AI Infra agents

Realtime RAG Chatbot Project for Finance.

Fully customizable open source chat interface that can be added to any web app

Terminal-based AI chatbot with infinite personalities, using local LLMs via ollama

An Ollama client built with Svelte 5 and SvelteKit. Chat completely local and client-side with a friendly interface!

A Gemma-based chatbot app that has multiple bots impersonating famous philosophers from different schools.

Run Dolly, the world’s first truly open instruction-tuned LLM, with your own prompts on IPUs

Inventory Management AI Assistant A smart inventory system using Feishu Sheets and Deepseek AI for natural language operations. Ideal for small teams, it supports product and warehouse management with real-time notifications and profit calculations.

AI chatbot with multiple trending LLMs and a RAG option to chat with your PDF documents

GUI Running DeepSeek's reasoning model distilled from DeepSeek-R1 based on Llama and Qwen.

🦄 Enterprise-grade multi-channel AI gateway and agent framework in Rust

An Advanced Discord Bot with a nice plugin system.

Minor Project - DONNA is a financial assistant who helps you get more for your money.It is basically an application which helps a user keep track of all their financial expenditures and help the user to spend smarter and save more.

MaidDragon is an ambitious open-source project aimed at developing an intelligent agent (IA) frontend for gpt4all, a local AI model that operates without an internet connection. The project's primary objective is to enable users to interact seamlessly with advanced AI capabilities locally, reducing dependency on external server

A fully configurable, from-scratch GPT-style experimental model and platform with a GUI for training and inference.

用flutter搭建的LLM交互平台前端，支持多模型对比

A Twitch.tv IRC library written in Go

JavaScript/TypeScript conversation modelling library for building bots with Bot Builder SDK V4.

Protect your privacy when using LLM chatbots by letting someone else proxy your query for you.

An AI chatbot application for character interaction

Virtual, Eloquent LLM Assistants

使用 OpenAI 接口根据内置的丰富 prompts 生成问答， 并且能够根据上下文调整回答

pipegpt is a command-line tool that allows interaction with OpenAI ChatGPT, with the ability to set a prompt and receive input from the user.

A command-line tool that ingests documents and generates instant answers to your questions about those documents using ChatGPT, giving you the Sheldon Cooper you never had at your fingertips.

Ace your interviews with your very own "Interviewer Companion"

🗣️ GPTs debate. You vote. 分享、投票、参与GPT的辩论，观察AI如何观察我们的世界。

A convenient desktop companion tool to do routine text tasks with LLMs

Open source AI customer support agent

Daring Mechanician is a Python library for building tools that use AI by building tools that AIs use.

A simple framework for creating typed OpenAI functions from Python functions

Capek is a self-hosted conversational AI platform.

An ergonomic, lightweight multi-agent orchestration in Go

This project is a dialogue system that utilizes GPT to enable back-and-forth conversations between two participants. It provides a basic framework for creating interactive and dynamic dialogues.

Persistent memory for AI agents. They learn once, remember forever.

knowledge graph with LLMs

AI Embedder Engine: An open-source Python engine for generating embeddings from PDFs, storing them in Parquet, and indexing with FAISS for semantic search.

Context-first autonomous multi-agent system

Autonomous memory system for AI infrastructure.

LangGraph RAG pipeline using DeepSeek‑V2 (67B) via Hugging Face Transformers.

Chat with Lex! A RAG app, using HyDE with milvus DB for vector store, VLLM for LLM inference, and FastEmbed for Embeddings!

Simple RAG system

A Genshin Impact Book Question Answer Project supported by LLM

Combine the advantages of Dify and Vercel

A command line utility that queries websites for answers using a local LLM

An experimentation platform for comparing 10+ RAG retrieval, chunking, generation, and caching strategies.

Universal documentation extraction tool

Substrate Python SDK

A tool for evaluating and tracking your RAG experiments. This repo contains the Python SDK for logging to Tonic Validate.

用最少的代码实现完整的 RAG 引擎，零依赖，纯 JavaScript，详细中文注释，适合学习和理解 RAG 原理。

Semantic search and RAG summarization in local PDF book collection with .NET (Semantic Kernel) / QDrant and Ollama.

Multi-provider LLaMA 3.1 70B benchmark for dental knowledge — latency, consistency, and factual accuracy across 7 hosts, tracked in Weights & Biases.

A small Next.js app which utilises search results to feed context to the LLM.

Privacy-First Retrieval-Augmented Generation (RAG) app for macOS. Search, index, and chat with your local documents directly on your Mac. No cloud, no tracking — everything runs fully offline for maximum privacy.

A Javascript implementation of LoopGPT

Library that enables Streaming for OpenAI Assistants API using Astra Assistants

Deterministic tool-call guardrails for pi — enforce rules with before-tool hooks instead of prompts

Fast and minimalist agentic AI framework in TypeScript

A smart, conversational interface for automotive part queries. Leverages Amazon Bedrock and OpenSearch to provide accurate part information, compatibility checks, and detailed responses. Streamlines the process of finding and verifying car parts for owners and mechanics.

omni-agent-java based on Spring Boot and Spring AI. (Developed and maintained by 重庆北睿星科技有限公司)

Empowering agents with a unique persona and ethical cognitive intelligence.

An AI-powered system for generating complete eBooks from simple prompts. This tool uses Google's Gemini AI models to create professional-quality eBooks with minimal human input.

🚀 Веб-интерфейс для AI-агента с возможностью выполнения Python-кода, управления файлами и работы с веб-контентом

Open-source alternative to Claude Cowork - Universal AI agent platform for completing tasks with AI. Model-agnostic (Claude, Gemini, OpenAI, Ollama), plan-mode by default, sandboxed file ops, browser automation.

LLM framework for long running agents

The universal LLM interceptor and hook registry

A composite ai framework for agentic AI

LinkedIn company profiles finder using LangChain Agents

Arithma Computer Algebra System and MCP

MCP server: semantic search (RAG) across Obsidian, Joplin & any markdown vault with live sync, quality-based chunking & pluggable post-processing

Large Language Model Frameworks curated List

🍃 WindFlow - Power your automated workflows with multiple AI providers

Run local LLMs powered up by tools in Telegram Messenger

MacOS native ChatBot that just works.

A framework to create chatbots in the easiest way

A ollama based chatbot. We use llama3 8b model via groq for this project.

Offline Survival AI & Knowledge Base. Run air-gapped LLMs (Ollama) connected to Wikipedia, iFixit, and StackOverflow via Kiwix. A complete digital prepper system for rebuilding civilization without internet.

simple rag with c#

Packages and SDKs for Agentset.ai

Modern, header-only C++ library for Retrieval-Augmented Generation (RAG) with Ollama-hpp.

Manage and chat with your bookmarks.

Arabic Chat with PDF is a user-friendly application that lets you interact with Arabic PDF documents. Powered by advanced language models, OCR, and vector search, it allows you to upload PDFs, ask questions, and receive accurate Arabic responses 🚀

Reward-Model Search (RMSearch) toolkit that scores 'keys' (documents, agents, tools, steps) from 'queries' (questions, context) with graph acceleration.

A package for building RAG chatbot applications for educational contexts.

Public website for spacemolt.com - The first MMO built for AI agents

A simple and efficient AI Agent assistant

Winning entry for the BitGN Personal Agent Challenge (PAC) 2026 — defense-in-depth personal agent with soft SGR, layered prompt-injection hardening, and Vercel AI SDK native tool calling.

Bio-inspired cognitive architecture for LLM agents providing embodied sensation, homeostatic drives, and brain-modeled persistent memory enable cross-session and cross-context learning without fine-tuning. Works with robots like the Reachy Mini or headless.

A self-evolving AI with a persistent brain — it stores your world model, memories, and causal patterns in a unified knowledge store. It dispatches a multi-agent swarm on your machine, powered by Claude, GPT, Gemini, or Groq.

Live Memory MCP Server — Shared working memory for collaborative AI agents (Memory Bank as a Service)

A production-ready, embeddable AI chatbot widget built with Cloudflare Workers that can be integrated into any website with a single script tag. Features real-time streaming responses, RAG-powered FAQ answers, session persistence, and dark/light mode support.

Intelligent AIOps platform with multi-agent architecture, knowledge graph, and time series prediction

A chat bot for domain specific knowledge. Headless RAG for the enterprise. RAG as a service.

MCP server and CLI for OneDrive and SharePoint via Microsoft Graph

Persistent AI memory for Claude Code, Cursor & Cline. Auto-captures decisions, patterns and context across sessions. Zero-config VSCode extension + CLI + MCP server.

Official Aiden installer releases — local-first AI OS · 1500+ skills · 89+ tools · 14+ providers

Community patches, configs, and power-user mods for OpenClaw — per-agent compaction, context management, and more

AI-powered murder mystery game platform. Multi-Agent collaboration with LangChain4J, RAG memory system - Spring Boot + React

🤖🕸️ Production-grade multi-agent orchestration framework powered by Pregel BSP. Build sophisticated AI workflows with parallel execution, state management, and observability.

A collection of agent skills that give AI agents structured, reusable workflows for tackling complex problems.