Awesome GitHub RepositoriesOn-Demand Context Loading

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

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

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

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

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

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

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

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

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

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

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

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

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

zplug 是一个 Zsh Shell 插件管理器，旨在从远程存储库和本地路径安装和组织社区插件、主题和命令。它专注于通过版本化配置实现环境可重现性，允许将插件固定到特定的 Git 分支、标签或提交哈希。 该项目通过使用延迟加载系统来优化 Shell 启动速度，该系统将插件的执行推迟到明确需要时。为了加速初始环境设置，它采用并行安装程序同时下载多个扩展。 该管理器支持多源安装并处理扩展依赖关系解析，以确保所需的包以正确的顺序加载。它还包括下载外部二进制工件并自动将其映射到系统路径的功能，以及在安装和更新期间执行自定义生命周期钩子的功能。

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

Copilot 是一个自托管的客户支持平台，使用大语言模型（LLM）和向量化知识库来自动化用户协助。该系统由用于网站集成的可嵌入 AI 聊天小部件、容器化管理仪表板和向量数据库知识库组成。 该平台包含一个 API 编排器，用于处理结构化的 API 规范，允许语言模型与外部端点和操作进行交互。它通过在向量数据库中索引 API 定义和文档来管理响应的专门上下文。 该基础设施涵盖了用于服务器和后台工作进程的容器化服务编排、基于队列的异步处理，以及用于监控实时用户交互的管理界面。该系统还处理数据库模式迁移和知识索引。

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

Kiln 是一个 LLM 开发工作台和评估框架，专为设计、测试和优化提示词（Prompt）及 AI 智能体而设计。它作为一个多智能体编排器和 RAG 优化工具，为 AI 系统的迭代开发提供了可视化界面。 该项目通过全面的微调流水线脱颖而出，支持零代码模型训练和推理蒸馏。它支持创建分层多智能体系统，其中专门的执行者通过工具调用进行协作，并实现了一个模型上下文协议（MCP）服务器，将这些智能体和检索能力作为标准化工具暴露给外部客户端。 该平台涵盖了广泛的能力，包括用于质量保证的自动化 AI 评判评分、用于训练和评估的合成数据生成，以及用于增强模型响应的混合向量-关键词检索。它还提供了用于提示词演进、追踪审计以及通过 Git 集成管理协作数据集的工具。 该工作台可通过可自托管的 REST API 和专门的 Python 库进行编程工作流执行。

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

This project is a declarative framework and domain-specific language for managing Emacs Lisp packages. It functions as a startup performance optimizer by grouping package installation, variable settings, and keybindings into single blocks to reduce initial boot time. The system distinguishes itself through a deferred loading framework that delays package execution until specific keys, hooks, or modes are triggered. It uses a macro-based declaration syntax to organize configuration and automate the generation of autoloads, ensuring packages are only loaded when they are actually required. The