AI Agent Toolkit

Here we will keep track of the latest AI Agent Toolkit, including AI Agent Framework, Memory, Tool, MCP, Prompt, Context Engineering, Code, Deep Research, Eval, Benchmark, Security, Monitor, Traces and Agent Reinforcement. 🎆

Table of Contents

• AI Agent Framework
• Memory
• Prompt & Context Engineering
• Mutimodel
• Browser & Web
• MCP & Tool
• Deep Research
• Code
• Agent Reinforcement
• Eval & Benchmark
• Monitor & Traces
• Security

Project List

AI Agent Framework

Source	Description	Code	Paper
Adala	Adala is an Autonomous DAta (Labeling) Agent framework.	GitHub
Agency	A fast and minimal framework for building agent-integrated systems.	GitHub
AgentBoard	An Analytical Evaluation Board of Multi-turn LLM Agents.	GitHub
Agent Group Chat	An Interactive Group Chat Simulacra For Better Eliciting Collective Emergent Behavior.	GitHub	arXiv
Agent K	An autoagentic AGI that is self-evolving and modular.	GitHub
AgentKit	AgentKit: Flow Engineering with Graphs, not Coding.	GitHub
AgentKit	AgentKit: rapidly build high quality Agent apps.	GitHub
AgentLabs	Open-Source Universal AI Agent Frontend.	GitHub
Agent Protocol	Open interface for AI agent communication.	GitHub
Agents	An Open-source Framework for Autonomous Language Agents.	GitHub	arXiv
AgentScope	Start building LLM-empowered multi-agent applications in an easier way.	GitHub
Agentsflow	Drag & drop UI to build and run a flow of autogen AI agents.	GitHub
agentUniverse	agentUniverse is a LLM multi-agent framework that allows developers to easily build multi-agent applications.	GitHub
AgentVerse	AgentVerse is designed to facilitate the deployment of multiple LLM-based agents in various applications.	GitHub	arXiv
AIOS	LLM Agent Operating System.	GitHub
Atomic Agents	The Atomic Agents framework is designed to be modular, extensible, and easy to use.	GitHub
AutoAgents	A Framework for Automatic Agent Generation.	GitHub	arXiv
AutoGen	AutoGen is a framework that enables the development of LLM applications using multiple agents that can converse with each other to solve tasks.	GitHub	arXiv
AutoGPT	Build & Use AI Agents.	GitHub
Buffer of Thoughts	Thought-Augmented Reasoning with Large Language Models.	GitHub	arXiv
Byzer-Agent	Easy, fast, and distributed agent framework for everyone.	GitHub
CAMEL	Communicative Agents for “Mind” Exploration of Large Scale Language Model Society.	GitHub	arXiv
Character-LLM	A Trainable Agent for Role-Playing.	GitHub	arXiv
ChatDev	Communicative Agents for Software Development.	GitHub
CogAgent	A Visual Language Model for GUI Agents.	GitHub	arXiv
crewAI	Framework for orchestrating role-playing, autonomous AI agents.	GitHub
DB-GPT	DB-GPT is an open-source framework designed for the realm of large language models (LLMs) within the database field.	GitHub	arXiv
Dify	Dify is an open-source LLM app building platform.	GitHub
Digital Life Project	Autonomous 3D Characters with Social Intelligence.		arXiv
DSPy	DSPy is the framework for solving advanced tasks with language models (LMs) and retrieval models (RMs).	GitHub	arXiv
everything-ai	Your fully proficient, AI-powered and local chatbot assistant🤖.	GitHub
fabric	fabric is an open-source framework for augmenting humans using AI.	GitHub
FastGPT	FastGPT is a knowledge-based platform built on the LLM.	GitHub
fastRAG	Efficient Retrieval Augmentation and Generation Framework.	GitHub
Fine	Automate software development with AI Agents.	GitHub
Flowise	Build LLM Apps Easily.	GitHub
GraphRAG	A modular graph-based Retrieval-Augmented Generation (RAG) system.	GitHub
KwaiAgents	A generalized information-seeking agent system with Large Language Models (LLMs).	GitHub	arXiv
Lagent	A lightweight framework for building LLM-based agents.	GitHub
LangChain	Get your LLM application from prototype to production.	GitHub
Langflow	Langflow is a UI for LangChain, designed with react-flow to provide an effortless way to experiment and prototype flows.	GitHub
LangGraph	Building language agents as graphs.	GitHub
LangGraph Studio	LangGraph Studio offers a new way to develop LLM applications by providing a specialized agent IDE that enables visualization, interaction, and debugging of complex agentic applications.	GitHub
Langroid	Multi-Agent Framework.	GitHub
Lepton AI	A Pythonic framework to simplify AI service building.	GitHub
LlamaIndex	LlamaIndex is a simple, flexible data framework for connecting custom data sources to large language models.	GitHub
LLMStack	Open-source platform to build AI Agents, workflows and applications with your data.	GitHub
Marvin	The AI Engineering Framework.	GitHub
MetaGPT	The Multi-Agent Framework.	GitHub
MindSearch	MindSearch: Mimicking Human Minds Elicits Deep AI Searcher.	GitHub
Mixture of Agents (MoA)	Mixture-of-Agents Enhances Large Language Model Capabilities.	GitHub	arXiv
Mobile-Agent	Autonomous Multi-Modal Mobile Device Agent with Visual Perception.	GitHub	arXiv
Multi-LLM Agent	α-UMi: Small LLMs Are Weak Tool Learners.	GitHub	arXiv
OpenAgents	An Open Platform for Language Agents in the Wild.	GitHub	arXiv
OpenGPTs	A framework for creating agent runtimes.	GitHub
OpenPaL	Building Open-Ended Embodied Agent via Language-Policy Bidirectional Adaptation.	GitHub	arXiv
Phidata	Build AI Assistants using function calling.	GitHub
Pipecat	Open Source framework for voice and multimodal conversational AI.	GitHub
PR-Agent	An AI-Powered 🤖 Tool for Automated Pull Request Analysis, Feedback, Suggestions and More!	GitHub
ProAgent	From Robotic Process Automation to Agentic Process Automation.	GitHub	arXiv
Qwen-Agent	Qwen-Agent is a framework for developing LLM applications based on the instruction following, tool usage, planning, and memory capabilities of Qwen.	GitHub
Ragas	Ragas is a framework that helps you evaluate your Retrieval Augmented Generation (RAG) pipelines.	GitHub
RAGoon	Improve Large Language Models retrieval using dynamic web-search ⚡.	GitHub
ReWOO	Decoupling Reasoning from Observations for Efficient Augmented Language Models.	GitHub
Search with Lepton	Building a quick conversation-based search demo with Lepton AI.	GitHub
Superagent	The open framework for building AI Assistants.	GitHub
SuperAGI	SuperAGI - A dev-first open source autonomous AI agent framework.	GitHub
SWE-agent	Agent Computer Interfaces Enable Software Engineering Language Models.	GitHub
TaskGen	A Task-based agentic framework building on StrictJSON outputs by LLM agents.	GitHub
TaskingAI	The open source platform for AI-native application development.	GitHub
TaskWeaver	A Code-First Agent Framework.	GitHub	arXiv
ToRA	ToRA: A Tool-Integrated Reasoning Agent.	GitHub	arXiv
Translation Agent	Agentic translation using reflection workflow.	GitHub
UFO	A UI-Focused Agent for Windows OS Interaction.	GitHub
Vanna	Vanna helps you generate and run accurate SQL for your database using LLMs via Retrieval-Augmented Generation.	GitHub
WebDesignAgent	An agent used for webdesign.	GitHub
XAgent	An Autonomous Agent for Complex Task Solving.	GitHub
X-Force IDE	X-Force IDE is a low-code, agent-as-a-service UI framework.	GitHub

^ Back to Contents ^

Memory

Source	Description	Code	Paper
Chroma	Chroma - the AI-native open-source embedding database.	GitHub
LanceDB	LanceDB is a developer-friendly, open source database for AI.	GitHub
Milvus	A cloud-native vector database, storage for next generation AI applications.	GitHub
Pinecone	Pinecone serverless lets you deliver remarkable GenAI applications faster, at up to 50x lower cost.
Weaviate	The AI-native database for a new generation of software.	GitHub

^ Back to Contents ^

Prompt & Context Engineering

Source	Description	Code	Paper
DSPy	DSPy: The framework for programming—not prompting—language models.	GitHub

^ Back to Contents ^

Security

Source	Description	Code	Paper
E2B	Cloud Runtime for AI Agents.	GitHub

^ Back to Contents ^