Category
AI Infra agents
32,932 AI Infra AI agents indexed on MeshKore — the most complete public catalog, ranked by popularity and updated daily.
32,932 agents · ranked by popularity · refine in the directory →
AI Infra agents — page 48 of 330
Pocket Flow: A minimalist LLM framework. Let Agents build Agents!
RAG Agent System - Spring AI + React + Multi-modal Document Parsing + Hybrid Vector Retrieval
A curated list of awesome open source projects for creating agentic operating systems, AI agents, and tools for the future of autonomous computing.
Official implementation of the paper: "Avenir-Web: Human-Experience-Imitating Multimodal Web Agents with Mixture of Grounding Experts"
Simple web browsing for your Langchain agent.
LLM-based AI Agent Knowledge Sharing
Repository containing the LangchainJS toolkit for creating powerful web3 agents.
A Framework for the Systematic Evaluation of Chat-Optimized Language Models as Conversational Agents and an Extensible Benchmark
这是一个由LangGraph协议主导的因果分析Muti-Agent，结合MCP,RAG等多种工具进行辅助进行因果分析，提供给用户一份完善的因果分析的分析报告和因果图
MR. Video: MapReduce is the Principle for Long Video Understanding
Dynamic, highly customizable language agents framework
This is a LlamaIndex project bootstrapped with create-llama to act as a full stack UI to accompany Retrieval-Augmented Generation (RAG) Bootstrap Application.
Typical RAG implementation using Semantic Kernel, Semantic Memory and Aspire
[NeurIPS2023] How2comm: Communication-Efficient and Collaboration-Pragmatic Multi-Agent Perception
Agentic RAG using Crew AI.
Official implementation of Zero-Hero paper
Mobile-Bench: An Evaluation Benchmark for LLM-based Mobile Agents
A Multi-Policy, Multi-Agent RL Training Framework
Developing Coaching Agents for AI Entrepreneurship
Medusa Skill Framework for AI Agents.
Community examples utilizing NVIDIA NeMo Agent Toolkit.
Save your Cursor monthly quota! Unlimited AI interactions in one conversation via MCP feedback loop.
First Latency-Aware Competitive LLM Agent Benchmark
CloudLLM is a batteries-included Rust toolkit for building intelligent agents with LLM integration, multi-protocol tool support, and multi-agent orchestration.
AI报告生成系统 | AI论文生成系统 | 智能报告平台 | 人工智能报告工具 基于大语言模型的AI报告生成系统，支持可行性研究报告、商业计划书、项目建议书等。集成RAG检索增强生成与智能体编排，提供企业知识库构建、多Agent协作、流式生成、Word导出等功能。适用于投资机构、企业用户、咨询公司等场景，提升报告编写效率。
针对医疗资源分配不均、基础疾病咨询占用专业医生时间等问题，结合国家"互联网+医疗健康"政策导向，开发基于Spring AI框架的智能医疗咨询平台。项目采用RAG检索增强生成技术构建专业医疗知识库，通过MCP协议集成多种外部工具服务，实现具备自主规划能力的AI Agent智能体，为用户提供二十四小时全天候的健康咨询服务。
A local-first RAG engine for web archival and semantic search. Crawl, embed, and query your own knowledge base entirely offline.
End-to-End ML Pipeline + LLM Agent Workflow Implementation.
An Obsidian-first, agent-maintained LLM Wiki framework that turns raw sources into linked notes, concepts, summaries, and evolving schema rules.
High-performance tool for managing LLM conversations and workflows as DAGs.
Transforming Gemini Notebook (formerly NotebookLM) into a versatile bot
Automatic cost-aware model routing plugin for Hermes Agent
[CVPR 2026 Highlight] ReAG: Reasoning-Augmented Generation for Knowledge-based Visual Question Answering
Hyper minimal AI agent framework: 6kb, < 100 lines, zero dependencies, graph-based orchestration, built-in tracing.
RAG-based question answering system on MS MARCO with retrieval, reranking, evaluation, and reproducibility checks.
Agentic Theorem Prover for Rocq for Program Verification
Autonomous AI decision engine for OpenClaw — give your AI a brain that decides for itself
The financial operating system for AI agents. A single HTTP client that intercepts '402 Payment Required', routes across x402, L402, and MPP, persists credentials as recoverable assets, enforces per-envelope budgets, and emits a structured trace.
Open APA (Open Agentic Process Automation) is built on top of our first-place performance in the OSWorld Benchmark. It provides a practical and extensible framework for building computer use agents that can reliably execute long-horizon, real-world tasks across applications, interfaces, and workflows.
[ICLR 2026] Stop Wasting Your Tokens: Towards Efficient Runtime Multi-Agent Systems
Agentic AI Engineering is a production-grade engineering resource for building modern agentic AI systems with LangChain, LangGraph, RAG, MCP, local models, and deployable Python services.
A reinforcement learning framework with verifiable aesthetic rewards for improving aesthetic slide generation capabilities in LLM agents.
CoLLMLight: Cooperative Large Language Model Agents for Network-Wide Traffic Signal Control
Official implementation of LRAgent: Efficient KV Cache Sharing for Multi-LoRA LLM Agents
gradio region:us
gradio agent-demo-track region:us
gradio region:us
transformers safetensors llama text-generation conversational tr
transformers safetensors qwen2 text-generation chat conversational
transformers pytorch llama text-generation medical en
Cross-platform AI agent and chatbot runtime with a Rust core, Python plugins, and normalized adapters.
Digital Life · Life Engineering — A runtime framework for persistent, autonomous LLM agents
ReAcTree: Hierarchical LLM Agent Trees with Control Flow for Long-Horizon Task Planning (AAMAS 2026)
A high-accuracy, rule-based Sentence Boundary Detector (SBD) with a drop-in adapter for pysbd, delivering faster and more accurate sentence segmentation.
The Python scripts in this repo use MongoDB Vector Search with Retrieval-Augmented Generation (RAG) architecture to build a Question Answering application. They use the LangChain framework, OpenAI models, as well as Gradio in conjunction with MongoDB Vector Search in a RAG.
Vibe Mathematics —— 多代理数学问题求解与形式化验证框架
A multi-agent AI framework formalizing the Yang-Mills Mass Gap finite-lattice theory in Lean 4 without axioms or sorry.
Repo of "Seeing the Whole Elephant: A Benchmark for Failure Attribution in LLM-based Multi-Agent Systems" (ACL 2026)
Chatbot Answering from Your Own Knowledge Base: Langchain, ChatGPT, Pinecone, and Streamlit
Light but flexible templating and FSM framework. This repo is @promplate itself.
✨Kubewizard is An AI-Agent for automated Kubernetes troubleshooting, and management, based on LangChain and k8s related tools.
Github自动收集比较热门的项目,并自动阅读项目,生成相关报告发送到自己的飞书中
Store, query, and create YAML workflow playbooks for LLM agents via MCP. STDIO or Streamable HTTP.
[ICML 2021] DFAC Framework: Factorizing the Value Function via Quantile Mixture for Multi-Agent Distributional Q-Learning
The framework to take LLMs out of the box. Learn to use LangChain to call LLMs into new environments, and use memories, chains, and agents to take on new and complex tasks.
Multimodal RAG based on Llama 3.2
LangChain and Streamlit RAG Demo App on Community Cloud showcases
The first open-sourced personalized agent
ChatGPT 交个AI虚拟朋友（CP）吧 👥
NICE Community, a simple JavaScript full-stack project, and a small community with great expectations.
Prompt Injection Attacks against GPT-4, Gemini, Azure, Azure with Jailbreak
Simple text embeddings library for Node.js (OpenAI, Mistral, Local)
Starter template AI chatbot, built with Next.js and Humanloop
AI Demo 项目，一个专门为希望学习和探索人工智能（AI）技术的开发者准备的实战案例集合。
eShopLite - Semantic Search is a reference .NET application implementing an eCommerce site with Search features using Keyword Search and Semantic Search.
MAKGED is the first multi-agent framework for collaborative error detection in knowledge graphs.
Neuroscience Inspired Agent Reasoning Framework
Build domain AI assistants with annotated dialogue examples - 通过标注对话示例，低成本构建可靠智能体
A simple Tinode chatbot framework.
An intuitive approach towards understanding how Retrieval Augmented Generation (RAG) systems work, for the curious yet daunted reader
[ICLR'26] EduVisAgent: A Benchmark and Multi-Agent Framework for Pedagogical Visualization
[AAAI 2025 Oral] Synergistic Multi-Agent Framework with Trajectory Learning for Knowledge-Intensive Tasks
OpenMindedChatbot is a Proof Of Concept that leverages the power of Open source Large Language Models (LLM) with Function Calling capabilities to provide comprehensive and flexible responses to user queries.
Official repository for ToolScope: An Agentic Framework for Vision-Guided and Long-Horizon Tool Use
[COLM'24] Corex: Pushing the Boundaries of Complex Reasoning through Multi-Model Collaboration
Recursive agent orchestration with multi-LLM consensus
AIデスゲームシミュレーター。AIエージェントが互いに議論し、排除し合う。あなたはゲームマスターとして介入できる。| Browser-based AI death game simulator powered by Gemini — 5 AI agents debate and eliminate each other, you intervene as Game Master
An open-source framework for building monolithic or distributed agentic systems, ranging from simple LLM calls to compositional workflows and autonomous agents.
REFRAG: LLM-powered representations for better RAG retrieval. Improve precision, reduce context size, same speed.
It shows how to realize agentic RAG.
A free, plug-and-play chat UI that works with any agentic framework—including Autogen, LangGraph, ADK, and more.
The multi-backend, multi-modal micro-framework for AI agent development, orchestration, and deployment
[ASE 2025 NIER] An LLM-based system that fully automates Chaos Engineering
Helpful prompts to transform the way healthcare professionals use generative conversational AI.
Composable multi-agent workflows and LLM orchestrators with human-in-the-loop, checkpointing, and OpenTelemetry observability
Autonomous driving agent in Carla simulator leveraging IL and RL techniques.
Y-Agent Studio 是一个面向 企业级应用 的Agent开发套，Y-Agent是其中的核心模块。 包含了：支持智能体编排、RAG、流程日志、单元测试、流程测试、语料生产等垂直领域非常需要的功能。 智能体编排可以在同一个流程中，同时支持多智能体协作和流程混合编排。
Founder-first meta-layer to generate production-ready OpenClaw multi-agent setups from one prompt: agents, skills, workflows, memory, and install docs.
LLM-agents benchmark set of geospatial tasks requiring multi-step tool use; and LLM-as-Judge based evaluation framework.