yangjian102621/geekai

    4,665Auf GitHub ansehen↗

    Geekai is a multi-model AI platform and SaaS framework designed to deploy and manage AI agents and multimodal models through a unified interface. It serves as a multimodal AI gateway, providing centralized access to large language models and generative tools for text, image, audio, and video production. The project functions as an AI agent orchestrator, allowing for the definition of specialized personas and the import of external workflows and knowledge bases. It distinguishes itself by providing a complete commercial service layer, including credit-based billing, subscription management, an

    Enables conversational chat and image generation by integrating third-party API keys and model configurations.

    Vueazurechatgptdalle3
    Auf GitHub ansehen↗4,665
  • casibase/casibaseAvatar von casibase

    casibase/casibase

    4,443Auf GitHub ansehen↗

    Casibase is an open-source platform that orchestrates multi-turn conversations with large language models and manages retrieval-augmented knowledge bases from a single interface. It provides a unified system for connecting to over 30 AI model providers, ingesting documents into vector embeddings for semantic search, and running autonomous agent loops that can drive a browser, search the web, execute commands, and integrate with external tools. The platform distinguishes itself by combining AI conversation management with infrastructure and application orchestration capabilities. It includes a

    Integrates third-party language model services to power conversational and reasoning tasks.

    Goa2aagentagi
    Auf GitHub ansehen↗4,443
  • microsoft/flamlAvatar von microsoft

    microsoft/FLAML

    4,365Auf GitHub ansehen↗

    FLAML ist ein automatisiertes Machine-Learning-Framework, ein Tool zur Hyperparameter-Optimierung und ein Orchestrator für Large-Language-Model-Agenten. Es bietet ein System zur Modellauswahl und -abstimmung über verschiedene Lerner und Datensätze hinweg und stellt gleichzeitig ein Toolkit zur Optimierung der Inferenzparameter und Fine-Tuning-Einstellungen von Large Language Models bereit. Das Projekt verfügt über ein Meta-Learning-Tuning-System, das historische Aufgabendaten analysiert, um datenabhängige Standardkonfigurationen zu generieren und die Modellkonvergenz zu beschleunigen. Es ermöglicht zudem das Design kollaborativer Multi-Agenten-Systeme durch konversationelle Workflows und ereignisgesteuerte Orchestrierung. Die Funktionen decken eine ressourceneffiziente Hyperparametersuche für Machine-Learning-Modelle und beliebige Python-Funktionen ab und unterstützen hierarchische Suchräume sowie lexikografische Zieloptimierung. Das Framework enthält zudem Dienstprogramme für automatisierte Modellauswahl, gestapelte Ensemble-Konstruktion, Zero-Shot-Konfiguration und die Durchsetzung von Fairness-Beschränkungen. Das System unterstützt die Skalierung verteilter Abstimmungen und die gleichzeitige Ausführung von Versuchen über Compute-Cluster hinweg, um die Gesamtsuchdauer zu reduzieren.

    Integrates third-party learners and transformers into the automated tuning pipeline via provider APIs.

    Jupyter Notebook
    Auf GitHub ansehen↗4,365
  • lencx/nofwlAvatar von lencx

    lencx/nofwl

    4,150Auf GitHub ansehen↗

    nofwl ist ein plattformübergreifender Desktop-Client für die Interaktion mit Large Language Models. Er dient als grafische Benutzeroberfläche, die sich über persönliche API-Schlüssel mit externen KI-Diensten verbindet. Die Anwendung bietet eine lokalisierte Erfahrung mit Unterstützung für mehrere Systemsprachen und anpassbare visuelle Themen, einschließlich heller, dunkler und system-synchronisierter Schemata. Sie läuft unter Windows, macOS und Linux. Der Client verwaltet den Konversationsverlauf und die Benutzerkonfiguration durch Local-First-Datenspeicherung und speichert Chat-Nachrichten als strukturierte Textdateien auf dem Gerät des Benutzers. Er enthält zudem Dienstprogramme zum Kopieren von Konversationstexten und zur Inspektion von Roh-Nachrichtendaten.

    Uses API keys to authenticate outbound requests to third-party AI services.

    Rustapplicationchatgptdesktop
    Auf GitHub ansehen↗4,150
  • comfyanonymous/comfyui_examplesAvatar von comfyanonymous

    comfyanonymous/ComfyUI_examples

    3,918Auf GitHub ansehen↗

    This repository is a collection of node-based pipeline configurations, examples, and templates for generating AI media. It provides a workflow library and a curated gallery of blueprints designed for creating images, videos, and 3D assets using diffusion models. The project specifically offers a set of pre-configured node graphs for implementing advanced image generation and refinement techniques, with a focus on Stable Diffusion workflows. These examples demonstrate how to interconnect processing nodes to define complex generative logic without writing code. The available templates cover a

    Links the node interface to external closed-source models through specialized integration mechanisms.

    HTML
    Auf GitHub ansehen↗3,918
  • facebookresearch/map-anythingAvatar von facebookresearch

    facebookresearch/map-anything

    2,915Auf GitHub ansehen↗

    Map-anything is a 3D scene reconstruction framework and neural geometry estimator designed to transform two-dimensional images into metric three-dimensional spatial representations using feed-forward neural networks. It provides a specialized toolkit for predicting camera intrinsics and ray directions from single images without requiring external geometric metadata. The project includes a 3D model benchmarking suite that utilizes a unified model wrapper to standardize outputs from diverse reconstruction models. This allows for consistent evaluation and accuracy measurement across various spat

    Runs multiple third-party reconstruction models through a single interface to ensure consistent output formats for evaluation.

    Python3d-reconstructionaicalibration
    Auf GitHub ansehen↗2,915
  • stormzhang/ai-coding-guideAvatar von stormzhang

    stormzhang/ai-coding-guide

    1,164Auf GitHub ansehen↗

    This project provides a comprehensive guide and framework for implementing autonomous AI coding assistants within local development environments. It focuses on orchestrating multi-agent teams that can plan, execute, and verify complex software engineering tasks, such as refactoring, bug resolution, and test generation, while maintaining deep awareness of project-specific context and memory. The system distinguishes itself through a robust security-first architecture that enforces granular access controls, execution isolation, and mandatory human-in-the-loop approvals for all file modification

    Allows configuration of external AI providers by mapping base URLs and model identifiers to augment default service endpoints.

    agentai-codinganthropic
    Auf GitHub ansehen↗1,164
  1. Home
  2. Artificial Intelligence & ML
  3. Third-Party Model Integration

Unter-Tags erkunden

  • API Key IntegrationsMechanisms for connecting third-party AI services using API keys and custom model configurations. **Distinct from Third-Party Model Integration:** Focuses on API key connectivity for chat and image generation rather than converting models into internal scoring expressions.
  • API Service EvaluationsConnecting to third-party API services like OpenAI or ChatGLM to run model evaluations using a configuration file. **Distinct from Third-Party Model Integration:** Distinct from Third-Party Model Integration: focuses on evaluating models accessed via API services, not importing models into internal scoring.
  • Partner Media GenerationSynthesis of visual content using third-party partner models integrated via billing systems. **Distinct from Third-Party Model Integration:** Focuses on visual media synthesis rather than converting models into internal scoring expressions.
  • Video Model IntegratorsLoads and runs additional video generation models and techniques within a unified workflow. **Distinct from Third-Party Model Integration:** Distinct from Third-Party Model Integration: focuses on integrating video generation models specifically, not general ML models.
  • Video Model LoadersLoads and runs additional video generation models and techniques within a unified workflow. **Distinct from Third-Party Model Integration:** Distinct from Third-Party Model Integration: specific to video generation models, not general ML model conversion.