Awesome GitHub RepositoriesState Checkpointing

gstack is an AI agent framework and development workflow system designed to automate the software development lifecycle. It coordinates specialized AI personas to manage tasks across product design, engineering management, and quality assurance, transforming product intent into technical specifications and final releases. The project is distinguished by its deep integration of headless browser automation and semantic code memory. It utilizes a persistent Chromium daemon for web scraping and visual auditing, and implements a searchable knowledge base that logs architectural decisions and repos

TradingAgents is an autonomous financial research and simulation framework that coordinates specialized agents to analyze market data and execute investment strategies. The system functions as a multi-agent debate environment where independent units critique financial insights through structured, adversarial reasoning to improve decision accuracy and mitigate investment risks. The platform distinguishes itself through a risk-gated transaction pipeline that validates all proposed financial actions against market volatility and liquidity constraints before execution on a simulated exchange. To

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

Deepagents is an LLM agent orchestration platform and stateful application server designed for deploying and managing AI agents built with computational graphs. It provides a containerized runtime environment that handles agent execution, state persistence, and the versioning of AI assistants. The platform distinguishes itself through deep integration with the Model Context Protocol, allowing agents to function as servers that expose tools and capabilities to external clients. It features a sophisticated observability suite for capturing execution traces, performing LLM-based evaluations agai

LangChain.js is a framework for building, executing, and monitoring stateful agentic applications. It provides an orchestration engine that models workflows as directed graphs, allowing developers to connect language models, data sources, and external tools into modular, multi-step processes. The platform distinguishes itself through its focus on stateful execution and human-in-the-loop control. It manages agent lifecycles by persisting execution state across threads, enabling fault tolerance and the ability to pause workflows at designated breakpoints for manual review or modification. This

This project is a secure container runtime that provides strong isolation for application workloads by implementing a userspace kernel. By intercepting system calls and executing them within a memory-safe, restricted environment, it minimizes the attack surface exposed to the host kernel. It functions as a drop-in engine for standard container orchestration platforms, ensuring compatibility with industry-standard runtime specifications while maintaining a hardened execution boundary. The runtime distinguishes itself through its ability to virtualize core system resources, including an indepen

This project is a collection of educational resources and reference implementations for the Apache Flink stream processing framework. It provides a learning resource focused on mastering distributed stream processing through implementation guides, performance tuning tutorials, and practical examples. The repository features detailed walkthroughs for building real-time data pipelines using the DataStream and Table APIs. It includes specific integration examples for connecting Apache Flink with Kafka brokers and Elasticsearch indices, as well as reference implementations for real-time deduplica

John is a command-line security utility designed for password strength auditing and cryptographic hash recovery. It functions as a professional tool for identifying weak user credentials and recovering access to protected files, archives, and private keys across various operating systems, databases, and applications. The software distinguishes itself through a high-performance architecture that utilizes processor-level vector instructions to perform parallel cryptographic operations. It incorporates a rule-based mutation engine that transforms dictionary words into complex candidates based on

This project is a comprehensive suite of AI tools and frameworks, featuring an LLM multi-agent orchestrator, an autonomous agent runtime, and a stateful application framework. It provides the infrastructure to build and manage specialized AI agents capable of coordinating complex tasks through graph-based workflows and shared state. The system is distinguished by its implementation of the Model Context Protocol, allowing for standardized resource discovery and communication between AI clients and servers. It further includes an AI-powered documentation generator designed to analyze source cod

Metaflow is a Python machine learning framework and MLOps workflow orchestrator designed to manage the lifecycle of data pipelines from local prototyping to production. It serves as a distributed compute manager and an experiment tracking system, enabling the creation of reproducible pipelines that transition between development and high-availability production environments. The framework distinguishes itself through an integrated checkpointing system that automatically persists intermediate data artifacts to remote storage, allowing failed runs to be resumed from the last successful step. It

Skill Seekers is a toolset for generating large language model knowledge bases, featuring a multi-source content scraper and a dedicated RAG data pipeline. It extracts technical data from documentation, code, and video to create structured assets and configuration files for AI-powered IDE extensions. The project distinguishes itself through the ability to transform raw data into polished tutorials and specialized skills for AI plugin marketplaces. It utilizes abstract syntax tree parsing and optical character recognition to analyze GitHub repositories, PDFs, and video frames, converting these

This is a Raft consensus library and distributed consensus engine implemented in Go. It provides the primitives necessary to build fault-tolerant distributed services by implementing a replicated state machine that ensures a group of servers agree on a shared system state through leader election and log replication. The project distinguishes itself through a pluggable architecture for storage backends and snapshot storage, decoupling the consensus logic from physical persistence. It includes specialized mechanisms for leadership transfer, protocol version management to support rolling upgrade

The agent-framework is an LLM agent orchestration framework and multi-agent workflow engine designed for building autonomous AI agents. It provides a tool integration layer for binding external functions, APIs, and sandboxed code as executable tools for language models. The framework distinguishes itself through a graph-based system for designing sequential and parallel task flows, featuring state management and checkpointing for long-running processes. It implements comprehensive conversational state management and an observability suite that uses telemetry to trace execution flows and monit

reconftw is an attack surface management framework and reconnaissance workflow orchestrator designed to automate the discovery, mapping, and monitoring of external digital assets. It operates as a modular tool-chain pipeline that coordinates a sequence of security tools to perform intelligence gathering and vulnerability scanning. The project distinguishes itself through a cloud-native deployment model that parallelizes scanning workloads across a fleet of remote VPS instances to bypass local resource constraints. It utilizes container-based environment isolation to ensure consistent executio

FASTER is a high-throughput key-value store that combines an in-memory data store with a hybrid memory-disk storage engine, enabling datasets larger than available RAM. It uses a latch-free, cache-optimized index for concurrent point lookups and heavy updates, and records all mutations to a persistent append-only log on disk with checksum validation and group-commit checkpointing for crash recovery. The system supports multi-key transactional workloads through atomic multi-key locking, ensuring transactional consistency without coarse-grained contention. It exposes the key-value store to remo

Open Multi-Agent is a TypeScript framework for multi-agent orchestration that decomposes natural language goals into a runtime-generated directed acyclic graph of tasks. It functions as a task orchestrator and workflow state manager, coordinating multiple AI models to execute parallel and sequential operations. The framework is distinguished by a proposer-judge consensus protocol used to validate agent outputs through a quorum of agreement. It employs provider-agnostic model routing to assign specific models to tasks based on roles or execution phases and utilizes state-based workflow checkpo

PraisonAI is an autonomous AI agent platform that coordinates multiple LLM-powered agents for research, planning, and execution of complex workflows. It functions as a multi-agent orchestration framework, a workflow builder, and a Model Context Protocol server, while also providing retrieval-augmented generation through vector knowledge bases. Agents can interact via CLI, web, or standardized protocols with sandboxed code execution. The platform distinguishes itself with a rich set of agent communication protocols, including A2A, REST, WebSocket, voice and telephony integration, and MCP, allo

re-frame este un framework funcțional pentru construirea de aplicații single-page în ClojureScript. Acesta oferă o bază de date centralizată și imutabilă care servește drept unică sursă de adevăr pentru întreaga stare a aplicației, impunând un flux de date unidirecțional strict, unde evenimentele declanșează tranziții de stare și actualizări ulterioare ale vizualizărilor. Framework-ul se distinge printr-un graf de semnale reactive și un pipeline de middleware bazat pe interceptoare. Tratând logica aplicației ca pe o secvență de evenimente bazate pe date și efecte secundare declarative, acesta decuplează logica de business de stratul de vizualizare. Această arhitectură permite dezvoltatorilor să gestioneze tranziții complexe de stare și operațiuni externe prin funcții pure, asigurându-se că efectele secundare sunt executate de un interpretor separat, nu prin apeluri imperative. Sistemul include o suită cuprinzătoare de capabilități pentru gestionarea arhitecturii aplicației, inclusiv derivarea reactivă a datelor, reconcilierea vizualizărilor bazată pe abonamente și gestionarea stării bazată pe evenimente. Suportă fluxuri de lucru avansate, cum ar fi trasarea evenimentelor, checkpoint-uri de stare și capacitatea de a simula (stub) efecte secundare pentru testare izolată. Proiectul este conceput pentru integrarea cu React, utilizând reconcilierea virtual DOM pentru a actualiza eficient interfețele utilizator. Oferă un set robust de utilitare pentru gestionarea problemelor transversale, gestionarea grafurilor complexe de flux de date și coordonarea operațiunilor asincrone într-un pipeline de evenimente secvențial și predictibil.

Acest proiect este o colecție de cursuri de deep learning în PyTorch, constând în proiecte practice și exerciții de programare. Se concentrează pe implementarea arhitecturilor de rețele neuronale și antrenarea modelelor pentru a rezolva probleme complexe de date. Repository-ul include o suită de proiecte de computer vision pentru construirea de clasificatori de imagini, autoencodere și aplicații de transfer de stil. Dispune de un laborator de rețele generative adversariale (GAN) pentru crearea de imagini sintetice și implementări specifice pentru transfer learning, pentru a adapta ponderile pre-antrenate la sarcini noi. Codul sursă acoperă analiza datelor secvențiale pentru procesarea limbajului natural (NLP) folosind rețele neuronale recurente și word embeddings. Capabilitățile suplimentare includ preprocesarea datelor de imagine, evaluarea performanței modelelor și deployment-ul modelelor antrenate în infrastructuri cloud. Materialele sunt livrate sub forma unei serii de Jupyter Notebooks.