In this blog, we will give you a brief introduction to AgentBoard, an open source AI agent visualization toolkit which can be used the same way as Tensorboard, which helps visaulize Tensors data during model training. AgentBoard aims to visualize key elements and information of AI Agents running loops in development and production stages of real-world scenarios. It provides easy logging APIs in python and can help log multiple data types such as text (prompt), tools use (function calling of LLM API), image, audio and video. With organized logging schemas, agentboard will visualize the agent-loop (PLAN -> ACT -> REFLECT -> REACT etc ), RAG (Retrieval Augumented Generation), Autonomous Agents running, Multi-Agents orchestration, etc. The rest of the blog will cover the basic data types usage, visualization of Agent Loop, Chat History, Tool Use, Functions Calling, RAG, etc.

大模型LLM 应用+AI Agents框架，为我们提供了非常便利的自动化执行任务的能力。微信公众号(订阅号)则是非常适合落地各种AI Agents的场景，我们可以利用微信公众号提供的文本、图像、语音的输入，在自己服务器上部署一套API框架，把自己感兴趣的一些对话、图文、语音等能力的API封装为Agents。这里给大家介绍一个拆箱即用的微信公众号服务端框架 Flask+tencent代码库来实现，并且会利用一个简单的金融智能助理(Finance Agent)的例子来实现一个根据用户输入来查询实时股价，并且返回给微信公众号用户的功能，支持更加复杂定制的AI Agents业务逻辑。

AI agent research have attracted a lot of attention with the rapid development of Large Language Model (LLM) and Reasoning (RL or CoT Chain of Thought) technology. Generative AI Agents use LLM to plan, act and reflect on the memories from the environment as well as the interactions from other agents, just like the environment in Stanford's Generative Agents paper "Generative Agents: Interactive Simulacra of Human Behavior". The simulation environment usually consists of a environment (Such as A Small Town) and multiple AI Agents taking actions to make plans and achieve goals. Before making plans and taking actions, agents will retrieve related information from memories, which is a list of descriptions of the timestamp and exact events, such as "2023-02-03 Someone is watching a movie...". During multi-agents simulation, each agent will have its own timeline and their actions are usually asynchronous. In this blog, we will give a review of the tools of AI Agents Visualization, especially in the situation where there are multiple agents with asynchronous actions during the simulation.