awesome-repositories.com
Blog
MCP
awesome-repositories.com

Découvrez les meilleurs dépôts open-source grâce à notre recherche par IA.

ExplorerRecherches sélectionnéesAlternatives open sourceLogiciels auto-hébergésBlogPlan du site
ProjetÀ proposNotre méthodologiePresseServeur MCP
Mentions légalesConfidentialitéConditions d'utilisation
© 2026 Bringes Technology SRL·VAT RO45896025·hello@awesome-repositories.com
·
panaversity avatar

panaversity/learn-agentic-ai

0
View on GitHub↗

Learn Agentic Ai

This project is an educational curriculum and architectural framework for building autonomous AI agents and multi-agent systems. It provides a structured learning path focused on the development of independent software components capable of planning, executing tasks, and utilizing external tools to achieve high-level goals.

The framework emphasizes multi-agent system orchestration through distributed architectures where specialized agents collaborate using standardized communication protocols. It details specific design patterns such as dual-memory systems for maintaining short-term plans and long-term history, as well as evaluator-optimizer loops for iterative output refinement.

The project covers a broad range of technical capabilities, including retrieval augmented generation with knowledge graph grounding, the implementation of safety guardrails and human-in-the-loop oversight, and the use of stateful actor models. It also addresses the operational side of AI, including containerized deployment via Kubernetes and the management of machine-to-machine payments.

The materials are delivered as a series of technical guides and courses, utilizing Jupyter Notebooks for practical implementation.

Features

  • Autonomous AI Agent Frameworks - Provides a framework for building self-directed agents that decompose high-level goals into executable plans.
  • AI Agent Curricula - Offers a structured educational curriculum and code samples for learning agentic design and autonomous system development.
  • Hybrid Short-and-Long Term Memory - Implements a dual-memory architecture separating working memory for planning from long-term historical storage.
  • Agentic Workflow Orchestration - Coordinates complex, long-running processes by delegating tasks to autonomous agents.

Recherche par IA

Explorez plus de dépôts awesome

Décrivez vos besoins en langage naturel — l'IA classe des milliers de projets open source sélectionnés par pertinence.

Start searching with AI
3,908 stars·901 forks·Jupyter Notebook·mit·7 vues
  • Agent Collaboration Protocols - Facilitates direct collaboration and task delegation between agents using standardized messaging protocols.
  • Agent-to-Agent Communication - Standardizes interaction and collaboration between diverse agents through dedicated communication protocols.
  • Agent Discovery - Locates suitable agents within a deployment environment using intent-based queries and knowledge graphs.
  • Agent Metadata Resolvers - Implements metadata resolvers to identify available agent skills and services via standardized endpoints.
  • Agent Skill Frameworks - Filters and selects agents based on specific capability identifiers to ensure the correct tool is chosen for a task.
  • AI Agent Capabilities - Defines agents with specific instructions, safety guardrails, and capabilities to invoke external functions.
  • AI Agent Orchestrators - Decomposes high-level intents into subtasks assigned to a hierarchy of domain-specific specialized agents.
  • Agent Tool Definitions - Provides detailed specifications for agent tools, including required inputs, outputs, and operational constraints.
  • Model Context Protocol - Implements a standardized protocol for models to access local data sources and external tools for improved context.
  • Agentic Workflow Automation - Structures AI tasks using prompt chaining, routing, and self-correction loops for complex business processes.
  • AI Agent Development - Provides a framework for developing autonomous software components that manage their own lifecycles and interact via natural language.
  • AI Guardrails - Defines policy rules and behavioral constraints to ensure autonomous agent behavior remains safe and unbiased.
  • Agent Governance - Provides safety guardrails, action whitelists, and human-in-the-loop escalation to ensure operational boundaries.
  • Cloud-Native Deployments - Teaches container and Kubernetes orchestration for AI workloads to ensure resilient production environments.
  • Evaluator-Optimizer Loops - Employs evaluator-optimizer loops where one agent generates solutions and another provides iterative feedback for refinement.
  • Composable Agentic Architectures - Constructs complex agentic systems using modular patterns including prompt chaining and parallelization.
  • Conversation State Management - Maintains interaction history across multiple requests to enable seamless, stateful dialogue without resending full context.
  • Retrieval-Augmented Generation - Implements retrieval augmented generation to ground model responses in external knowledge bases and factual context.
  • Function Calling Interfaces - Implements systems that enable language models to execute external tools and API functions to extend their capabilities.
  • Human-in-the-Loop Workflows - Routes low-confidence decisions to a human dashboard for approval before resuming automated workflows.
  • Multi-Agent Orchestration - Provides a framework for decomposing and delegating complex tasks across a team of specialized autonomous agents.
  • Multi-Agent Orchestration Frameworks - Provides an architectural framework for coordinating and managing the collaboration of multiple intelligent agents.
  • Multi-Agent Orchestration Systems - Implements platforms for coordinating multiple autonomous agents to execute complex, collaborative workflows using standardized protocols.
  • Multi-Agent Systems - Develops scalable AI systems using a distributed architecture where agents function as stateful actors.
  • Tool-Using Agents - Enables agents to trigger specific functions by matching request parameters with available capabilities through reasoning.
  • Interaction Protocols - Provides open protocols that serve as a universal language for models to interact with external tools.
  • Factual Grounding - Integrates graph databases with language models to provide factual grounding and reduce hallucinations through structured data.
  • Agent Memory Management - Implements systems for storing and retrieving historical context and reasoning traces to maintain interaction continuity.
  • AI Agent Deployments - Packaging and deploying multi-modal AI agents to Kubernetes clusters to ensure efficient scaling.
  • Token Authentication - Implements token and API key authentication to verify agent identity and authorize requests.
  • Skill Permissions - Defines authorization levels and security requirements for individual agent capabilities to restrict sensitive access.
  • AI Agent Security - Secures autonomous agents using transport-layer encryption and role-based access controls to protect data exchange.
  • Actor Models - Architects agents as stateful actors that manage their own lifecycle and state within a distributed system.
  • Client Initializations - Automates the creation of communication clients from discovered URLs to establish managed agent connections.
  • Agent Deployment - Provisions and deploys new agents using declarative specifications or natural-language prompts.
  • Operational Self-Healing - Provides autonomous operations capabilities to monitor system health and patch configurations to resolve anomalies.
  • Agentic Browser Controllers - Bridges autonomous agents to web browser elements using automation APIs as a foundation for reasoning.
  • Agentic Integration Interfaces - Develops standardized protocols and hooks to connect agents with external tools through defined parameters.
  • Model Provider Integrations - Offers unified interfaces for connecting and configuring various AI model providers supporting the Chat Completions API.
  • Web Workflow Automations - Implements automated sequences that translate natural language goals into concrete browser actions like clicking and navigation.
  • Custom AI Assistant Development - Enables the creation of personalized AI assistants by combining specific personas with integrated tools and low-code workflows.
  • External Service Integrations - Connects agents to external databases and services using a standardized protocol to maintain interaction context.
  • External Tool Integrations - Provides a uniform server-client interface for agents to discover and invoke external resources and utilities.
  • Self-Correction Loops - Integrates reflection and monitoring to detect failures and automatically replan or retry tasks.
  • Agent Response Streams - Streams agent responses and tool results asynchronously in real-time to handle long-running tasks.
  • Agent State Persistence - Implements mechanisms for storing and retrieving agent sessions and internal context across execution turns for persistent memory.
  • Knowledge Graphs - Uses graph-based structures to map semantic relationships between entities for grounding AI agents in structured data.
  • Graph Querying - Provides tools and declarative pattern matching for traversing and querying complex connected data structures.
  • LLM-to-Structured Data Converters - Transforms free-form AI responses into structured JSON data and function calls using defined explicit schemas.
  • Evaluator-Optimizer Loops - Employs an evaluator-optimizer pattern where separate agents generate and refine solutions iteratively.
  • Automated Software Delivery - Implements CI/CD pipelines and GitOps workflows to automate the delivery of agent applications.
  • Cloud Native Application Development - Provides frameworks for building cloud-native applications designed for scalability and resilience within a cluster.
  • Containerized Application Runtimes - Packages AI applications into portable container images using multi-stage builds for consistent execution environments.
  • Containerized Deployment Orchestration - Utilizes containerized deployment orchestration to ensure scalable and resilient execution of AI agents.
  • Kubernetes Application Deployments - Implements automated workflows for deploying containerized agent workloads and Helm charts into Kubernetes clusters.
  • LLM Hosting - Provides guidelines for hosting and operating large language models on private infrastructure for data control.
  • RAG Implementation Guides - Provides educational resources and step-by-step guides for building retrieval-augmented generation systems using graph databases.
  • Agent-to-Agent JSON-RPC - Standardizes data exchange between distributed agent systems using JSON-RPC streaming over HTTP.
  • Pub-Sub Messaging - Uses a publish-subscribe messaging model to decouple agent communication for asynchronous real-time interactions.
  • Event-Driven AI Runtimes - Utilizes a publish-subscribe model to enable real-time, asynchronous reactions to agent events.
  • Microservices Design Patterns - Implements architectural patterns for decomposing agent systems into microservices with service discovery and messaging.
  • AI Pipeline Compositions - Combines autonomous agents into higher-level services to prototype and deploy complex AI solutions.
  • Agent Performance Monitoring - Tracks quantitative reliability metrics including task completion rates and tool-use accuracy.
  • AI Agent Execution Monitors - Provides integrated tracing to visualize and debug the flow of agent actions for performance optimization.
  • Distributed Tracing - Uses distributed tracing to track function calls and interactions across networks to diagnose logic flows.
  • AI Agent Behavior Monitors - Provides mechanisms to measure task performance and reasoning processes using benchmarks and simulated conversations.
  • Agent Testing Suites - Provides automated testing suites to validate agent behavior and the reliability of agentic workflows.
  • Educational Agent Projects - Comprehensive learning repository for mastering agentic AI concepts.

    • Historique des stars

    Graphique de l'historique des stars pour panaversity/learn-agentic-aiGraphique de l'historique des stars pour panaversity/learn-agentic-ai

    Questions fréquentes

    Que fait panaversity/learn-agentic-ai ?

    This project is an educational curriculum and architectural framework for building autonomous AI agents and multi-agent systems. It provides a structured learning path focused on the development of independent software components capable of planning, executing tasks, and utilizing external tools to achieve high-level goals.

    Quelles sont les fonctionnalités principales de panaversity/learn-agentic-ai ?

    Les fonctionnalités principales de panaversity/learn-agentic-ai sont : Autonomous AI Agent Frameworks, AI Agent Curricula, Hybrid Short-and-Long Term Memory, Agentic Workflow Orchestration, Agent Collaboration Protocols, Agent-to-Agent Communication, Agent Discovery, Agent Metadata Resolvers.

    Quelles sont les alternatives open-source à panaversity/learn-agentic-ai ?

    Les alternatives open-source à panaversity/learn-agentic-ai incluent : agentscope-ai/agentscope — Agentscope is a comprehensive toolkit for developing and orchestrating autonomous multi-agent systems. It provides a… mervinpraison/praisonai — PraisonAI is an autonomous AI agent platform that coordinates multiple LLM-powered agents for research, planning, and… microsoft/ai-agents-for-beginners — This project is a structured educational resource and technical guide for designing and implementing autonomous… langroid/langroid — Langroid is a multi-agent orchestration framework and tool integration suite designed for building complex AI… fetchai/innovation-lab-examples — This project provides a comprehensive framework for building, deploying, and orchestrating autonomous agents within a… modelengine-group/nexent — Nexent is an enterprise AI control plane and LLM agent orchestration platform. It provides a zero-code environment for…

    Alternatives open source à Learn Agentic Ai

    Projets open source similaires, classés selon le nombre de fonctionnalités partagées avec Learn Agentic Ai.
    • agentscope-ai/agentscopeAvatar de agentscope-ai

      agentscope-ai/agentscope

      26,895Voir sur GitHub↗

      Agentscope is a comprehensive toolkit for developing and orchestrating autonomous multi-agent systems. It provides a unified framework for building agents that can reason, execute tools, and manage memory, enabling the creation of complex, collaborative workflows where multiple specialized agents interact to solve multi-step objectives. The platform distinguishes itself through a robust orchestration engine that supports both sequential and concurrent agent pipelines. It utilizes a centralized event bus for real-time telemetry, allowing developers to track agent reasoning, tool usage, and sys

      Pythonagentchatbotlarge-language-models
      Voir sur GitHub↗26,895
    • mervinpraison/praisonaiAvatar de MervinPraison

      MervinPraison/PraisonAI

      5,592Voir sur GitHub↗

      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

      Pythonagentsaiai-agent-framework
      Voir sur GitHub↗5,592
  • microsoft/ai-agents-for-beginnersAvatar de microsoft

    microsoft/ai-agents-for-beginners

    67,369Voir sur 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

    Jupyter Notebookagentic-aiagentic-frameworkagentic-rag
    Voir sur GitHub↗67,369
  • langroid/langroidAvatar de langroid

    langroid/langroid

    3,894Voir sur GitHub↗

    Langroid is a multi-agent orchestration framework and tool integration suite designed for building complex AI applications. It serves as a multi-modal integration layer that connects diverse local and remote language models with an agentic retrieval-augmented generation system. The project distinguishes itself through a collaborative message-exchange paradigm, allowing specialized agents to delegate tasks hierarchically and coordinate via structured communication. It features an advanced state management system for conversational AI, including the ability to rewind and prune conversation hist

    Pythonagentsaichatgpt
    Voir sur GitHub↗3,894
    • Voir les 30 alternatives à Learn Agentic Ai→