bytedance/agentkit-samples

Awesome samples for Volcengine AgentKit Platform with VeADK.

What it solves

It provides a comprehensive collection of reference implementations and tutorials for developers using AgentKit, an enterprise-grade AI Agent development platform by Volcengine. It lowers the barrier to building, deploying, and operating complex intelligent agents by providing concrete examples of how to integrate various platform features.

How it works

The repository is organized by difficulty and use case, offering a tiered learning path:

  • Basic Tutorials: Simple examples covering core concepts like short-term memory and basic dialogue.
  • Use Cases: Advanced implementations demonstrating complex business logic, asynchronous tool calls, and custom plugins.
  • Integration Examples: Demonstrations of how to migrate existing projects from other frameworks (like LangChain or LangGraph) into the AgentKit Runtime.

Who it’s for

Developers looking to build enterprise AI agents using the AgentKit platform, specifically those needing practical examples for RAG, multi-agent collaboration, or multimodal capabilities.

Highlights

  • Diverse Agent Templates: Includes specialized agents for travel planning, restaurant ordering, AI coding, customer support, and store inspection.
  • Multi-Agent Orchestration: Examples of hierarchical structures, professional division of labor, and distributed agent-to-agent (A2A) communication.
  • RAG and Memory: Implementations using VikingDB for vector retrieval and managing both short-term and long-term memory.
  • Multimodal Integration: Tools for real-time voice chat and image/video generation.
  • Framework Compatibility: Native support and migration paths for LangChain, LangGraph, and Google ADK.

Related

  • Project
    NirDiamant/GenAI_Agents

    A comprehensive collection of over 50 GenAI agent tutorials and implementations, guiding developers from basic bots to complex multi-agent systems using frameworks like LangGraph and LangChain.

  • Project
    Lamatic/AgentKit

    AgentKit is an open‑source SDK that provides a catalog of 70 ready‑made “kits” (full apps, pipelines, or templates) for building, testing and deploying AI agents. Kits are defined by a simple config file, can be edited in a visual flow studio, and are shipped as Next.js apps that run server‑less. The collection covers support triage, code review, RAG chat, hiring assistants, legal/medical bots, and many other business‑focused agents, making it a turnkey platform for creating reliable, enterprise‑grade AI agents.

  • Project
    agentset-ai/agentset

    Agentset is an open-source platform for building, evaluating, and shipping production-ready RAG and agentic applications, providing end-to-end tooling from ingestion to hosting.

  • Project
    adongwanai/AgentGuide

    An open-source knowledge base and career guide for AI Agent engineering and research, providing structured learning paths and interview preparation to help users build production-grade Agent systems.

  • Project
    Shy2593666979/AgentChat

    A modern intelligent dialogue system that enables the creation and management of AI agents with multi-agent collaboration, RAG, and a three-layer memory architecture.