Awesome GitHub RepositoriesShared Memory Management

Lobe Chat is a self-hosted AI platform that provides a web-based interface for interacting with multiple large language models. It functions as an AI agent orchestrator, allowing for the design, scheduling, and management of autonomous agent teams to perform operational tasks. The platform features an extensible plugin framework and SDK to integrate external tools and custom function calls into workflows. It utilizes a provider-agnostic model layer to unify various AI APIs and includes a context-aware memory system to store structured user information for personalized interactions. The syste

Graphify is a knowledge retrieval system that transforms directories of source code and documentation into structured, queryable project maps. It utilizes a code-to-graph parser to extract technical metadata and system connectivity, converting a mix of code, SQL schemas, and documentation into a unified graph structure. The project distinguishes itself by integrating these knowledge graphs with AI coding assistants through a Model Context Protocol server and dedicated tool hooks. This allows AI agents to perform lookups and impact analysis on node neighbors and shortest paths to understand ho

Nginx is a high-performance HTTP server and reverse proxy designed to handle high-concurrency traffic through an efficient, event-driven architecture. It functions as a versatile traffic management gateway and content delivery accelerator, providing the infrastructure necessary to route client requests, balance loads across backend servers, and serve static assets with minimal resource consumption. The project distinguishes itself through a master-worker process model that separates configuration management from request processing, ensuring stable operations under heavy load. Its modular requ

Nanoclaw is an LLM agent orchestrator and multi-platform chat gateway designed to deploy and manage isolated AI agents. It provides a containerized runtime that executes agents within sandboxed Linux containers, ensuring filesystem and state isolation through dedicated workspaces and host bind-mounts. The project distinguishes itself through a unified routing pipeline that connects agents to diverse messaging platforms, including WhatsApp, Discord, Slack, Telegram, Signal, and iMessage. It integrates the Model Context Protocol to extend agent capabilities via managed external data and functio

Envoy is a high-performance, cloud-native service proxy designed for service-to-service communication in distributed architectures. It functions as a service mesh data plane, providing a centralized mechanism for managing, securing, and observing network traffic between microservices. The project is distinguished by its ability to perform dynamic traffic management and configuration updates in real-time without requiring service restarts or downtime. It utilizes a non-blocking, event-driven architecture to handle high-concurrency connections and supports hot-restart process management, which

This project is a machine learning array framework and tensor computation library designed for high-performance numerical computing. It provides a comprehensive suite of tools for constructing and training neural networks, featuring an automatic differentiation engine that facilitates gradient-based optimization and complex mathematical modeling. The library distinguishes itself through a unified memory architecture that allows data to be shared across CPU and GPU devices without explicit copies, significantly reducing data movement overhead. Its execution model relies on a lazy evaluation en

This project is a comprehensive, community-maintained knowledge base and toolkit designed for competitive programming. It serves as a centralized repository for algorithmic theory, data structures, and mathematical techniques, providing a structured reference for informatics and collegiate programming competitions. The project distinguishes itself by integrating educational content with a robust suite of automation utilities. It provides a complete workflow for competitive programming, including tools for automated test case generation, solution verification, and direct interaction with onlin

simdjson is a high-performance JSON parser that utilizes SIMD instructions to process gigabytes of data per second. It functions as a SIMD JSON parser, a multithreaded NDJSON processing library, a UTF-8 validation engine, and a tool for JSON minification and string building. The project focuses on high-throughput data processing, enabling the ingestion of massive JSON volumes and the verification of UTF-8 encoding standards. It includes dedicated capabilities for constructing JSON strings with optimized memory usage and removing unnecessary whitespace from documents to reduce file size. The

AgentMemory is a persistent knowledge store and memory server designed to provide AI coding agents with long-term memory. It functions as a knowledge graph engine and vector database store that saves and recalls project context, architectural decisions, and patterns across different sessions. The system distinguishes itself by using a tiered-memory consolidation pipeline that compresses raw observations into episodic, semantic, and procedural layers to optimize token usage. It employs a hybrid retrieval strategy combining keyword matching, vector embeddings, and graph traversal to surface rel

This project provides a framework for managing multi-agent systems, designed to automate complex software development, infrastructure, and business workflows. It functions as a multi-agent workflow orchestrator that routes tasks to domain-specific workers while maintaining state persistence and infrastructure automation. By leveraging large language models, the system decomposes high-level objectives into actionable plans, ensuring that complex operations are executed with consistency and reliability. The framework distinguishes itself through its hierarchical agent registry and policy-driven

This platform is a modular, metadata-driven framework designed for building custom business applications and data management systems without traditional coding. It functions as a low-code environment where data models, user interfaces, and business logic are defined through visual configurations rather than hardcoded views. The architecture supports multi-tenant isolation, allowing multiple independent applications to run within a single shared memory space while maintaining strict logical separation of data and configurations. What distinguishes this system is its deep integration of artific

Letta is a framework for building, deploying, and managing autonomous AI agents that maintain persistent state across long-term interactions. It provides a comprehensive suite of primitives for defining agents with configurable personas, modular memory blocks, and tool-use capabilities, enabling them to retain user preferences and conversation history over extended sessions. The platform distinguishes itself through its advanced memory management and orchestration capabilities. It allows agents to autonomously update their own memory, perform retrieval-augmented generation, and coordinate com

Frida is a dynamic binary instrumentation toolkit that provides a framework for deep process introspection and live application state manipulation. It enables the injection of custom scripts into running processes to trace function calls, modify memory, and analyze application behavior in real-time across diverse operating systems and processor architectures. The project distinguishes itself by embedding a high-performance JavaScript engine directly within the target process, allowing for the execution of user-defined logic for real-time inspection. It utilizes instruction-level hooking to re

Triton is a parallel computing framework and high-level programming language designed for writing custom compute kernels. It functions as a deep learning compiler, translating complex mathematical operations into high-throughput instructions that maximize hardware utilization and memory efficiency on graphics processing units. The framework distinguishes itself through a hardware-agnostic compute abstraction that allows developers to define kernels without manual low-level tuning. It employs just-in-time compilation to generate optimized binary instructions at runtime, utilizing static data f

FlameGraph is a performance profiling and visualization toolkit designed to identify bottlenecks in software execution. It functions as a processing engine that transforms raw stack trace samples into interactive, hierarchical diagrams. By representing aggregated execution frequency as nested rectangles, the tool allows developers to visualize hot code paths and analyze system behavior across both kernel and user-space environments. The project distinguishes itself through its ability to perform differential profile analysis, which highlights performance regressions or improvements by compari

This is a comprehensive library of code examples and reference implementations for building cross-platform user interfaces with Flutter. The project provides a collection of demo applications and guides designed to illustrate the implementation of design patterns, animation techniques, and testing workflows. The repository features specific demonstrations for native integration, including examples of embedding modules into existing native applications, using platform channels, and bridging native code with the framework. It also serves as an animation reference, providing implementations for

Swoole is a coroutine-based concurrency library and IO framework for PHP. It provides a system for building high-performance network servers and applications by bringing asynchronous, event-driven, and coroutine-based concurrency to the PHP runtime. The project distinguishes itself by implementing user-space coroutine scheduling and non-blocking IO interception, which transforms standard blocking network and file operations into asynchronous actions. It further enables high-speed data exchange across multiple PHP processes through shared memory management and specialized data structures. The

Sanic is an asynchronous Python web framework designed for building high-performance APIs and services. It operates as a production-ready ASGI web server, utilizing a non-blocking event loop to handle concurrent requests and maximize throughput. The framework is built to support scalable architectures, offering built-in worker process management to distribute traffic across available CPU cores. What distinguishes Sanic is its focus on modularity and developer-centric tooling. It features a blueprint-based system for organizing complex applications into pluggable components, alongside a robust

The Disruptor is a lock-free inter-thread messaging library and high-performance event bus. It implements a concurrent ring buffer designed for high-concurrency and low-latency message sequencing. The project utilizes a specific messaging architecture to eliminate lock contention, enabling high-throughput event routing and the exchange of continuous event streams between threads. It ensures strict first-in-first-out ordering and immediate data visibility across processing threads. The library provides capabilities for lock-free data streaming, sequential data ordering, and sequence-based eve

The Rust Programming Language Book is the official technical guide and educational resource for the Rust language. It provides a comprehensive walkthrough of the language's design, focusing on its core identity as a systems programming language that enforces memory safety and high-performance execution without the need for a garbage collector. The project is distinguished by its focus on ownership, borrowing, and lifetime tracking, which allow the compiler to verify memory safety and thread safety at compile time. It covers the language's unique approach to zero-cost abstractions, including t