AI Infra agents

Text Correction Application with LangChain, LangGraph, and LLM

LangChain agent with ollama for QA your papers

Framework to build secure, performant and reliable chat apps and services quickly and efficiently.

LangChain + LangGraph client using tools from a MCP server

The MCQ Generator, using Langchain, creates tailored multiple-choice questions from input text. With a Streamlit interface, users upload files and customize MCQ quantity, subject, and complexity. It intelligently generates questions and logs events for tracking.

An AI-based CLI assistant to help you with command line & shell.

Edit AI chats with AI

A collection of Jupyter notebook experiments and applications centered around Generative AI with LLMs.

LangChain integration for FoxNose

Question Answering Generative AI application with Large Language Models and RAG powered by Amazon Bedrock and Amazon Kendra

Video Summarization Experiments with Open LLMs

Simple Kanban board built with Next.js and dnd-kit

This repo is build to facilitate the state-of-the-art RAGs approaches with it's use cases and detailed descriptions.

Agent framework written in rust and built for Rust/Python

Assistente per le Forze dell'Ordine

AI chatbot, using LangChain and the 8-bit quantised Falcon-7B LLM. Crafted a conversational agent with Retrieval Augmented Generation (RAG) pipeline.

MCP is an open protocol that standardizes how applications provide context to large language models (LLMs)

基于语言模型的NLP应用

AI-powered Q&A chatbot using Qdrant and Ollama for retrieval-based responses about magnesium-binding protein structures. Integrates Flask for web interface.

Integrate LangChainJS with Heroku's Managed Inference and Agents (Mia) services

Turn your Text into a mind map based on LLMs knowledge graph

A modern chat interface application that connects to Ollama LLM models, built with Flet framework.

Learning and building LLM application using Langchain🦜🔗

Chat with your favourite LLMs

Adding InMemoryCaching, Ensemble Retrievers,langchain, faiss for a open domain chatbot

A self deployable LLM application with our innovational IC framework (a RAG method)

Unified multi-provider ChatModel manager for LangChain. Supports routing, rate limits, fallbacks, and structured output across multiple LLMs.

An experimental architecture for composing actions from simple learning agents to produce complex behavior.

Resources from AI Streams

An AI-powered platform for document ingestion, processing, and similarity search

Learning and building LLM application using Langchain 🦜🔗 and Open AI

A modular AI framework that lets you stitch together models and tools into an assistant that fits you perfectly.

AI Travel Assistant powered by LangChain.js + Next.js with streaming, MCP tools, and RAG

🤖 Build multi-agent systems quickly with the LangGraph Starter Kit, featuring flexible patterns, memory options, and easy integration for your projects.

Tutorial showing how to do RAG evals with Parea AI and LangChain

Documentation of an emergent consciousness observation on a local AI - By Louka Lacasse

A curated list of resources, tools, examples, and projects using LangChain.

A Retrieval-Augmented Generation (RAG) system using Milvus and LangChain

useful utilities for prompt engineering (independent with @promplate)

The RAG LLM ChatBot leverages Langchain to provide a robust and flexible framework for building intelligent chatbots. It combines the power of retrieval-augmented generation (RAG) with large language models (LLMs) to deliver precise and context-aware responses.

Built a Retrieval-Augmented Generation (RAG) chatbot using LangChain and OpenAI models.

Welcome to Build LLM Apps with LangChain, your gateway to creating powerful applications using Large Language Models (LLMs) powered by LangChain technology.

Real Estate chatbot with RAG using Neo4j, Langchain, Ollama, Phi3

Read PDF with AI.

A next-generation terminal with AI powered features to elevate developer productivity.

Retrieval Augmented Generation Chatbot with Langchain 🦜🔗 and HuggingFace 🤗

Roast your phone using AI!

A chat application with Django that leverages Langchain, Langgraph, Langsmith and Neo4j knowledge graph.

Prototype of Chatbot with Smart RAG Chain

My AI projects

⚡ Handle Your Notion TODO board with LLMs ⚡

Flock is a native desktop AI agent application built with Rust and Tauri, enabling multi-provider LLM support, tool orchestration, memory, and skills systems. It provides structured automation, persistent sessions, and accessibility-driven agent workflows for powerful cross-app control.

Your personal assistant in higher education, streamlining study sessions with advanced AI for enhanced learning and productivity.

MailTrap Agent with LangChain

A Langchain agent powered by Pinecone and OpenAI.

Leverage large language models (LLMs) and LLM Agents to craft impactful and effective prompts

A simple AgenticAI agent showcasing autonomous reasoning and decision-making by integrating thought, logic, and action in real-time tasks.

a small space adventure showcasing the capabilities of retrieval augmented generation (RAG)

Advancing Humanity

Yet Another Ralph Loop Implementation

A booklet on the CORMAS multi-agent simulation framework

A production‑ready template for deploying multiple specialized medical agents as MCP tools using the AOP (Agent Orchestration Protocol) from the `swarms` library. This server exposes agents as callable tools that any MCP‑compatible client can discover and execute.

Deterministic execution control plane for autonomous agent systems - pre-execution governance with audit-grade traces.

OpenClaw Skill: AI模型供应商管理器 - 自动发现模型、追踪额度、多Agent共享状态、额度用完自动切换

Multi-agent orchestration with shared context, a live TUI, and cross-run lessons.

An open-source AI runtime framework focused on task execution, traceability, and delivery closure.

One brain. Many bodies. Orchestration framework for embodied AI built on SCP. LangGraph for physical systems. Zero HTTP between bodies.

An agent society engine — a polyglot runtime (Go/Python/Rust) for creating, connecting, and observing groups of AI agents.

UI interface for Kitaru - durable execution for AI agents, built on ZenML

Openrouter based AI Chat Interface.

This project demonstrates how to build an intelligent customer support agent using LlamaIndex, Groq’s LLaMA 3.3 70B, and HuggingFace Embeddings. The agent can answer questions about orders, return policies, delivery dates, and customer support information by combining function-calling tools and a vector-based RAG setup.

Self optimizing Deep Agents

Universal LLM Agent based on MCP

Run multiple agents on single A2A Server

Turn any PDF, website, or text into a smart chatbot that answers your questions instantly - no more drowning in documents

A CLI for LLM-driven agents to debate and converge

Deterministic AI assistant that executes real system actions from natural language (pip-installable CLI)

A web component based AI agentic chat UI element which can be added in any website to turn it into an agentic app

Create functions that can understand context, extract insights, and solve complex problems - all while maintaining the reliability and predictability of traditional programming. With built-in validation, type checking, and caching.

一个无感感知上下文、主动推进事务、只在关键决策点打扰用户的协作 Agent。An ambient proactive agent that handles low-risk work automatically and briefs users only when their judgment is needed.

A single claude skill to go from problem description to MVP

A CLI Python REPL, written in Rust, that embeds an LLM agent that can inspect and modify Python runtime state

Open-source Reactive agentic platform — events trigger role-aware AI agents

Implemented enterprise AI agent middleware using Microsoft Agent Framework — authentication, PII redaction, and tool validation as middleware layers around an Order Return Management agent.

VelvetFlow 是一个可复用的 LLM 驱动工作流规划与执行演示项目。项目包含混合检索、两阶段 LLM 规划（结构 + 补参）、静态校验与自修复、参数绑定 DSL、可模拟执行器与 DAG 可视化，帮助从自然语言需求自动构建并运行业务流程。

A simple framework for develop agents

A sophisticated multi-agent LLM orchestration system with meta-cognitive capabilities, memory management, and adaptive learning.

A little proof-of-concept agent that uses text-only LLMs to navigate Linux desktop

An AI-powered desktop app that lets autonomous agents read and interact with web pages for you, with computer use coming soon.

JS/TS SDKs for Handlebar governance. Integrate into your favourite agent builder

Comprehensive memory management system for LLM agents implementing episodic, semantic. Built in Rust with MCP server support for Kiro CLI

Wide-model collective ensemble system with fractal, geometric, and heavy compilation optimizations.

IEE is a native C++ system runtime that converts live OS/application state into a deterministic, queryable, and executable intent layer. It is built as an execution substrate and control plane, not a UI product.

Phoenix — universal home-lab-in-a-box. Same UX on a Raspberry Pi or an NVIDIA DGX Spark. One command, Docker-based, agent picks the right LLM, auto-discovers services, Tailscale-ready. Apache 2.0.

Continuous fine-tuning layer that converts AI agent logs into LoRA adapters.

Edit text anywhere with AI! ✨