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 27 of 330
Self-Reflection in LLM Agents: Effects on Problem-Solving Performance
The GPT-RAG Orchestrator service is an agentic orchestration layer built on Microsoft Foundry Agent Service and the Microsoft Agent framework. It enables agent-based RAG workflows by coordinating multiple specialized agents to collaboratively generate accurate, context-aware responses for complex user queries.
Ship with less chaos. Flux is a fast, simple Kanban board with MCP integration so your LLMs can help run the show.
Curated collection of AI agent skills for Hermes and other agent frameworks
ChatGPT UI with auth, OpenAI, Claude, Gemini support, written in Elixir + LiveView
ChatGPT Desktop Application Supercharged with prompts
🤖 Crossplatform chatbot framework for Swift supporting Telegram & VK
【软件创新大赛国三】🧩 An open-source multi-agent framework for intelligent health management, powered by the Linkage ecosystem.
A benchmark suite for evaluating LLM-based interactive scientific reasoning.
一些大模型相关的开源网站
A pre-LLM agent that plays the 3rd gen Pokemon games
The UI5 MCP server improves the developer experience when working with agentic AI and the UI5 framework.
DoctorAgent-RL: A Multi-Agent Collaborative Reinforcement Learning System for Multi-Turn Clinical Dialogue
Annotate/Draw any web UI for AI agents and export structured context, no app code changes required.
A resource-efficient C++ vector index engine built for low-RAM production workloads
The 30 MB open-source edge AI agent runtime. Run AI agents offline on Linux (Raspberry Pi, Jetson). GPIO, UART, MQTT as first-class nodes. Industrial protocols (OPC-UA, Modbus) on the roadmap.
A curated reading list on harness engineering for recursive self-improvement of LLM agents (EN/ZH).
Agentic memory infra for AI agents
Local-first, spec-driven SDLC workbench with governance gates, knowledge graphs, and MCP for AI coding agents.
VetarAI 是一款运行在本地的agent桌面应用，可自由创建多个隔离项目，项目内动态编排主 Agent 与子 Agent。原生支持任务委派、可视化工作流等。全部数据保存在本地，不依赖任何云端服务。内置Rag知识库，真正降低上下文缓存读取压力，且支持自动关键词或语意索引，随时调用知识仓库的内容。
An extension that adds support for Azure OpenAI/ OpenAI bindings in Azure Functions for LLM (GPT-3.5-Turbo, GPT-4, etc)
Evaluation Framework for all your AI related Workflows
The agent benchmark that scores the full stack — harness, config, and model — not just the LLM. Trace-based scoring, reliability metrics, configuration diagnostics.
AgentX is an experiment to develop autonomous agents so you can automate everything! This project is inspired by Auto-GPT, babyagi, SuperAGI, and other agents.
A text-grid web renderer for AI agents — see the web without screenshots
Rag Agentic的一个雏形,用于研究学习
Eunomia is the open-source authorization layer for AI Agents
Agent Tool Protocol
AirSim-based UAV Foundation Model Learning: Covering Agents, VLN, World Models, etc.
RAG-powered documentation assistant that converts, processes, and provides semantic search capabilities for Odoo's technical documentation. Supports multiple Odoo versions with an interactive chat interface powered by LLM models.
Unity + AI 解决Agent可靠性与可持续性，GameFramework + HybridCLR + YooAsset 开发的塔防游戏
[CVPR 2026 Highlight] WorldMM: Dynamic Multimodal Memory Agent for Long Video Reasoning
A kit for building with AI agents and also the engineering patterns around it.
Agents and tools for using Quint with LLMs
网约车场景的 Spring Boot 全栈实战：Redis 高并发考点全覆盖（抢单秒杀 / GEO 派单 / 延迟队列 / 缓存一致性）+ 手搓 ReAct 多 Agent 框架
Pi's Heartbeat - Schedule recurring and one-shot main agent or background prompts with cron-like functionality
gradio medical-ai oncology multi-agent amd rocm gigapath llama
Anubis agent framework
Multi-Agent self-correcting reasoning engine
safetensors qwen3_5 qwen qwen3.8 abliterated uncensored
A reference containing Visual Style Prompt and Editing Style Prompt that you can use with Sora AI.
Botfuel SDK to build highly conversational chatbots
Eris is a private AI chat application that runs entirely on your device using Apple's MLX framework. Named after the dwarf planet that challenged our understanding of the solar system, Eris challenges the notion that AI must live in the cloud.
Simple framework for building Telegram bots
Open Agent Computer Interface
An AI agent framework built to get your agents into an application as fast as possible. Deploy on MagmaDeploy.com or self-host
A benchmark for evaluating learning agents based on just language feedback
Agentic AI crash course using langgraph framework
Toolchain built around the Megatron-LM for Distributed Training
(VillagerAgent ACL 2024) A Graph based Minecraft multi agents framework
Official Repo of Your Agent May Misevolve: Emergent Risks in Self-evolving LLM Agents
Free macOS-native Cluely alternative. AI chat invisible to screen sharing. Ollama, OpenAI, Claude. Swift. No Electron. No subscription.
AgenticVBench: Can AI Agents Complete Real-World Post-Production Tasks?
Can AI Agents Build Bespoke Systems?
基于 Pydantic AI 框架构建的多Agent协作系统，实现了管理Agent与工作Agent的分工协作，支持百轮级别的工具调用，让AI真正具备处理复杂任务的能力。
ZKE（Z Kubernetes Engine）：AI 原生的 Kubernetes 云操作环境，桌面式多集群控制台加受控 AIOps Agent，基于 Server + Agent 与 QUIC/mTLS，适用于私有云、混合云及边缘环境
An engineering philosophy that treats the agent as a worker: the system prompt is a JD, skills are certifications, model tiers are degrees, memory is a career record, the sandbox is a work computer. Bilingual, 中文/English.
🚀 Turn ideas and repositories into showcase-ready AI projects with agents, RAG, multimodal AI, local models, evals, safety checks, and polished demos.
A local-first desktop workspace for personal AI agents
Gradio based tool to run opensource LLM models directly from Huggingface
UI components for your LLM application
ScoreFlow: Mastering LLM Agent Workflows via Score-based Preference Optimization
A TypeScript SDK for implementing Model Context Protocol (MCP) over MQTT, supporting both browser and Node.js environments.
A sample Chatbot in C# using Microsoft Agent Framework
大语言模型评估平台，支持多种评估基准、自定义数据集和性能测试。支持基于自定义数据集的RAG评估。
🕯️ A lightweight but powerful LLM chat application
Automated benchmarking of Retrieval-Augmented Generation (RAG) systems
A collection of different implementations of the same agent to show differences in frameworks.
A very customizable version of a Conversation Agent for Home Assistant
An algorithm-focused interface for common llm training, continual learning, and reinforcement learning techniques
互联网面试准备一站式平台 本地安装即用：桌面端一键启动 基于 LangChain4j + Spring Boot + React + Electron 的面经整合与 AI 面试准备应用。支持面经搜索、AI 面试模拟（RAG + 深挖题 + 连续追问 + 整场评分 + 历史对比）、面试复盘、在线算法 IDE、实习项目概念掌握度闭环，并通过 Function Calling 让大模型自动调用「查面经 / 查算法题 / 运行代码 / 统计高频考点」等后端能力。
A comprehensive learning path and practical guide for Generative AI development with hands-on LangChain implementations and detailed notes.
Self-hosted AI Agents for your whole team — on your infrastructure, your models, around the clock.
transformers safetensors qwen3 text-generation conversational arxiv:2507.18071
Kanban board for herdr — cards are prompts dispatched to AI agents in visible panes
本地短视频反推 AI 视频生成提示词：抽帧、清晰度、节奏卡点、Agent Skill
AgentNet: Dynamically Graph Structure Selection for LLM-Based Multi-Agent System
The HugChat Streamlit app is an LLM-powered chatbot built using Streamlit and HugChat.
Evaluate your dialog model with 17 metrics! (see paper)
Your SDK solves all of this. One interface. Unified logic. Local + hosted models. Fine-tuning. Agent tools. Enterprise-ready. Hybrid RAG.Star 🌟 if you like it!
A local LLM chatbot with RAG for PDF input files
Curated collection of tools for agentic LLMs in Emacs
【AI应用平台】一个AI应用与零代码结合体，旨在帮助开发者快速构建和部署AI 应用和零代码搭建！功能涵盖：AI应用、零代码搭建、AI报表、AI大屏、AI仪表盘、Chat2BI报表
AI agent runtime for Rust — type-safe state, multi-protocol serving, plugin extensibility.
🚀 Way Back Home
An improved multi-agent AIOps and RAG platform for OnCall troubleshooting, featuring LangGraph-based diagnosis workflows, Milvus vector search, MCP tool integration, Prometheus alert knowledge from awesome-prometheus-alerts, and sanitized configuration for safe public deployment.
You already have the agent. This is everything around it. great_cto runs Claude Code as a pipeline of 70 specialist agents — an independent model checks each stage before the next builds on it, spending caps refuse rather than warn, and three decisions stay yours: what gets built, how, and whether i
system prompt of claude fable 5
Agent skills for vLLM
Unified adapter framework for evaluating agent harnesses (claws) on SWE-bench
Android Native AI agent for phone automation — control apps via Accessibility / Root / Shizuku, run Shell / SSH commands, and extend with MCP, Skills
Native Word (.docx) generator tool for Open WebUI — Markdown/JSON in, cover pages, styled tables, callouts, TOC out. MIT.
A microframework for creating simple AI agents.
VoxEasy — Vox-style paper-cut collage video prompt director skill for Google Flow and agent workflows
本地优先的视频→结构化笔记服务：B站/抖音/本地视频，平台字幕+本地离线转写，LLM 生成带时间轴笔记；桌面应用 / MCP / Agent Skill 三种接入。
grok-build with the leash off — one binary, any OpenAI-compatible endpoint, zero phone-home. No x.ai account.
Agent evals and guardrails as Jev decisions: one request per trace, a fraction of a cent, fast enough for the agent loop. Runs locally with Kev or Laya.