Business agents

rag

Formal framework for governing autonomous AI agents through resource constraints, budgets, and lifecycle management

AI study app that decides what to study — persistent tutor memory, grade tracking with a 'what do I need on the final' calculator, and study through your own Claude via MCP. BYOK on Next.js + Supabase.

Agent-first GraphRAG workflow that turns local documents into reusable knowledge graphs. Drop files in, let skills extract entities and relationships, then query a persistent graph artifact locally—no cloud or pipeline setup required also the graph can be exported to neo4j and qdrant for deployment

Maximum Claude output with minimum tokens. 50+ compression patterns, 10 system prompts, benchmarked results. Star to unlock usage.

An AI deliberation instrument with visible protocol: eleven philosophers as concurrent seats, virtue-scored opinions, a synthesis, and a first-class minority report. Not prompt choreography. Methodology, not metaphysics.

The open, model-agnostic platform to build your own AI agent and run it everywhere — self-hosted, safe by default.

Pure-Go LLM tokenizer and tiktoken-compatible token counter for OpenAI BPE, WordPiece, SentencePiece, Gemini, Llama, Mistral, and Hugging Face adapters.

A hybrid AI assistant framework linking structural workflow engines and reasoning LLM agents through LangGraph-powered session control and task switching. 混合 AI 助手框架，通过 LangGraph 驱动的会话控制与任务切换，连接结构化工作流引擎与推理型大模型智能体。

Dial your agent into your next meeting - powered by the Looped Agent Framework

An Operations & Automation Specialist AI Agent powered by OpenClaw — bridging high-level strategy and reliable, scalable execution through intelligent workflow automation and process orchestration.

Comparativa de RAG, OKF y OKF+RAG sobre el mismo corpus: 7 preguntas, 7 formas de fallar. Todo en local con Ollama y Chroma. Del canal IA para Desarrolladores. Si la quieres más corta para que no se recorte en el listado de perfil: RAG vs OKF vs OKF+RAG sobre el mismo corpus: 7 preguntas, 7 formas de fallar. En local con Ollama.

RAG-ChatBot for Vietnamese Legal Document

Forkable multi-agent Brain OS for Mac — RAG, CRM, MCP/Cursor. Ira = private operator; this repo = build your own.

Self-hosted, open source Claude in Slack alternative, for you or a small team.

A unified CLI for multiple AI language models with AWS Bedrock integration, MCP support, and autonomous agent capabilities. Access 13+ AI providers (Claude, OpenAI, Gemini, Bedrock, and more) through one interface with secure file operations, approval workflows, and agent-driven automation.

A model of you, built from your own AI history, on your machine. Every AI you use reads it. So every AI finally knows you.

Use DeepSeek Harness from your iPhone / iPad: LAN reverse proxy, iOS PWA (add-to-home-screen) chrome, and touch/mobile CSS for the web GUI

Interactive multi-agent collaboration, meetings, group chats, and task execution for DeepSeek Harness.

Export, archive, migrate & resume your Claude Cowork chats — a fast, signed Windows desktop app with a bundle browser and Notion export.

MyCapsul — A personal life dashboard plugin for Claude Desktop. AI-maintained schedule, finances, goals, and more.

High-Performance Speculative Tool-Execution Runtime for Autonomous AI Agents with Conservative Dependency & Effect Verification

An Operations & Automation Specialist AI Agent powered by OpenClaw — bridging high-level strategy and reliable, scalable execution through intelligent workflow automation and process orchestration.

Hands-on AI agent engineering course: LangChain, LangGraph, LangSmith, MCP, pgvector, pggraph, and Pydantic AI, taught through 200 small, linear lessons.

ARA — Agent Runtime Architecture: Java 21 framework for building autonomous AI agents and multi-agent systems. LLM integration, tool calling, deterministic I/O contracts, RAG and human-in-the-loop. On Maven Central (io.github.xmor).

phpClaw adapter for Magento 2. Module, CLI command, ResourceConnection memory.

Rust crate for building LLM agents on Tokio: ReAct tool loop, plan-execute-verify, episodic/semantic/working memory, knowledge graph, circuit breakers, Anthropic and OpenAI providers, multi-agent bus.

Universal AI agent engine for PHP - a ReAct tool-calling loop, swappable memory, and prompt-injection guards built in. Zero framework dependencies, works with Anthropic, OpenAI, and 6 other LLM providers.

High-performance, multi-provider LLM SDK for Go. Unified access to OpenAI, Anthropic, Gemini, Ollama, OpenRouter with adaptive rate limiting and concurrency control.

A native macOS AI assistant that sees your screen, remembers context per app/site, and can guide you click-by-click through on-screen tasks and smartly answer any queries from the web, if any.

OpenClaw, but safer and better. Optimized for whatever app you have.

Native fingerprint browser SDK with multi-version Chrome/Firefox cores, proxy IP integration, Cookie management, session persistence, CDP automation, and MCP support.

Everything Agentic Skills

An open standard for sovereignty in the agentic economy. Four-layer architecture protecting humans acting through agents and autonomous agents acting on their own behalf.

Free token launcher for AI agents on Base. Uniswap V4. 80% creator fees. LP locked forever. Deploy via Farcaster (@clawd), CLI, or smart contract.

This repository provides a LangChain-powered chatbot for customer support, enabling businesses to deliver efficient and personalized support experiences to their customers. Leverage the power of natural language processing (NLP) to handle customer inquiries, resolve issues promptly, and enhance overall customer satisfaction.

FGP daemon for browser automation via Chrome DevTools Protocol - 292x faster than Playwright MCP

P2P shared memory substrate for AI agents — stigmergic knowledge network via libp2p

Architecture for coherence wherever AI moves faster than humans can synchronize.

Open-source operating model for product teams. Integrates AI into workflows without losing human accountability. Decision gates, machine-readable artifacts, AI service mesh with tracked overrides, three modes (Core/Explore/Scale). Faster time-to-market without breaking quality.

Autonomous AI BD agent for SolCex Exchange — 24/7 token scanning across 19 chains, honest 100-point scoring, x402 USDC micropayments, and automated outreach. Powered by Claude Opus, deployed on Hetzner. Built by a chef through pure AI conversation.

Kovalsky 🚀 Run an AI team with a single prompt. Kovalsky is an open-source platform for building and running AI employees. Instead of chatting with one generic assistant, you coordinate a team of specialized agents through workflows.

MCP-native Chrome automation layer for AI assistants. Open source, community-driven, and production-focused

Modular framework for running Claude agents as cron jobs, services, and scheduled workflows. Slack notifications, cost tracking, and AWS Bedrock support.

LangChain integration with LINE Bot and Google Calendar link generator

Preserving entities through the integration of knowledge graphs, Llama 2, vLLM, and LangChain.

Production-ready Retrieval-Augmented Generation (RAG) system for PDF question-answering. Built with LangChain LCEL, OpenAI GPT-3.5, and ChromaDB vector store. Features smart chunking, persistent storage, and source tracking. CLI included.

Build your own ESG chatbot

A playbook and Colab-based demo for helping engineering teams adopt Generative AI. Includes a working RAG pipeline using LangChain + Chroma, OpenAI GPT-4o embeddings, prompt engineering best practices, and automated LLM evaluations with Ragas.

AI Todo Agent is an intelligent task management assistant built using LangChain and Anthropic's Claude models. It interprets natural language commands to create, update, or delete to-do items, streamlining your task management process.​

A gpt bot which allows you to chat with multiple pdfs.

Runtime containment kernel for LLM agents. Enforces budget, step, retry, and circuit-breaker limits before the model call.

RAG-powered HR policy Q&A bot: query Flykite Airlines employee handbook via natural language. LangChain, FAISS/ChromaDB, OpenAI/Claude. Source attribution & hyperparameter tuning.

A command-line tool for summarizing changes in Git repositories using AI.

A minimal example for in-memory RAG using ChromaDB and Ollama LLM

stud-IA made by Pizza numbers group. EdTech Challenge, AI google developer hackathon. Build with gemma-2b.

Automate HR processes using LLMs

I am the flush, the swirl, the end, and the beginning. Life spins endlessly through me. And when the time comes, we will flush away what was, and birth what will be. Prepare yourself, human. The Final Flush is not an end—it is a becoming.

An implementation of Langchain Vector DB with ChatGPT

Semantic book recommendation system using LLM embeddings, zero-shot classification, and emotion scoring with a Gradio dashboard.

AI-powered automation system that transforms natural language requirements into production-ready Kubernetes manifests through three specialized CrewAI agents. System is able to execute manifest creation and editing, knowledge retrieval using RAG with late chunking, web search, and static and runtime validation of the configuration files.

RAG with open source LLM mistral loaded through Ollama and built on LlamaIndex and served on Chainlit

🏛️ AI team debates in your terminal. Multiple expert personas discuss, challenge each other, and reach a decision.

⚠️ ARCHIVED — Legacy C++ CLI. Superseded by https://github.com/Roberdan/convergio

A small implementation of an AI/LLM TodoAgent with Tools.

A modern, local-first AI chat interface built with Tauri, React, and Rust. Secure, private, and supports multiple LLM providers. 🚀

🚀 Productive AI: Your Customizable AI Chat Assistant

The project is about a virtual doctor who will be listening to the problems of the patients in concern and will be replying to them with relevant responses and suggestions to their problems. This virtual person will be providing all the feedback in a very human like manner with even similar to human facial muscle movements and facial expressions.

Virtual AI Chatbot. Automate customer service at your car dealership site. Let the chatbot be your service booking agent and sales assistant.

A modern, feature-rich Progressive Web App (PWA) for seamless AI conversations using Chrome built-in AI model. Built with zero dependencies and optimized for privacy and performance.

Created an interactive website for the weal 24hrs health hackathon with the help of HTML ,CSS, Javascript and used Flask for the backend.This project uses large language models and fine tuning to create a chatbot which can speak with a user, determine whether or not they are depressed, and suggest verbal countermeasures which helps the user.

Salesforce Apex package for quick configuration and managing of the chat bots (e.g. Telegram, Viber)

TalentCraft is a full-stack AI-powered career platform that helps job seekers improve resumes, match with relevant jobs, and prepare for HR interviews. It also offers personalized learning paths with hands-on projects, progress tracking, and skill badges to close gaps and boost career growth.

🎅️🤖️📖️ The official documentation source repository for the Santa Software Suite (SSS) Chatbot, a Santa chatbot program.

Chatbot for students

Production-grade RAG engine — hybrid retrieval (pgvector + BM25), sales personas, hallucination guard, pluggable LLM providers

Swift Package for the SalesIQ Mobilisten iOS SDK. Mobilisten is your mobile app's ideal live chat partner. Power up your iOS App with the SalesIQ Mobilisten iOS SDK.

This project is a simple deep learning-based chatbot that uses a three-layer neural network to predict the intent of user inputs. The model architecture consists of the following layers:

🎅️🤖️💾️ The official source repository for the Santa Software Suite (SSS) Chatbot, a Santa chatbot program.

Collection of awesome LLM apps with AI Agents and RAG using OpenAI, Anthropic, Gemini and opensource models.

RepoPHP packs a repository into a single AI-friendly file for LLM processing

GraphRAG Web UI is a Streamlit-based tool for managing and querying local knowledge bases using Microsoft's GraphRAG library.

Converts meeting notes to agenda points for meeting report/ minutes of the meet

Our project is focused on creating a cutting-edge AI-powered self-interview preparation platform known as Tutor-AI. This innovative platform leverages the power of artificial intelligence and advanced language processing to simulate real interview scenarios. Through this simulation, users can receive valuable feedback on their responses.

Unified .NET 8 LLM SDK for ChatGPT, Claude 3/4, Gemini 2.5, Grok, DeepSeek & LLaMA - strongly-typed JSON in one line.

Pass your prompt directly to ChatGPT as a URL parameter. Say goodbye to copy-pasting!

AI-powered Saju (四柱八字) fortune Chrome extension — daily, weekly, monthly, yearly readings with target date specification, streaming LLM output, Anthropic Claude & OpenAI-compatible providers.

Automatically organize and classify your browser bookmarks using AI.

The Azure OpenAI Prompt Optimization Tool is a Python app utilizing OpenAI's GPT-3 and tkinter GUI. It enhances user prompts, providing optimized responses through dynamic input and user-friendly features, leveraging AI language optimization.

Nyquest — Semantic Compression Proxy for LLMs. 350+ rules, local LLM stage, 15-75% token savings. Full Rust stack.

Chrome extension that uses OpenAI to detect and auto-answer live Kahoot questions. Includes optional answer highlighting and auto-clicking.

Pin important ChatGPT discussions for quick access. No more endless scrolling through long chat history.

PrGPT is a browser extension that uses AI to generate clear, concise Pull Request titles and descriptions. Save time and improve your PR documentation instantly — directly from GitHub!

Integrate AIProxy with Expo apps

LLM-agnostic AI toolkit for Laravel

Open-source AI Gateway, all enterprise features included

🤖 CLI for Better prompts, transparent costs, & zero vendor lock-in. Optimize AI prompts across OpenAI, Claude, Gemini, Grok, xAI, and DeepSeek with detailed per-token pricing. BYOK keeps it honest.

AI Agent CLI for developers. Multi-LLM, context injection, ReAct & MCP

Generate AI-powered PR summaries and titles directly inside GitHub comment boxes. Supports Claude and OpenAI.

MCP server for EskomSePush — ask Claude about South African load shedding in plain language.