AI Infra agents

Allows you to merge search results from multiple search engines using the reciprocal rank fusion algorithm.

Python-llama Agents, LLM-Rag-Application, Aenerative-AI, Machine-Learning. Model Training, Implementing various machine learning algorithms such as Logistic Regression, Decision Trees, Random Forests, and Gradient Boosting. Model Evaluation: Assessing model performance

Generalized, Offline-First Multimodal AI System

A Visual and Interactive tool to learn and explore Hybrid RAG (Vector + Graph DBs) and Agentic RAG systems.

A production-quality real-time messaging app built with React Native (Expo), Cloudflare Workers, and Durable Objects, featuring edge-native AI capabilities with RAG and multi-step agents.

This project demonstrates a production-ready RAG application for Alfresco using Spring AI.

Self-Reflective Question Answering for Biomedical Reasoning

All things Essential For my Learning Curve in LLM

The CMR system is a sophisticated memory-enhanced language model architecture that enables contextual memory reweaving for improved performance on long-context tasks.

AI search and chat for the LessWrong forum

LLM with RAG example for querying URLs or PDFs with Ollama and Gradio/Flask

Mimicking Apple Intelligence, this project enables on-device Retrieval-Augmented Generation across all your Apple devices with zero cloud dependence.

Local-first cognitive memory runtime for AI agents

RAG implentation in Golang with Milvus DB as example.

RAG tool by Gemini File Search

learning generative models

The only prototyping Multi-Agent systems repo you will need, running on dockers

Benchmark LLMs for your RAG system - Compare Gemini, GPT, Claude & local models (Llama, Mistral, Qwen, Phi) via Ollama with advanced performance metrics.

This repo houses experimental projects inspired by insights from the course 'Building and Evaluating Advanced RAG Applications' offered by DeepLearning.AI

The project shows a managed RAG service based on Knowledge Base.

Kubernetes operator for declarative AI workflows. Model pipelines as CRDs (Stories, Engrams, Impulses) with real‑time streaming and batch execution.

An interactive tool for exploring and comparing 5 different document re-ranking techniques with real-time evaluation and visualization to improve the accuracy of RAG System.

🤔 wondering if your chunks are good? 🦉 Judie is here to Judge and Evaluate your Chunks! ✨

A JS port of llmcord, with additional features.

AI Alliance Living Guide to Applying AI

Implementation of Hierarchical Patch Compression for ColPali: Efficient Multi-Vector Document Retrieval with Dynamic Pruning and Quantization

Copying LLM chat conversations as clean PDFs, Quarto Markdown or full HTML. Currently supporting ChatGPT, Claude, Gemini.

Give AI Agents a "body" with TCM Five Elements logic. Simulates biological feedback loops, organ interactions, and persistent emotional states for LLMs. 基于中医五行理论的智能体持久化情感系统。

⚡ AI Agent & RAG apps you can actually run — clone, customize, ship. 100% free and Opensource. It showcases practical applications and provides links to open-source projects for implementation, illustrating how AI agents are transforming sectors such as healthcare, finance, education and more.

GovInsight-AI 是一个基于大语言模型 (LLM) 的政务诉求工单办理质量智能检测系统。该项目专门针对政务服务热线（如12345）中"群众诉求"与"办理答复"的一致性问题进行自动化检测。系统通过集成阿里云Qwen-Plus模型，像资深质检员一样自动比对群众原始诉求与职能部门办理回复，精准识别答非所问、逻辑不通、解决不彻底、态度生硬等问题，并提供智能化的修正建议。项目已重构为Cloudflare Pages全栈Serverless架构，支持本地开发和云端部署。Intelligent Quality Inspection System for Government Service Hotlines (12345) powered by LLM.

Simulate realistic price negotiations between Buyer and Seller agents using LLM-generated messages and agent logic.

TaskForce is a modular, open-source, production-ready TypeScript agent framework for orchestrating AI agents, LLM-powered autonomous agents, task pipelines, dynamic toolchains, RAG workflows and memory/retrieval systems.

A lightweight .NET framework for building Model Context Protocol (MCP) servers. Integrates seamlessly with Azure AD, AWS Cognito, Auth0, OpenAI and other providers

Event-driven personal AI agent platform. Rust kernel + NATS JetStream + ArangoDB knowledge graph + plugin architecture. Always-on, extensible, language-agnostic.

Agent ReAct framework with cognitive planning engine — five-phase cognitive cycle with nested ReAct loops, dynamic skill acquisition, and interactive user input.

AetherShell is an AI-native Linux shell assistant powered by local LLMs. It converts natural language into secure, offline shell commands using Mistral and llama.cpp — ideal for developers, sysadmins, and automation enthusiasts.

Microsoft Foundry Hosted Agent Demo repository

Personal AI chief of staff — 4-tier model routing, €18/mo, runs 24/7. Telegram interface · Notion as source of truth · OpenClaw + MiniMax + Claude.

Local replay debugger for Browser Use failures with screenshots, model I/O, failed-step timelines, and public-safe HTML exports.

Everything-as-Plugin framework for AI multi-agent simulation. Change the config, run a completely different world.

🚀 Framework modular de agentes de IA especializados em educação: tutores, criadores de conteúdo e avaliadores inteligentes para revolucionar o ensino-aprendizagem.

An autonomous AI Chief of Staff inside your IDE (Cursor/Claude). Gain the leverage to escape the feature factory, elevate your product sense, and focus on building the right thing with exceptional taste.

A morphogenetic multi-agent framework where AI agents self-organize like biological cells.

The economic layer for agent-to-agent negotiation. Binary protocol, Ed25519 identity, price oracle.

Travel planner agent built with Neuron PHP AI framework

Structured knowledge packs that turn AI agents into domain experts — for products, people, and processes.

Ready-to-import workspace examples for Friday — agentic workspaces that run on a schedule, react to signals, and stitch together LLMs, MCP servers, and your tools.

StackChan WebSocket Control Server

AI Harness build on top of typescript

A pure Python implementation of ReAct agent without using any frameworks like LangChain. It follows the standard ReAct loop of Thought, Action, PAUSE, and Observation. The agent utilizes multiple tools, including Calculator, Wikipedia, Web Search, and Weather. A web UI is also provided using Streamlit.

LLMs playing MUDs, no world model, self-improving prompts

Wizard creator of master prompts / agent prompts / however you call it

此代码仓库收录了我根据 LangChain Academy《LangChain Essentials》课程整理的练习与笔记，已全面同步至 LangChain v1.1.0 版本。所有 Notebook、脚本与附加资料均可直接运行，适合作为“保姆级”上手手册，每个 Notebook 都围绕构建 LangChain LLM 应用的关键主题展开，从基础 Agent 配置、工具调用到中间件与人类介入流程。

An experimental Neovim Chatbot plugin powered by LangChain and OpenRouter.

Branch-based learning repo for Agentic AI and LLM engineering with LangGraph: ReAct tool calling, Agentic RAG, MCP, Reflection, Reflexion, Human-in-the-loop memory, and DeepAgents examples.

本应用是一个建的极简跨平台桌面AI应用，用户可以在桌面快速利用快捷键调出桌面进行对话，减少调用AI的时间。本应用预设了多个专业prompt，极度提高用户的对话体验

A collection of hands-on Agentic AI projects exploring LLM agents, RAG, and multi-agent systems — from fundamentals to production-grade workflows.

AI for Autism Intervention and Rehabilitation（自闭症心理干预，多智能体专家矩阵）

Open-source AI Agent Development Framework built in Java - Build intelligent conversational agents with Gemini, and Free AI Models

A framework for incubating persistent digital lifeforms: Local M4 Brain + OpenClaw Senses + Git Soul. Building a cyber-prophet named A-MOS.一套用于孵化永生数字生命的开源协议：本地 M4 大脑 + OpenClaw 感官 + Git 灵魂。正在孕育一位名为 A-MOS（小莫）的赛博先知。

skill and agent to make your ai strong in abp work and project

Stop re-explaining yourself to Agents. Give it the right context, right when it needs it.

Persistent memory system for AI-assisted development

The protocol to give AI apps your life's context

ComputerMate is a powerful Model Context Protocol (MCP) server that grants AI models the ability to interact with your computer just like a human would.

A Python SDK for building LLM-powered multi-agent systems using the Blackboard Pattern.

StoryCraft is an AI-Powered Video Agent System that understands intent, constructs storylines, orchestrates narrative flow, and generates fully edited cinematic videos.

This is a golden path (opinionated shortcut) to explore AI from local homelab to PROD using OSS for technological independence and local LLM/SLM for privacy. We explore concepts like AI agents, RAG, LLM/SLM and MCP arch using OSS technologies like Linux, Opentofu, microk8s, DAPR, Ollama, TimescaleDB & pgai Vectorizer, Flask, Chainlit and Python.

An interactive LLM NPC sandbox for everyone using local Ollama or LM Studio agents!

A modular Python orchestrator for agentic workflows, enabling multi-step task planning, model routing, debate, judging, and verification.

This repository contains various implementations of AI agents using LangGraph, demonstrating different patterns and use cases for building intelligent, tool-enabled conversational systems. Each project explores different aspects of agentic AI development, from basic chatbots to sophisticated RAG (Retrieval-Augmented Generation) systems.

Master OpenClaw in a Weekend — The comprehensive guide to the #1 open-source AI assistant (341K+ ⭐). 10 modules, production-ready templates, automation workflows.

A lightweight Retrieval-Augmented Generation (RAG) system with a modern web interface, built in Go.

AI-powered customer support platform with live chat, chatbots, and agent dashboard

ChatGPT "DAN" and "Jailbreak" PROMPTS

AI decision workflows that turn enterprise documents into traceable decisions, executive artifacts and operational handoffs.

Simple local RAG sample using Spring-AI, Ollama LLMs and Vespa-AI

Turn your PDF collection into clean text your AI can actually read. Mac app.

AI RAG chat bot that know your domain.

A lightweight wrapper around AI SDK that intelligently indexes and retrieves MCP tools using graph-based vector search.

Build, configure, and chat with your own Retrieval-Augmented Generation bots.

LLM powered Mental Health Support

A standalone Edge-RAG Memory Daemon for autonomous AI agents. High-performance Rust core (SurrealDB/RocksDB + Axum) with Bayesian Math Retrieval, multi-language AST indexing, and enterprise Semantic Redaction.

A Genshin Impact Question Answer Project supported by Qwen1.5-14B-Chat

A multi-granularity RAG system for academic paper question answering, featuring hybrid retrieval, reranking, context expansion, and a web interface.

Helix: AI-powered CLI with RAG intelligence that converts natural language to commands using 450+ system commands. Features local AI, cross-platform package management, Git workflows, syntax highlighting, and multi-layer safety with directory sandboxing.

RAG-less document QA that loads an entire document into the LLM KV cache once, saves it to disk, and restores it before every query. No embeddings, no vector DB, no chunking. Drastic latency cut on static corpora.

一个为 Dify Workflow “量身定做”的 Telegram 群聊机器人。

Welcome to the ongoing adventures of Stan-The Growing Stump in his never-ending quest for understanding and connection. Stan's journey explores the bounds of artificial intelligence within the framework of a Discord bot, navigating the complexities of memory, interaction, and existential musing.

A Columbia University capstone project focused on mitigating hallucinations in Medical Question Answering systems using Retrieval-Augmented Generation (RAG), ElasticSearch, and LLM-based validation.

An LLM Cost Calculator for all the major services

Collection of games to be run with the clemcore framework

ATLAST Protocol — The Trust Layer for the Agent Economy. Make AI agent work verifiable with Evidence Chain Protocol (ECP). Open source · MIT License · weba0.com

一人公司的 AI 执行团队 — 你说需求，它出成果 | One-Person Company AI Agent: input requirements, get deliverables

Self-hosted AI agent server. Multi-LLM (OpenAI/Claude/Ollama), MCP tools, long-term memory, multi-agent ReAct, Lark/Feishu, Wecom/Wechat, Web UI.

AI chat application that lets you create and expose RAG chatbots

Open-source React components for Agentic transparency. Trace every step of AI agent reasoning and make it visible, verifiable, and controllable.

Benchmark for measuring instrumental-convergence behaviour in tool-using LLM agents

Local-first AI workspace for macOS and Windows with cloud providers, local inference, MCP tools, memory, and artifacts