Business agents

Unofficial Model Context Protocol server for Alza.cz — read-only catalog browser for AI agents. Uses Playwright to defeat Cloudflare bot protection.

MCP server that connects Claude AI to Bitrix24 — CRM, tasks, disk, calendar, automations and more

An open framework for an LLM-maintained knowledge base for GTM and RevOps teams. Schema, routing, conflict resolution, and worked examples. Foundation before agents.

55 founder-grade books distilled into a Claude skill. Stack any decision through Cagan + Trout + 大败局 + 俞军 + 谢胜子 + more — multi-book perspectives in seconds.

An agentic browser for macOS. Linen opens websites, reads them, clicks, types and scrolls in the tabs you already have open. Apple Intelligence on-device out of the box, or bring a key for OpenAI, Anthropic, Gemini, DeepSeek, Groq, Mistral, OpenRouter, xAI or a local Ollama server.

Free multi-profile antidetect browser for people and AI agents. Independent, persistent browser identities.

The full-stack TypeScript framework for AI agents. An agent is a file: drop it in agents/ and it gets an HTTP route, token streaming, human-in-the-loop approvals and a typed client. React pages with file routing and SSR, OAuth sessions, Postgres, WebSockets, cron, and nine deploy targets. Apache-2.0.

Open-Source Prompt Engineering Workbench: LLMs complete tasks and score results based on prompts, and automatically iterate to generate higher-quality prompts through Q&A cycles.

TypeScript mirror of the Maida trace contract. Emit and validate Maida-native agent traces from Node. Deliberately narrow -- not at feature parity with the Python package.

Local desktop switcher for Grok CLI providers and official accounts (CC Switch-style)

Google Calendar, Gmail, Tasks, Drive & Contacts MCP server for Pi. 26 tools, single binary, OAuth login.

Teach once, replay anywhere — harness-agnostic Teach-by-Demonstration engine (Record → Compile → Replay → Verify) with OpenMausBot and DeepSeek Harness integrations.

Local MCP gateway with progressive tool discovery, description compression, and controlled access to large results.

An infinite canvas your local LLM draws on. Typed widgets, BYO model (Claude/OpenAI/Ollama), MCP-native, local-first, MIT.

Free Claude Skill that formats & audits resumes so Workday, Greenhouse, Lever & iCIMS parse them correctly — no more blank Company/Dates/Title fields.

🔥🔥🔥EMNLP 2026 Main🔥🔥🔥 EvLink: Source-grounded evidence linking for Graph RAG

基于 Go 语言 Clean Architecture 设计的 Local-First 边缘 AI 超级自动化一体机。集成本地 RAG 知识库问答、LLM 推理背压限制、无头浏览器等高并发 RPA 引擎及智能优先级调度，实现零依赖单体化安全部署。

🏆 Microsoft Hackathon 2026 — ideas, project board and submissions for the challenge 'Collaboration using GitHub Planning & Tracking Tools in the Agentic Age' (one of three challenges).

A semantic spatial workspace for AI agents.

Persistent memory for Home Assistant Assist, in plain markdown. No vector DB, no embeddings — works with Anthropic Claude, OpenAI, and any LLM conversation agent.

Browser-based VRM animation editor with human and AI agent workflows, local FBX-to-VRMA conversion, and validated export.

RAG systems, LLM agents, and production pipelines for legal and financial document intelligence.

Browser extension that adds power features to ChatGPT — file/folder upload and more

On-demand Model Context Protocol (MCP) server for Android — FCM push-woken, end-to-end encrypted via SNI-passthrough TLS, per-device ACME certs

An MCP server for orchestrating multi-agent workflows inside herdr, enabling real-time communication, pane management, and contextual handoffs.

A self-improving ML agent that compounds capability across projects through knowledge crystallization, reusable skills and shared ML/MLOps infrastructure.

A collaboration space where humans and AI agents carry projects forward through shared context, durable roles, work, documents, meetings, and handoffs.

AI agent skill for preparing Chrome Web Store submission materials

Give an AI eyes and hands on a physical computer — MCP server that lets Claude see and drive any machine through a JetKVM (screenshots, keyboard/mouse, boot media, power) on stock firmware

Open-source, self-hosted AI workforce. Meetings in, shipped work out. Multi-model AI Council. BYOK.

Evidence-backed verification for action-taking AI agents. Compile the task into a contract once, then verify every run against real state and trajectory evidence with zero model calls.

Python tarot reading engine with RAG-based interpretation assembly and optional LLM synthesis.

Seven universal skills, context file templates, global instructions, and a curated prompt library for Claude Co-work.

Minimal, provider-agnostic Python client for large language models, built on niquests.

Workshop: Build an AI-driven geospatial app using LLMs (OpenAI/Anthropic), CesiumJS, and MCP servers — 4 hands-on labs with React + Next.js

Stealth headless Chromium on your own CDP endpoint, with a prompt-injection firewall between the agent and the web.

Emergent AI city simulation — LLM agents build a living city in your browser. Three.js viewport, deterministic TS sim core, Ollama/DeepSeek agent pipeline.

The browser layer for any AI agent - drives your real logged-in Chrome, learns workflows by watching you once, replays them with zero LLM tokens. MCP + HTTP + REST.

A single-file 3D visualization of your AI agent ecosystem. Wireframe brain hull, neon neurons, live pulses, idle Earth-style rotation. No build step.

A complete legal assisstant for Hermes Agent — 1,432 skills across five layers. Apache-2.0.

Local CLI that sends a computer-use agent's Chrome through global residential and mobile IPs. npx aluvia-cli setup

Terminal bridge that drives browser AI chats and exposes sandboxed local repo tools through MCP.

Deploy AI agents on-chain from any MCP client or your browser: mint a Metaplex Core asset and register its EIP-8004 identity in the Metaplex Agent Registry on Solana. By three.ws.

Zero-weight AI gateway for Cloudflare Workers • Gateway de IA zero-peso para Cloudflare Workers. Multi-provider routing with auto-fallback, key pool, OpenAI+Anthropic endpoints, context compression & RAG search. One-click deploy.

Interactive human-in-the-loop desktop GUI & Model Context Protocol (MCP) server for AI agents

In an industry where personalization is key to customer satisfaction, your company wants to revolutionize how clients interact with real estate listings. The goal is to create a personalized experience for each buyer, making the property search process more engaging and tailored to individual preferences.

Self-hosted AI agent platform

.NET SDK for integrating with various AI model providers.

Autonomous subscription payments on Algorand. Lock ALGO in smart contract vaults, agent releases on billing day, MCP server for AI agents, Telegram bot, ARC-3 NFT receipts, on-chain proofs. AlgoBharat Hack Series 3.0.

A local VLM-powered agent that controls your computer through natural language commands

Trader Tony is a Solana-focused trading bot with advanced sniping capabilities and risk management, controlled through a Telegram interface.

Production-ready AI agent using LangGraph and OpenAI for intelligent task management with WhatsApp interface, Google Calendar sync, and automated Cloud Run deployment

Rust framework for building production-ready AI agents using actor-model concurrency with multi-provider LLM support (Claude, OpenAI, Ollama) and built-in tool use

A cost-aware, multi-LLM routing agent using Gemini as the default and external models on demand.

Beyond the Sum: Unlocking AI Agents Potential Through Market Forces - Paper examining infrastructure requirements for AI market participation

iii worker that makes every registered function available to AI agents through MCP and A2A protocols.

KSI Ξ Agent Improving Ecosystem. A graph-based orchestration system for evolving AI agents through collaborative improvement and meta-optimization

Production middleware for MCP servers. Auth, sessions, health checks, graceful shutdown, transport ergonomics. Wraps the official Model Context Protocol SDK.

Kernel contract for the Life Agent OS — canonical types, runtime ports, event taxonomy, policy gates. The genome that all subsystems implement.

A Chrome Dinosaur game clone powered by NEAT (NeuroEvolution of Augmenting Topologies) that evolves neural networks to play and master the game through generations of training. Watch AI dinosaurs learn, adapt, and overcome obstacles in real-time with visualized network structures.

Exploring the Emergence of Complex Systems through Individual Decisions and Relationships

Large Language Model (LLM) chatbot with a custom knowledge base

This is a Streamlit app that leverages LangChain, a language processing toolchain, to generate responses based on user prompts and perform document similarity searches using Chroma.

Stay ahead with KnowEdge – giving your knowledge an edge through AI-powered learning and smart insights.

Simple Generative AI enabled Streamlit web application that answers general questions from PDF documents provided to it.

In this project, I created an application using Google Gemini Pro and Langchain to process multiple PDF documents. We will use FAISS vector embeddings to enhance document processing capabilities.

This is an implementation of cover letter generator using LLama3.1, LangChain, ChromaDB and Streamlit

Lots of little applications showing langchain at work

PDF Question Answering (QA) powered by ChatGPT

Build an AI Powered Mobile Chatbot with Expo and Cloudflare AI

Discover knowledge with ease using - AzureOpenAI, Chroma, and Langchain. This solution generates a knowledge base from a given URL and efficiently responds to queries, streamlining the information discovery process.

RAG using Ro-LLM, Langchain and ChromaDB

KT 에이블 스쿨 5기에서 진행한 프로젝트 내용들입니다

Streamlit app for Question Answering uploaded CSV using Retrieval-Augmented Generation

Create long documents through RAG and Chain of thought by using Langchain, OpenAI, Pinecone.

A typed, permission-enforced language for orchestrating AI agents. Compile-time contracts, built-in guardrails, multi-backend dispatch.

Multi-agent framework for generative AI.

OPUS — bio-inspired multi-agent swarm architecture for collective LLM reasoning. Open-source. Ars Magna.

This extension aims to allow agent-based models to account for norms. During plan generation, agents must be able to represent and reason about norms. The end-goal is to be able to describe a planning problem with norms endowed by its organizations through the various roles that the agent must fulfill, and see how it affects its plans.

Conversational business process runtime for AI agents via MCP

KG RAG vs VectorDB vs (pure agentic)

The Developer's Micro-OS — Context management, semantic search, and AI-powered browsing for software engineers.

A universal multi-bridge MCP hub connect any LLM to n8n, Blender, Notion and more through a single pedagogical gateway

Rook — your strategic AI advantage. Open-source personal assistant in Telegram.

Programmable SMS Quickstart & Twilio Autopilot

AI-powered chatbot sidebar for Google Sheets, integrating multiple AI providers (OpenAI, Anthropic, Google, etc) for intelligent responses directly within your spreadsheets.

The Apollo Adlux Hospital RAG Chatbot system, Built on the Ollam 3.2 LLM, this chatbot leverages Retrieval-Augmented Generation (RAG) to offer accurate, contextually relevant answers by pulling information from hospital resources and FAQs.

【AIGC 聊天记录一键导出】Share your favorite chat messages in 1 second.

Making the web easily acccessible through chat bots. Created in 24 hours at #tamuhack2020

A discord chatbot powered by Openai's GPT-3, with several other features ready to be deployed through heroku!

Web3GPT is an AI-powered smart contract development platform that combines Large Language Models (LLMs) with specialized AI agents to streamline blockchain development.

This is a Telegram bot for audit contracts in blockchains (Ethereum, BSC, Polygon, Avalanche, Fantom)

Send ChatCPT chat to Figshare and get a DOI

A Bible verse posting assistant bot for Slack.

🚀 Automatically generates actionable tasks from your meetings using GPT-4! 📋 Stay organized with AI-driven insights, real-time updates, and easy PDF exports. 💡 Empower your team and enhance productivity! 💪✨

🚀 Build and understand a Large Language Model from scratch using PyTorch through hands-on notebooks focused on core Transformer concepts.

マルチAI対応チャットクライアント。ZundaGPT2の読み上げなし版なのだ。仕事や勉強に使うならこちらなのだよ。

A chrome extension for open AI