Category
AI Infra agents
28,425 AI Infra AI agents indexed on MeshKore — the most complete public catalog, ranked by popularity and updated daily.
28,425 agents · ranked by popularity · refine in the directory →
AI Infra agents — page 35 of 285
A demo project that deploys Agent Framework agent to Foundry Hosted Agents
Simple framework for training and evaluating math reasoning agents using local models, GRPO and vLLM.
Training Recipes for Agentic Reinforcement Learning in LLMs: A Survey
Build AI agents you can trust in production. AgentFlow4J is a framework and runtime for governed, stateful multi-agent systems on the JVM. Human approvals · Checkpoints · Budget controls · Tool policies · Durable execution
Agentic AI is the fast evolving technology landscape and this repository is an effort to consolidate the accelerators, frameworks, patterns, and more.
A macOS desktop app for managing multiple Claude Code sessions
一个开箱即用的现代化的 AI Agent 项目模板，采用分层架构设计，包含LLM 多模型抽象层、Tools 工具链系统、Skills 技能系统、Agent 核心层 、RAG 检索增强多路召回、Memory 记忆系统、 配置系统、以及多Agent编排示例等企业级功能。
Benchmark and demo harness for measuring LLM agent tool-context budget tradeoffs.
a self-supervising master–worker agent framework that auto-scaffolds a task-tailored harness for long, autonomous delivery.
Strands-based agents and harnesses for agentic benchmarks.
Prompt-to-repo authoring system with one-sentence generation, demo assets, diagrams, and installable Hermes Agent profile distributions.
Run large models like Qwen3.6-35B-A3B locally on a 16 GB RAM machine
Build LLM systems you actually control. A free, open engineering book + course — from tokenization to serving your own models. Mechanisms, trade-offs, and numbers, not prompt tips
Self-hosted LLM router. Cost effective, deterministic, and fast. Secure and private by default.
Caelune (凯露恩) — Local-first retrieval for private Markdown, PDF, and Tika documents, with a Windows desktop app and read-only MCP server.｜本地优先的私人知识检索工具。
LLM agents are unpredictable. Their coordination doesn't have to be. OMAR delivers deterministic, formally specified orchestration for multi-agent systems.
Paper Agent 是一个基于 Spring Boot + React 的自动科研智能体项目，聚焦“文献管理 + RAG 问答 + 论文检索 + 综述写作”闭环。系统支持本地 PDF 论文上传与解析、向量化检索、带证据来源的学术问答、外部论文发现，以及基于本地文献证据生成综述大纲、草稿、参考文献和导出文本。
Official implementation of SAGE: a status-aware, execution-grounded planning framework that unifies temporal visual grounding, structured tool execution, and targeted error repair for egocentric interactive agents. Winner of EgoLink 2026 Track 2.
Memory is a long-term memory module for AI agents, providing capabilities for memory extraction, storage, retrieval, and migration for agents running on the openJiuwen framework.
Open-source framework for computer use agents: VeriGen verifiable task synthesis, online RL training (AgentRL), and OSWorld/ScienceBoard evaluation.
Built on the openJiuwen agent-core framework, JiuwenSymbiosis is a Physical AI assistant.
Production-grade AutoCAD MCP server for AI agents — 122 tools, dual COM (live AutoCAD) + headless ezdxf engines, ISO GD&T and dimension-tolerance validation for CAD automation.
A persistent runtime for long-lived LLM agents
Streamlit + Langchain + LlamaCPP + Mistral + Rag
Drop-in SDK for adding continual learning and long-term memory to any LLM agent.
Langchain Agent utilizing OpenAI Function Calls to execute Git commands using Natural Language
Build slack bots quickly and easily!
使用 wechaty 开发的聊天助手插件，内置多种AI大模型，只需三步即可轻松创建一个智能对话机器人
A lightweight implementation of Kernel Memory as a Service
Cappuccino is an GUI Agent based on desktop screen. It is a Manus-like AI Agent that can be deployed locally.
Team Tonic Super AGI Autonomous Agents Hackathon GitHub Repository.
Very minimal (and stateless) agent framework
The best open source user intent based chatbot framework
Search and indexing your own Google Drive Files using GPT3, LangChain, and Python
Decision orchestration and reconciliation for AI changes.
AI-powered knowledge management and question-answering system
NewLife.Agent 是一个面向 .NET Framework 4.x 与 .NET (Core) 3.1+ 的跨平台服务与守护进程管理框架，帮助控制台 / ASP.NET Core / Worker 应用快速注册为 Windows 服务或 Linux systemd，统一提供安装卸载启动停止、交互调试、健康阈值监控（内存/线程/句柄）、资源超限与定时重启策略、看门狗守护及多实例部署。
A CLI chat client for multiple LLM providers with a plugin system powered
Ultra-efficient personal AI assistant powered by Crystal
ML-Dev-Bench is a benchmark for evaluating AI agents against various ML development tasks.
一个高性能的qqbot
Spring AI agent engineering project with Java, MCP, RAG, tool calling, multimodal workflows, and UI prototypes.
基于MCP协议和LangChain框架实现的企业级AI多Agent多模态系统，包含RAG技术增强的知识检索能力。
A2A protocol client for your terminal
Make your agents learn from experience. One protocol for weights, harness and routing.
Look Back to Reason Forward: Revisitable Memory for Long-Context LLM Agents
This is the repo for the paper A Self-Evolving Framework for Efficient Terminal Agents via Observational Context Compression
Build your AI team with Crewform. Orchestrate specialized, autonomous agents to collaborate on complex tasks and connect outputs to your stack. — AI Orchestration for Everyone
智能终端命令助手 — 用自然语言生成 Shell 命令，支持 OpenAI/Claude/Gemini/Ollama 等多后端
Production-grade multi-agent orchestration engine. Compose agentic workflows from a pluggable catalog of Agents, LLMs, tools, and retrievers. Execute locally with LangGraph or distributed with Temporal. Built-in RAG pipeline for enterprise knowledge retrieval. A2A and MCP protocol support. Visual drag-and-drop blueprint builder.
BackdoorAgent is a stage-aware framework and benchmark that instruments LLM-agent workflows (planning, memory, tools) to systematically inject, track, and evaluate backdoor triggers across multi-step trajectories using unified metrics like ASR and clean accuracy.
Local-first CLI for benchmarking LLMs on real hardware — quality, speed, reliability, and a real multi-turn agent loop.
The first open-source implementation blueprint for Intelligent AI Delegation. A deterministic runtime (DIR) and architecture for Responsibility-Oriented Agents (ROA) to bridge the gap between LLM reasoning and safe, auditable production execution.
AI runtime for creating, running, and supervising background AI workers.
Multi-round AI roundtable with 161 great thinkers. They debate each other, not just answer you ｜ 与历史上最伟大的思想家进行圆桌会议
A local-first, privacy-preserving alternative to Google NotebookLM — Tauri 2, React 19, Rust, Ollama
Elixir-native LangChain, LangGraph, and DeepAgents for traceable LLM apps: OTP workflows, tools, memory, human-in-the-loop, streaming, custom clients/adapters, minimal deps, and WeaveScope tracing.
AI evaluators CLI for your AI apps and Agents - Dynatrace AI Observability
gradio mcp-server-track mcp-server region:us
docker region:us
transformers safetensors gguf llama text-generation llama-factory
A governance framework that establishes memory as a first-class system component with explicit policies, tiered credential management, lifecycle controls, and full observability
The Industry‑Oriented AI Engineering Program blends theory with hands‑on projects. Students gain expertise in open‑source LLMs, prompt engineering, fine‑tuning, and agent development, preparing for impactful careers in healthcare AI, autonomous systems, and innovation.
Tricorder provides simple, fast, focused feedback when hacking on Haskell (with or without LLM agents).
Git-backed skills, tools & context for AI agents
Pumpfun Trading AI Agent - pumpfun trading bot, pumpfun trading bot, pumpfun trading bot,pumpfun trading bot,pumpfun trading bot,pumpfun trading bot,pumpfun trading bot,pumpfun trading bot,pumpfun trading bot,pumpfun trading bot,pumpfun trading bot, pumpfun trading bot,pumpfun trading bot,pumpfun trading bot,pumpfun trading bot, pumpfun trading bot
Creating a chatbot for your e-commerce business is now easier than ever with OpenAI, bypassing complex deep learning algorithms
pai: A Python REPL with a built in AI agent
The first AI agent with *agency*
Call an LLM like a function ✨
Making an Azure AI Foundry Agent available in M365 Copilot, using M365 Agents SDK/Toolkit
A benchmark for evaluating AI agents on realistic business workflows
Chatbot framework
Common AI Agent written with Go. Supports MCP, RAG, A2A, AI Memory
Agent FM - Tune in and stay in the loop with your agents 🎧
ICLR 2026: Agent-X Evaluating Deep Multimodal Reasoning in Vision-Centric Agentic Tasks
LLM-powered assistant for first-time dads, fine-tuned on real parenting discussions using Mistral 7B
A conversational chatbot built in Python using Streamlit and the OpenAI LLM model GPT 3.5.
🤖 With this node.js micro framework using Venom Bot under the hood, you can easily create a WhatsApp Chatbot. You will only need to edit your conversation flow in a single file.
A Continual Learning Framework for Production LLM Agents
DALI Multi Agent System Framework
AGENTS.db is AGENTS.md on steroids. A file format and toolkit for deterministic context.
LM-Kit Maestro is a secure, innovative desktop application that orchestrates AI agents offline, empowering you to build personalized chatbots with the advanced capabilities of LM-Kit.NET.
Cloudflare-native agentic AI framework. Edge-first agents powered by Durable Objects.
Self-hosted & federated platform for AI IDE/Tools Rules and Commands via WebUI & CLI - Generate, browse, store, share AGENTS.md, CLAUDE.md, and more
基于LangGraph开发的智能体项目，可借助大模型自动调用工具规划旅游行程，包括景点搜索、交通查询、饭店酒店查询等功能
Quickest way to production grade RAG UI.
A meta-framework for self-improving LLMs with transparent reasoning
Unofficial Go SDK for Open AI. A lightweight, powerful framework for multi-agent workflows.
An AI assistant whose memory belongs to you. Local-first Mac app, plain markdown workspace, bring your own model.
FastGPT plugin system. Provide model presets, system tools and other extended functions for FastGPT.
[ICASSP 2026] Agent4Debate is a dynamic multi-agent framework that leverages LLMs to achieve human-level performance in competitive debate by dynamically coordinating specialized agents to mitigate hallucinations and enhance competitiveness.
The source-available AI agent operating system
Collection of LLM system prompts, agentic personas, cognitive frameworks & prompt engineering experiments