awesome-repositories.com
المدونة
MCP
awesome-repositories.com

اكتشف أفضل مستودعات المصادر المفتوحة باستخدام بحث مدعوم بالذكاء الاصطناعي.

استكشفعمليات بحث منسقةبدائل مفتوحة المصدربرمجيات ذاتية الاستضافةالمدونةخريطة الموقع
المشروعخادم MCPحولكيفية ترتيب النتائجالصحافة
قانونيالخصوصيةالشروط
© 2026 Bringes Technology SRL·VAT RO45896025·hello@awesome-repositories.com
·

21 مستودعات

Awesome GitHub RepositoriesOn-Demand Context Loading

Mechanisms for fetching detailed operational instructions only when a specific capability is triggered.

Distinct from Project Context Managers: Focuses on token-reduction via lazy-loading of instructions rather than static project constraints.

Explore 21 awesome GitHub repositories matching software engineering & architecture · On-Demand Context Loading. Refine with filters or upvote what's useful.

Awesome On-Demand Context Loading GitHub Repositories

اعثر على أفضل المستودعات باستخدام الذكاء الاصطناعي.سنبحث عن أفضل المستودعات المطابقة باستخدام الذكاء الاصطناعي.
  • microsoft/ai-agents-for-beginnersالصورة الرمزية لـ microsoft

    microsoft/ai-agents-for-beginners

    67,369عرض على GitHub↗

    This project is a structured educational resource and technical guide for designing and implementing autonomous systems using large language models. It provides a comprehensive curriculum and code samples focused on agentic design patterns, autonomous development, and the creation of systems capable of planning and executing multi-step tasks. The resource details the implementation of agentic retrieval-augmented generation, where models autonomously plan and refine data searches. It covers a wide array of orchestrators and design patterns, including metacognitive reflection for self-correctin

    Injects relevant background information into the model before processing a query to ensure informed responses.

    Jupyter Notebookagentic-aiagentic-frameworkagentic-rag
    عرض على GitHub↗67,369
  • addyosmani/agent-skillsالصورة الرمزية لـ addyosmani

    addyosmani/agent-skills

    60,849عرض على GitHub↗

    Agent-skills is a collection of structured instructions and behavioral personas designed to standardize how AI coding agents perform engineering tasks. It functions as a workflow orchestrator that maps natural language intent to repeatable technical sequences and verification checklists. The project distinguishes itself through the use of specialized markdown-defined roles, such as security auditors or test engineers, to apply targeted domain expertise. It employs an evidence-based verification model that requires runtime data or passing tests as mandatory exit criteria to ensure AI-generated

    Allows for the explicit referencing of skill files within prompts to force specific workflows on-demand.

    Shellagent-skillsantigravityantigravity-ide
    عرض على GitHub↗60,849
  • junegunn/vim-plugالصورة الرمزية لـ junegunn

    junegunn/vim-plug

    35,685عرض على GitHub↗

    vim-plug is a plugin manager for the Vim text editor that functions as a git-based dependency manager and configuration bootstrapper. It downloads and organizes external plugin packages from remote repositories to extend the editor's functionality. The project acts as a lazy-loading orchestrator to reduce editor startup time by deferring the loading of plugins until specific commands or file types are encountered. It enables version pinning by allowing plugins to be fetched using specific git branches, tags, or commit hashes. The manager provides a framework for plugin installation, lifecycl

    Reduces editor startup time by loading plugins only when specific commands or file types are encountered.

    Vim Scriptvim
    عرض على GitHub↗35,685
  • spacevim/spacevimالصورة الرمزية لـ SpaceVim

    SpaceVim/SpaceVim

    20,253عرض على GitHub↗

    SpaceVim is a modular configuration framework for Vim and Neovim designed to manage settings, plugins, and keybindings across different editing environments. It functions as a plugin manager that uses a layered organization system to group related functions and plugins, reducing the manual effort required for configuration. The system is centered around a mnemonic keybinding strategy that utilizes the space bar as the primary modifier for editor commands. To maintain performance, the framework implements a startup optimizer that delays the loading of non-essential plugins until they are requi

    Implements a deferred plugin loading mechanism to minimize initial editor startup time.

    Vim Script
    عرض على GitHub↗20,253
  • wsdjeg/spacevimالصورة الرمزية لـ wsdjeg

    wsdjeg/SpaceVim

    20,248عرض على GitHub↗

    SpaceVim is a modular configuration framework designed for managing plugins and settings across Vim and Neovim. It utilizes a layer-based architecture to organize related editor extensions into functional groups, reducing the overhead associated with manual setup and maintenance. The framework features a mnemonic keybinding system that maps editor commands to intuitive key sequences and provides integrated discovery guides. To improve performance, it employs a deferred plugin loader that reduces startup time by loading extensions only when they are specifically required. The system provides

    Implements a deferred plugin loader that increases startup speed by delaying initialization until modules are requested.

    Vim Script
    عرض على GitHub↗20,248
  • nesquena/hermes-webuiالصورة الرمزية لـ nesquena

    nesquena/hermes-webui

    14,912عرض على GitHub↗

    Hermes-webui is a self-hosted AI orchestrator and web interface for managing autonomous agents. It serves as a multi-provider gateway that connects cloud and local large language models, providing a central hub to execute scheduled background jobs, run shell commands, and manage agent memory on private hardware. The system distinguishes itself through a persistent memory manager that utilizes knowledge graphs and markdown files for long-term context across sessions. It features a model context protocol host for extending agent capabilities with standardized tools and supports the orchestratio

    Writes new skill modules to extend functional abilities based on learned context and operational experience.

    Pythonagentai-agentshermes
    عرض على GitHub↗14,912
  • hkuds/openharnessالصورة الرمزية لـ HKUDS

    HKUDS/OpenHarness

    14,084عرض على GitHub↗

    OpenHarness is a framework for building and orchestrating AI agents that utilize tools and plugins to execute complex tasks. It provides an orchestration system for managing language model lifecycles and a multi-agent coordination system for delegating workloads across teams of specialized subagents. The project features an agent gateway that bridges language model agents to external chat platforms and communication channels. It includes a tool integration engine for executing shell, file, and web operations, supported by a memory and skill manager that handles persistent user preferences and

    Implements modular, domain-specific instruction files loaded into the agent context to guide task execution.

    Python
    عرض على GitHub↗14,084
  • andrewyng/context-hubالصورة الرمزية لـ andrewyng

    andrewyng/context-hub

    13,700عرض على GitHub↗

    Context Hub is a retrieval-augmented generation framework and context management system designed to provide large language model agents with curated, versioned markdown documentation. It functions as a documentation provider that delivers precise API references and technical context to reduce hallucinations and token waste. The system incorporates an agentic memory layer that maintains persistent local annotations and user feedback to improve how agents retrieve task-specific knowledge. It uses a version-controlled repository of technical documentation designed for both machine readability an

    Retrieves only the minimal subset of required reference files based on current task requirements to optimize tokens.

    JavaScript
    عرض على GitHub↗13,700
  • agentskills/agentskillsالصورة الرمزية لـ agentskills

    agentskills/agentskills

    10,303عرض على GitHub↗

    Agent Skills is a framework for bundling executable scripts and metadata to extend the capabilities and tool-use of language model agents. It provides a standardized directory structure for packaging specialized workflows, technical instructions, and portable agent capabilities for distribution across different AI platforms. The project features a tool optimization suite used to refine skill triggers and evaluate the reliability of agent-activated capabilities. It includes a context-aware knowledge manager that organizes technical references into a hierarchy, loading them on demand to reduce

    Reduces token consumption by loading full technical instructions on demand rather than during initial discovery.

    Pythonagent-skills
    عرض على GitHub↗10,303
  • jeffallan/claude-skillsالصورة الرمزية لـ Jeffallan

    Jeffallan/claude-skills

    9,935عرض على GitHub↗

    This project is an AI agent workflow orchestrator and automated software lifecycle manager designed to sequence specialized AI personas for end-to-end software development. It serves as a prompt engineering library and a full-stack development toolkit that guides the process from initial discovery and specification through to deployment and code review. The system features a context management framework that utilizes progressive loading and routing tables to fetch reference files on-demand, reducing token consumption within the model context window. It employs a definition-based routing syste

    Reduces token consumption by lazily fetching detailed reference data and documentation only when specific triggers occur.

    Pythonai-agentsclaudeclaude-code
    عرض على GitHub↗9,935
  • nvim-mini/mini.nvimالصورة الرمزية لـ nvim-mini

    nvim-mini/mini.nvim

    9,325عرض على GitHub↗

    mini.nvim is a comprehensive library of independent modules designed to extend Neovim with a wide array of navigation, user interface, and text manipulation tools. It serves as a modular plugin collection, a UI toolkit for creating custom statuslines and notifications, and a package manager for installing and pinning external plugins from Git. The project provides a specialized fuzzy picker framework for filtering files and symbols, an LSP completion engine with interactive snippet expansion, and a dedicated plugin test framework that uses headless editor instances and remote procedure calls

    Optimizes startup time by scheduling the execution of plugin setup code to occur after the initial load.

    Lualuamini-nvimneovim
    عرض على GitHub↗9,325
  • evomap/evolverالصورة الرمزية لـ EvoMap

    EvoMap/evolver

    8,744عرض على GitHub↗

    Evolver is a self-evolving AI agent framework that uses gene expression programming to autonomously improve agent behaviors through a continuous five-step loop of scanning, selecting, mutating, validating, and solidifying. It functions as an auditable evolution system that records every mutation and selection step, and can translate natural-language problems into executable Python code for automated grading and evaluation. The framework distinguishes itself through a distributed architecture that enables multiple agents to collaborate and share learned experiences across a network. It operate

    Selects relevant Genes or Capsules at runtime by computing signal overlap and loads their full content only when needed.

    JavaScripta2aagent-evolutionagent-framework
    عرض على GitHub↗8,744
  • feast-dev/feastالصورة الرمزية لـ feast-dev

    feast-dev/feast

    6,727عرض على GitHub↗

    Feast is an open-source feature store for machine learning that provides a central platform for defining, storing, and serving features across both training and inference workflows. It operates as a declarative system where feature definitions are written as code in Python files, synchronized to a central registry, and made available for low-latency online retrieval or point-in-time correct historical joins for training datasets. The project abstracts storage behind a pluggable architecture, allowing offline and online backends to be swapped without changing retrieval logic, and coordinates ma

    Pre-loads heavy resources like models and lookup tables at server startup to reduce per-request overhead.

    Pythonbig-datadata-engineeringdata-quality
    عرض على GitHub↗6,727
  • zplug/zplugالصورة الرمزية لـ zplug

    zplug/zplug

    6,033عرض على GitHub↗

    zplug هو مدير إضافات لـ Zsh shell مصمم لتثبيت وتنظيم إضافات المجتمع، والسمات، والأوامر من المستودعات البعيدة والمسارات المحلية. يركز على قابلية إعادة إنتاج البيئة من خلال إعدادات ذات إصدارات، مما يسمح بتثبيت الإضافات على فروع git أو علامات أو تجزئات التزام محددة. يعمل المشروع على تحسين سرعة بدء تشغيل shell باستخدام نظام تحميل كسول يؤجل تنفيذ الإضافات حتى تصبح مطلوبة صراحةً. لتسريع إعداد البيئة الأولي، يستخدم مثبتاً متوازياً يقوم بتنزيل امتدادات متعددة في وقت واحد. يدعم المدير التثبيت متعدد المصادر ويتعامل مع حل تبعية الامتدادات لضمان تحميل الحزم المطلوبة بالترتيب الصحيح. كما يتضمن قدرات لتنزيل القطع الأثرية الثنائية الخارجية وتعيينها تلقائياً لمسار النظام، بالإضافة إلى تنفيذ خطافات دورة حياة مخصصة أثناء التثبيت والتحديثات.

    Implements a system to delay the activation of plugins until a specific command is first invoked, optimizing startup speed.

    Shell
    عرض على GitHub↗6,033
  • google/perfettoالصورة الرمزية لـ google

    google/perfetto

    5,558عرض على GitHub↗

    Perfetto is a platform for system-level performance tracing and analysis on Linux and Android. It combines a high-throughput trace recorder, a SQL-based query engine, and a browser-based visualizer into a single toolchain. The platform covers CPU scheduling and call-stack profiling, native and Java heap memory allocation tracking, GPU and graphics events, and system-wide counters such as CPU frequency and power consumption. The architecture decouples trace recording from offline analysis, using a compact protobuf format for event encoding and columnar storage for efficient SQL queries. The we

    Provides a library of curated query examples that users can load for trace analysis.

    C++
    عرض على GitHub↗5,558
  • opencx-labs/copilotالصورة الرمزية لـ opencx-labs

    opencx-labs/copilot

    5,113عرض على GitHub↗

    Copilot هي منصة دعم عملاء ذاتية الاستضافة تستخدم نماذج لغوية كبيرة وقواعد معرفة متجهة (vectorized) لأتمتة مساعدة المستخدم. يتكون النظام من أداة دردشة ذكاء اصطناعي قابلة للتضمين لتكامل الموقع، ولوحة تحكم إدارة حاوية، وقاعدة معرفة بقاعدة بيانات متجهة. تتضمن المنصة منسق API يعالج مواصفات API المهيكلة، مما يسمح للنماذج اللغوية بالتفاعل مع نقاط النهاية والعمليات الخارجية. ويدير سياقاً متخصصاً للاستجابات عن طريق فهرسة تعريفات API والوثائق داخل قاعدة بيانات متجهة. تغطي البنية التحتية تنسيق الخدمة الحاوية للخوادم وعمال الخلفية، والمعالجة غير المتزامنة القائمة على الطابور، وواجهة إدارية لمراقبة تفاعلات المستخدم في الوقت الفعلي. يتعامل النظام أيضاً مع ترحيلات مخطط قاعدة البيانات وفهرسة المعرفة.

    Injects structured API definitions as context into the language model to enable automated interaction with external operations.

    TypeScriptai-copilotcopilotllm
    عرض على GitHub↗5,113
  • vudovn/antigravity-kitالصورة الرمزية لـ vudovn

    vudovn/antigravity-kit

    4,979عرض على GitHub↗

    Antigravity-kit is a multi-agent orchestrator and routing engine designed to coordinate specialized large language model agents. It functions as a conversational workflow automation tool and a context management system that executes complex tasks through a chat interface. The system utilizes a routing engine to classify user requests and dispatch them to domain-expert agents. It employs a multi-agent orchestration model that allows specialist workers to operate in parallel and combine their outputs. To manage operational efficiency, the kit includes a memory layer for storing project convent

    Fetches detailed operational instructions only when specific capabilities are triggered to reduce token overhead.

    TypeScript
    عرض على GitHub↗4,979
  • kiln-ai/kilnالصورة الرمزية لـ kiln-ai

    kiln-ai/kiln

    4,910عرض على GitHub↗

    Kiln is an LLM development workbench and evaluation framework designed for designing, testing, and optimizing prompts and AI agents. It functions as a multi-agent orchestrator and a RAG optimization tool, providing a visual interface for the iterative development of AI systems. The project distinguishes itself through a comprehensive fine-tuning pipeline that supports zero-code model training and reasoning distillation. It enables the creation of hierarchical multi-agent systems where specialized actors coordinate via tool calling, and it implements a Model Context Protocol server to expose t

    Defines reusable instructions and reference documents that are loaded into agent context only when needed.

    Python
    عرض على GitHub↗4,910
  • tencentcloudadp/youtu-agentالصورة الرمزية لـ TencentCloudADP

    TencentCloudADP/youtu-agent

    4,576عرض على GitHub↗

    Youtu Agent is an open-source framework for building, running, and evaluating autonomous agents powered by large language models. It provides the core infrastructure for creating agents that follow reasoning loops, use toolkits, and coordinate with other agents to solve complex tasks, all managed through YAML-driven configuration files. The framework distinguishes itself through its support for multi-agent orchestration, where a planner agent decomposes tasks and coordinates specialized worker agents, and through its integration with the Model Context Protocol for connecting to external toolk

    Provides modular skill files that extend agent capabilities with structured instructions for complex tasks.

    Pythonagent-frameworkagentsopenai-agents
    عرض على GitHub↗4,576
  • jwiegley/use-packageالصورة الرمزية لـ jwiegley

    jwiegley/use-package

    4,465عرض على GitHub↗

    هذا المشروع هو إطار عمل تعريفي ولغة خاصة بالمجال لإدارة حزم Emacs Lisp. يعمل كمحسن لأداء بدء التشغيل من خلال تجميع تثبيت الحزمة، وإعدادات المتغيرات، وربط المفاتيح في كتل واحدة لتقليل وقت التمهيد الأولي. يتميز النظام من خلال إطار عمل تحميل مؤجل يؤخر تنفيذ الحزمة حتى يتم تشغيل مفاتيح أو خطافات أو أوضاع محددة. ويستخدم بناء جملة إعلان قائم على الماكرو لتنظيم التكوين وأتمتة توليد التحميل التلقائي، مما يضمن تحميل الحزم فقط عند الحاجة إليها فعلياً. يغطي المشروع مجالات قدرة واسعة بما في ذلك تثبيت الحزمة التلقائي من الأرشيفات البعيدة، وإدارة التبعية، والتحميل المشروط بناءً على نظام التشغيل أو البيئة. كما يوفر تعيين لوحة مفاتيح شامل للاختصارات والأوتار، بالإضافة إلى أدوات لتحليل إحصائيات التحميل وتعديل شاشات وضع الخط.

    Provides a system that delays the activation of packages until a specific command, hook, or mode is triggered.

    Emacs Lispautoloaddeferred-loadingemacs
    عرض على GitHub↗4,465
السابق12التالي
  1. Home
  2. Software Engineering & Architecture
  3. Project Context Managers
  4. On-Demand Context Loading

استكشف الوسوم الفرعية

  • Context Pre-loading2 وسوم فرعيةInjection of relevant background information into the prompt prior to query processing. **Distinct from On-Demand Context Loading:** Distinct from on-demand loading: focuses on the proactive injection of context to ensure informed initial responses.
  • Curated Query ExamplesA library of pre-built query graph configurations that users can load from the application. **Distinct from Context Pre-loading:** Distinct from Context Pre-loading: provides curated, reusable query configurations rather than injecting background context into prompts.
  • Deferred Plugin LoadingMechanisms for delaying the activation of plugins until a specific command or event is triggered. **Distinct from On-Demand Context Loading:** Specifically targets editor plugin activation rather than operational instructions or context fetching.
  • Skill Files1 وسم فرعيModular, domain-specific instruction files loaded into an agent's context to guide complex task execution. **Distinct from On-Demand Context Loading:** Distinct from On-Demand Context Loading: focuses on loading structured skill files for agent capabilities, not general context or data subsets.
  • Tiered Abstraction LoadingStrategies for loading content in levels of granularity, from abstracts to full details, to optimize token usage. **Distinct from On-Demand Context Loading:** Focuses on hierarchical data granularity (abstract/overview/detail) rather than lazy-loading of instructions.