awesome-repositories.com
博客
MCP
awesome-repositories.com

通过 AI 驱动的搜索,发现最优秀的开源仓库。

探索精选搜索开源替代品自托管软件博客网站地图
项目MCP 服务器关于排名机制媒体报道
法律隐私政策服务条款
© 2026 Bringes Technology SRL·VAT RO45896025·hello@awesome-repositories.com
·

38 个仓库

Awesome GitHub RepositoriesContext-Aware Tooling

Architectural patterns for dynamically loading tools based on operational context.

Distinguishing note: Focuses on dynamic tool loading for performance optimization.

Explore 38 awesome GitHub repositories matching software engineering & architecture · Context-Aware Tooling. Refine with filters or upvote what's useful.

Awesome Context-Aware Tooling GitHub Repositories

用 AI 发现最棒的仓库。我们将通过 AI 为您搜索最匹配的仓库。
  • moeru-ai/airimoeru-ai 的头像

    moeru-ai/airi

    41,040在 GitHub 上查看↗

    Airi is an interactive digital companion engine designed to bridge large language models with local animation rendering. It functions as a middleware platform that synchronizes conversational text streams with skeletal and facial movements to drive virtual avatars in real time. The framework distinguishes itself by integrating desktop context awareness, allowing characters to maintain situational awareness of a user's screen activity across both desktop and web environments. It utilizes a hybrid execution model that splits computational workloads between cloud-based language processing and lo

    Extracts visual metadata from the user environment to provide language models with situational awareness of the active desktop.

    TypeScriptai-companionai-vtuberclawdbot
    在 GitHub 上查看↗41,040
  • sickn33/antigravity-awesome-skillssickn33 的头像

    sickn33/antigravity-awesome-skills

    40,875在 GitHub 上查看↗

    This project is an agentic workflow orchestrator and skill registry designed to extend the capabilities of coding assistants and command-line interfaces. It functions as a centralized framework for managing, distributing, and executing modular instruction sets, playbooks, and plugin bundles across diverse development and infrastructure environments. The system distinguishes itself through a declarative approach to automation, utilizing manifest-driven dependency resolution to map specific capabilities to project requirements. By employing file-system-based injection and modular bundling, it a

    Dynamically activates specific toolsets based on project requirements to minimize noise and optimize agent focus.

    Pythonagentic-skillsai-agentsantigravity
    在 GitHub 上查看↗40,875
  • zuodaotech/everyone-can-use-englishZuodaoTech 的头像

    ZuodaoTech/everyone-can-use-english

    34,948在 GitHub 上查看↗

    This project is an AI-powered English education tool and browser extension designed for immersive language learning. It functions as a proficiency training suite that integrates AI tools and linguistic analysis directly into external websites and streaming video platforms. The system employs a DOM injection model to add interactive overlays and toolbars to web pages. It uses large language model APIs to provide real-time translations and maps curated pronunciation and grammar exercises to specific timestamps in external media. The tool covers a broad range of English proficiency training, in

    Sends page metadata and media timestamps to external LLMs for real-time translation and analysis.

    TypeScript
    在 GitHub 上查看↗34,948
  • eyaltoledano/claude-task-mastereyaltoledano 的头像

    eyaltoledano/claude-task-master

    27,567在 GitHub 上查看↗

    This project is an autonomous, multi-model orchestrator designed to manage the full software development lifecycle through a command-line interface. It functions as an intelligent agent that decomposes high-level product goals into actionable, prioritized subtasks, manages dependency graphs, and executes development cycles. By automating requirement parsing, technical research, and task tracking, it maintains project alignment and momentum throughout the implementation process. The system distinguishes itself through a provider-agnostic abstraction layer that allows users to assign specific a

    Dynamically adjusts the set of active tools to optimize token usage and performance during automated operations.

    JavaScriptaicursorcursor-ai
    在 GitHub 上查看↗27,567
  • roovetgit/roo-codeRooVetGit 的头像

    RooVetGit/Roo-Code

    24,279在 GitHub 上查看↗

    Roo-Code is an editor extension and AI agent orchestrator designed to automate software engineering tasks. It functions as an LLM-powered tool that generates source code from natural language descriptions and manages autonomous agents directly within the development environment. The system distinguishes itself through the use of role-based behavioral profiles, allowing the agent to switch between personas such as Architect or Debugger to align with different project phases. It also operates as a Model Context Protocol client, connecting to external servers to expand the data sources and tools

    Dynamically assembles project snippets and file structures into prompts to provide accurate context for code generation.

    TypeScript
    在 GitHub 上查看↗24,279
  • graphiteeditor/graphiteGraphiteEditor 的头像

    GraphiteEditor/Graphite

    24,258在 GitHub 上查看↗

    Graphite is a node-based visual design environment that integrates vector illustration, raster image processing, and motion graphics generation into a single platform. It utilizes a functional reactive pipeline and a data-flow execution model to propagate state changes through a graph of interconnected nodes, allowing users to construct complex, automated design workflows. The platform distinguishes itself through a context-aware evaluation engine that injects runtime metadata—such as coordinate data and loop indices—directly into the node graph. This enables the creation of procedural geomet

    Injects runtime metadata like loop indices and coordinates into nodes to enable dynamic, position-dependent design logic.

    Rust2d-graphicsanimationart
    在 GitHub 上查看↗24,258
  • mediar-ai/screenpipemediar-ai 的头像

    mediar-ai/screenpipe

    19,337在 GitHub 上查看↗

    Screenpipe is a local screen and audio recorder that captures and indexes digital activity to create a searchable archive of computer usage. It functions as an AI context engine, providing a local database of visual and auditory history to ground large language models. The system serves as a Model Context Protocol server, delivering screen history and meeting transcriptions to external AI assistants. It utilizes an OCR screen search tool to extract text from visual data and a speech-to-text transcription tool for identifying speakers in system and microphone audio. The software includes capa

    Functions as a visual context awareness engine that grounds LLMs with a local database of visual and auditory history.

    Rust
    在 GitHub 上查看↗19,337
  • cure53/dompurifycure53 的头像

    cure53/DOMPurify

    16,638在 GitHub 上查看↗

    DOMPurify is a security-focused library designed to sanitize untrusted HTML input, preventing cross-site scripting attacks by stripping malicious code while preserving safe content. It functions as a utility for secure document object model manipulation, ensuring that user-provided rich text can be rendered safely within web applications. The library distinguishes itself through a single-pass, mutation-observer-free processing model that operates on detached document fragments to avoid triggering unintended side effects. It employs recursive node traversal and context-aware logic to inspect a

    Adapts sanitization logic dynamically to handle complex or nested HTML structures safely.

    JavaScriptcross-site-scriptingdomdompurify
    在 GitHub 上查看↗16,638
  • powerline/powerlinepowerline 的头像

    powerline/powerline

    14,770在 GitHub 上查看↗

    Powerline is a statusline and prompt generation framework designed to provide consistent visual information across terminal shells, text editors, and multiplexers. It functions as a configuration-driven customization engine that allows users to define themes, color schemes, and dynamic segment layouts to maintain a cohesive interface across diverse command-line environments. The system utilizes a persistent background daemon to manage state and rendering logic, which offloads processing tasks to minimize resource consumption and ensure high responsiveness across multiple active application in

    Adjusts visual elements dynamically by highlighting based on application modes and truncating segments when screen space is limited.

    Python
    在 GitHub 上查看↗14,770
  • espanso/espansoespanso 的头像

    espanso/espanso

    13,987在 GitHub 上查看↗

    Espanso is a cross-platform text expander and desktop automation tool that monitors system-wide keystrokes to replace short trigger keywords with longer text blocks, images, or dynamic script outputs. It functions as a background service, enabling users to automate repetitive typing tasks across any application on their local system. The tool distinguishes itself through context-aware automation, which allows users to define specific rules that enable or disable expansion behavior based on the currently active window. It also features a centralized package management system for organizing and

    Provides context-aware automation by enabling or disabling rules based on the active application.

    Rustespansolinuxmacos
    在 GitHub 上查看↗13,987
  • cheat/cheatcheat 的头像

    cheat/cheat

    13,361在 GitHub 上查看↗

    Cheat is a command-line cheatsheet manager and terminal reference tool used for creating and viewing searchable, interactive guides. It functions as a plain-text knowledge base that organizes technical notes and command snippets through a hierarchical directory structure and metadata tags. The tool provides context-aware note management by discovering and displaying project-specific documentation based on the current working directory. It allows for the creation of a personalized collection of reference files that can be retrieved directly within a shell environment to assist with command opt

    Discovers and displays the most relevant technical documentation by traversing up the current directory tree.

    Go
    在 GitHub 上查看↗13,361
  • keephq/keepkeephq 的头像

    keephq/keep

    11,938在 GitHub 上查看↗

    Keep is an open-source AIOps alert management platform that aggregates, deduplicates, and orchestrates the lifecycle of alerts from multiple monitoring tools. It functions as a multi-provider integration hub to centralize the flow of data between observability, ticketing, and communication tools. The platform distinguishes itself through incident workflow automation and AI-powered enrichment. It uses a declarative workflow engine to execute multi-step operational sequences and integrates large language models to summarize event data and correlate technical logs for faster incident resolution.

    Integrates large language models to summarize event data and correlate technical logs for automated analysis.

    Python
    在 GitHub 上查看↗11,938
  • dbcli/myclidbcli 的头像

    dbcli/mycli

    11,932在 GitHub 上查看↗

    mycli is a MySQL command line client, database administration tool, and SQL query editor. It functions as a terminal interface for executing queries and managing MySQL connections, incorporating an integrated assistant that uses large language models to generate and analyze SQL statements based on the current database schema. The tool provides specialized query authoring capabilities, including context-sensitive syntax suggestions, fuzzy-matching identifier completion for tables and columns, and the ability to handover query buffers to external system text editors. It distinguishes its connec

    Enriches LLM API payloads with the current database schema to generate and analyze context-aware SQL queries.

    Pythonauto-completiondatabasemycli
    在 GitHub 上查看↗11,932
  • github/copilot.vimgithub 的头像

    github/copilot.vim

    11,631在 GitHub 上查看↗

    This project is a Vim plugin that functions as an AI-powered coding assistant. It integrates large language models directly into the text editor to provide real-time code suggestions and function completions based on the current file context and cursor position. The plugin distinguishes itself by utilizing an asynchronous event loop to maintain editor responsiveness while communicating with remote models. It employs a virtual buffer overlay to display generated code suggestions, allowing users to preview and accept proposed changes without modifying the underlying file until explicitly confir

    Constructs structured prompts by aggregating file content and cursor metadata to provide situational awareness to remote models.

    Vim Script
    在 GitHub 上查看↗11,631
  • josstorer/chatgptboxjosStorer 的头像

    josStorer/chatGPTBox

    10,738在 GitHub 上查看↗

    chatGPTBox is a browser extension that integrates large language model chat interfaces and AI tools directly into the web browsing experience. It functions as an AI productivity toolkit and API client, allowing users to access AI assistants via a floating chat interface without leaving their active webpage. The project distinguishes itself by offering context-aware assistance and website-specific adaptations based on the current URL. It further enhances the browsing experience by displaying AI-generated responses alongside standard search engine results and providing a system to route chat re

    Uses site-specific configuration mappings to trigger tailored AI behaviors based on the current webpage URL.

    JavaScript
    在 GitHub 上查看↗10,738
  • agentskills/agentskillsagentskills 的头像

    agentskills/agentskills

    10,303在 GitHub 上查看↗

    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

    Implements a hierarchical resource organizer that loads technical references on demand to reduce LLM token usage.

    Pythonagent-skills
    在 GitHub 上查看↗10,303
  • nidhinjs/prompt-masternidhinjs 的头像

    nidhinjs/prompt-master

    9,731在 GitHub 上查看↗

    Prompt Master is an AI skill that automates prompt engineering by detecting the target AI system and applying the correct prompt architecture automatically. It generates optimized prompts for over 30 different AI tools, adapting format and syntax to each target system without requiring manual conversion. The system distinguishes itself through several integrated capabilities. It extracts missing dimensions of intent from vague requests by asking up to three targeted clarifying questions before generating a final prompt. A memory block of prior decisions and constraints is prepended to maintai

    Prepends a memory block of prior decisions and constraints so the AI does not contradict earlier work.

    claude-aiclaude-skillsllm
    在 GitHub 上查看↗9,731
  • i18next/i18nexti18next 的头像

    i18next/i18next

    8,583在 GitHub 上查看↗

    i18next is a JavaScript localization library and internationalization framework used to translate application text into multiple languages. It functions as a dynamic translation manager that handles translation resources, language detection, and the mapping of unique keys to localized strings. The system features a pluralization and interpolation engine that applies language-specific grammatical rules for numeric counts and injects dynamic variables into strings. It utilizes a plugin-based backend architecture to load and cache translation namespaces from various sources, including remote ser

    Provides the ability to retrieve different translations for the same key based on an optional context parameter.

    JavaScript
    在 GitHub 上查看↗8,583
  • yogeshojha/rengineyogeshojha 的头像

    yogeshojha/rengine

    8,472在 GitHub 上查看↗

    Rengine is an automated reconnaissance framework and vulnerability management platform designed for attack surface monitoring. It functions as a centralized hub for discovering subdomains and open ports, gathering open-source intelligence, and tracking security flaws across target networks. The system integrates large language models to analyze reconnaissance data and generate vulnerability descriptions and insights. It distinguishes itself through a plugin-based tool integration that wraps external security scanning binaries and a target mapping system that tracks changes to assets over time

    Feeds reconnaissance data into large language models to synthesize vulnerability descriptions and surface insights.

    HTMLbug-bountybugbountyhacking
    在 GitHub 上查看↗8,472
  • intitni/copilotforxcodeintitni 的头像

    intitni/CopilotForXcode

    8,240在 GitHub 上查看↗

    CopilotForXcode is an AI source editor extension for the Xcode development environment. It provides a suite of tools including a conversational chat interface, a code completion tool, and a natural language refactorer to assist with Apple platform development. The project differentiates itself by integrating project context and compiler errors directly into its AI interactions. It supports custom prompt execution using template variables and enables the triggering of shell scripts and system shortcuts directly from the chat interface to automate development tasks. The system manages AI integ

    Aggregates cursor position, file contents, and compiler errors to enrich AI prompts.

    Swiftchatchatgptcode-completion
    在 GitHub 上查看↗8,240
上一个12下一个
  1. Home
  2. Software Engineering & Architecture
  3. Context-Aware Tooling

探索子标签

  • Context-Aware Knowledge Managers2 个子标签Hierarchical resource organizers that load technical references on demand to optimize LLM token usage. **Distinct from Context-Aware Tooling:** Focuses on hierarchical knowledge organization for token reduction rather than dynamic tool loading based on operational context.
  • LLM Contextual IntegrationsArchitectures that send real-time operational context to large language models for specific analysis tasks. **Distinct from Context-Aware Tooling:** Focuses on LLM API payload enrichment rather than general tool loading for performance.
  • Linguistic Context SelectionMechanisms for selecting alternative translations based on grammatical or situational context to resolve ambiguity. **Distinct from Context-Aware Tooling:** Distinct from Context-Aware Tooling: focuses on linguistic translation variants rather than dynamic tool loading.
  • Prompt Context Aggregators2 个子标签Utilities that collect data from multiple sources to enrich LLM prompts. **Distinct from Context-Aware Tooling:** Distinct from Context-Aware Tooling: focuses on aggregating content for prompts rather than dynamically loading operational tools.
  • Runtime Metadata InjectorsArchitectural components that inject dynamic runtime context into node graphs. **Distinct from Context-Aware Tooling:** Distinct from Context-Aware Tooling: focuses on injecting metadata into a node-based execution graph rather than loading tools.
  • Sanitization ContextsAdjusts filtering logic based on the document structure to prevent bypasses in nested or malformed HTML. **Distinct from Context-Aware Tooling:** Focuses on document-structure-aware sanitization, distinct from general tool-loading context.
  • Session Lifecycle HooksTriggers for loading metadata and executing cleanup routines at the start and end of an interaction session. **Distinct from Context-Aware Tooling:** Focuses on session start/end lifecycle events rather than the dynamic loading of tools based on state.
  • Tool-Specific Rule MappingsSystems that associate development guidelines with the unique input requirements of different AI-powered programming tools. **Distinct from Context-Aware Tooling:** Distinct from Context-Aware Tooling: focuses on mapping rules to specific tool interfaces rather than dynamic tool loading.
  • Visual Adaptation EnginesSystems that dynamically adjust interface elements based on available screen space and application context. **Distinct from Context-Aware Tooling:** Distinct from Context-Aware Tooling: focuses on UI rendering and layout adaptation rather than dynamic tool loading.
  • Visual Context Awareness Engines3 个子标签Systems that extract visual metadata from the desktop to provide situational awareness to language models. **Distinct from Context-Aware Tooling:** Distinct from general context-aware tooling: focuses on visual desktop metadata extraction for LLM situational awareness.