Business agents

Evaluate LLM agentic capabilities through combat games

A beautiful terminal-based AI chat interface built with Textual and LangChain

AI agent engine with 22 chat channels, 65 tools, and 15 skills. Self-hosted, local-first, works with any LLM provider.

AM — autonomous AI agent system. The agent does the work and ships the PR. ⭐ Star to follow along.

🦆📜 A minimal, deterministic, runtime-agnostic DSL for orchestrating workflows through declarative YAML specs.

Local-first AI operating layer: control plane, subsystem contracts, and executive War Room for governable multi-agent systems.

Open-source library of methodology-shaped SRE skills for AI agents (Apache 2.0)

The complete open-source LLM curriculum — prompt engineering, RAG, fine-tuning, agents, and production deployment. Beginner to advanced. Python. Free forever.

AI employee for your team — delegate real work in Slack and a team of Claude-powered agents gets it done. Built on the Claude Agent SDK with OS-level sandboxing, MCP tools, and a plugin architecture. TypeScript/Node.

Full-stack GraphRAG application with Django backend and React frontend. Build knowledge graphs, detect communities, and chat with documents using hybrid retrieval and LLM-powered reasoning.

An AI agent harness built for workflows.

Build your own frontend AI agent with Chrome

Model Context Protocol (MCP) servers that give AI agents local access to macOS apps: Mail, Calendar, Reminders, Messages, Contacts, Notes, Shortcuts, Files, System, and Maps. Unified server plus focused single-app servers.

RAG demo: question-answering over the OCP 2025 financial report using LangChain, Chroma & bge-m3 embeddings, plus LLM-as-judge faithfulness scoring.

Local-first Agentic RAG engine - GraphRAG, hybrid retrieval (BM25 + dense + RRF + rerank), multi-agent orchestration, MCP-native, 100% local inference via Ollama.

Self-hosted Claude Managed Agents control plane on Buddy Sandboxes

The Open-Source Automation & Omnichannel Webhook Gateway for Personal Zalo

A Schema-first agent layer for Foldkit: project an application's Model and Message union into one contract, then expose it through WebMCP, MCP, or in-app agents.

Official Roblox Studio plugin for Metain

AI-powered multimodal chat app with real-time responses, file support, token tracking, and dark mode. Built with Next.js. Open source under MIT.

A sophisticated trading system leveraging local LLM deployment through Ollama, distributed computing with Apache Spark, and vector-based episodic memory using ChromaDB to make intelligent trading decisions.

Chatbot-GPT, powered by OpenIM’s webhooks, seamlessly integrates with various messaging platforms. This tool enables private and group chats with bots, enhancing interactive communication. It delivers quick, automated responses, ideal for optimizing customer service and dynamic discussions, meeting diverse communication needs.

A Swift macro that allows you to call your function from Function Calling.

A simple agent powered by LLMs that performs tasks.

Chat with PDF powered by Anthropic's Claude AI on Amazon Bedrock!

GRAG is a simple python package that provides an easy end-to-end solution for implementing Retrieval Augmented Generation (RAG). The package offers an easy way for running various LLMs locally, Thanks to LlamaCpp and also supports vector stores like Chroma and DeepLake.

Streamline hiring by connecting AI agents that evaluate, negotiate, and schedule interviews to reduce time and improve candidate fit.

Sample App to integrate SalesIQ Android SDK (Mobilisten)

Oura Ring Model Controller Protocol (MCP).

synchronizes a directory with e.g. markdown files with a knowledge base in OpenWebUI

Shoe store WebMCP Demo for Google Chrome

Framework to talk to AI models and intelligently route

LLM-maintained markdown wiki on a git-native substrate. Obsidian-compatible, three-layer retrieval (grep + BM25 + embeddings), explicit supersession. Built on js-doc-store, js-vector-store, js-git-store.

[ACL 2026] An interactive and comprehensive legal agent benchmark

A Chrome extension that enables you to export WhatsApp Web conversations and generate AI responses using Google's Gemini AI.

A prediction market trading agent for Kalshi, accessible via iMessage. Built on Linq Blue and Claude.

Give AI eyes and hands on your desktop. Open-source MCP server for desktop automation — screenshots, UI control, browser automation, OCR. Works with Claude, Cursor, and any MCP client. macOS + Windows.

Open-source AI agent - any LLM, any MCP server, any channel. Self-hosted, autonomous, multi-tenant.

The AI that refuses to think for you. Open-source anti-deskilling framework implementing human-AI collaboration protocols from the Cabitza lab (Milano-Bicocca). Four modes: Forge, Anvil, Crucible, Executor.

Claude skill for FS25 mod development — answers verified against the game's own decompiled engine source (1,842 files). 1,413 classes, 119 MessageTypes, the mod sandbox, 30+ patterns, 20+ pitfalls. Works without a local decompile.

Ask Claude about your WHOOP recovery, sleep, strain and workouts. Self-hosted MCP server with sign-in.

AI agent toolkit for Compose multiplatform

Chatbot-GPT, powered by OpenIM’s webhooks, seamlessly integrates with various messaging platforms. This tool enables private and group chats with bots, enhancing interactive communication. It delivers quick, automated responses, ideal for optimizing customer service and dynamic discussions, meeting diverse communication needs.

Benchmarking RAG vs GraphRAG vs Compressed Knowledge Graphs on the McCreary Intelligent Textbook Corpus

Hybrid RAG over Indonesian legal documents (UU, PP, Perpres, court decisions) with local LLM via Ollama.

Ready-to go claws (NVIDIA NemoClaw + OpenClaw) across multiple sectors. Run on your ibl.ai instance or anywhere else.

AI-powered support operations platform with multi-tenant isolation built with Mastra, Kinde, Convex, and Resend.

Drop-in OpenClaw/NemoClaw agent configuration for the ibl.ai Financial Services segment — Advisory Assistant orchestrator plus 12 specialist subagents.

Shrink LLM prompts by 40-70% while preserving meaning, semantic chunking + extractive summarization

A native Windows app where multiple AI models collaborate in a structured, phase-driven workflow with defined roles, enforced authority on the software level, and a shared artifact to solve a user task.

Token-efficiency linter for LLM prompts and payloads

Local-first Agentic RAG engine - GraphRAG, hybrid retrieval (BM25 + dense + RRF + rerank), multi-agent orchestration, MCP-native, 100% local inference via Ollama.

The AI frontend you can reshape just by asking.

Frame-budget compiler and diagnostics for three.js games: batches naive scenes, measures every frame cost, explains what to fix. CLI and MCP for AI agents

R's AI DocManger: An AI Documenet Management System

🌐 Connect people and manage tasks with AILinkX, your all-in-one digital life operating system built on advanced AI technology.

Frenrug on-chain AI agent smart contracts.

Production-ready AI agent configurations and orchestration patterns

Your mobile app's ideal live chat partner. Power up your iOS App with the SalesIQ Mobilisten iOS SDK.

Sales Agent Streamlit chatbot

Use chrome browser. AI + AR chatbot developed in JS. You can find the Repo with backend from here... https://github.com/AnubhavMadhav/J.A.R.V.I.S

AI agent that helps you learn Tinygrad and updates you on the bounties

Metaprompt is an AI-powered prompt generator developed by Anthropic. This is the unofficial Metaprompt Community Github repo. All PRs are welcome 🙂

Vercel AI community package for using anthropic through vertex ai.

BPE Tokenizer implementations in C# for Anthropic, OpenAI LLM offerings

A repository dedicated to exploring, experimenting with, and applying Generative AI concepts and tools in practical, everyday scenarios.

Setup an MCP server in 60 seconds.

PolyG: Adaptive Graph Traversal for Diverse GraphRAG Questions

Implementation of Anthropic agentic workflow's using Google Gemini 2.0 Flash Experimental

Fully featured terminal AI chat for Anthropic's Claude

Async Python runtime for agents that survive failure, persist evidence, and pause for the real world.

A flexible foundation AI system for creating A2A-compatible autonomous AI agents that can collaborate, reason, and execute complex tasks through standardized agent-to-agent communication protocols.

🎨 Generate high-quality PPTs with AI, featuring smart transitions and interactive playback for seamless presentations and engaging visuals.

AI-powered Git Assistant for CLI

Give Your AI a Body — Desktop companion powered by OpenClaw. VRM 3D character lives on your desktop.

Sample application for Enterprise MCP server architecture. Built with Workato Enterprise MCP. Hospitality use case, with customer- and employee-facing agentic experiences.

Local-first AI workspace for law firms: case files stay on your machine, local or chosen cloud model, hash-chained audit trail with its own verifier. 9 editions. AGPL-3.0.

مكتب عمل شخصي على الماك: يشتغل على مجلد تختاره أنت، وينفّذ مهامك المتكررة بمهارات تكتبها بنفسك، عبر النموذج الذي تربطه · A personal work desk for macOS: it works inside a folder you choose and runs your repeat tasks through skills you write yourself. Arabic & English. A صدقة — free and open source.

Build local Dify workflows through real-time conversation in DeepSeek Harness

Assemble the AI council you can't afford to hire. Deliberon — structured multi-agent AI deliberation for Windows. Installer downloads + release notes.

Open-source, supervised AI browser agent for Chrome. Plan, navigate, click, type, and verify web tasks from a side panel with your own OpenRouter key.

MCP server for git repositories: local git in-process via gitoxide, plus GitHub, GitLab, Gitea and Forgejo through their CLIs

Give an AI agent a spare Android phone: self-hosted MCP, companion APK, live web control, and Chinese app walkthroughs.

Streamlit OpenAI app to chat with custom text documents of all kinds

LLM, Fine Tuning, Llama 2, Gemma, Mixtral, vLLM, LangChain, RAG, ChromaDB, FAISS

Python-based Legal Advisor harnesses the power of advanced Language Models for comprehensive legal guidance 📚. Uses LLM internally to give legal advices 🚀

CityPulse is an AI-powered platform that lets citizens report urban issues through a simple chat conversation. Built with Mistral for Mistral AI Global 2026 Hackathon.

A bot for Nextcloud Talk that creates Jitsi meetings.

A RuneScape Companion and Discord bot that synchronizes a RuneScape Friends/Clan Chat with Discord chat

Paper lists about 'Constitutional AI System' or 'AI under Ethical Guidelines'

Lua interface for working with multiple generative AI providers

A Lisp with first-class LLM primitives, implemented in Rust

AI-powered dev diary from your git history. One command, zero effort.

Multi-LLM AI debate platform — orchestrate structured debates between Claude, GPT, and Gemini with consensus scoring and synthesized verdicts.

MCP server empowering AI assistants with real-world capabilities: Gmail, Calendar, Tasks, Git integration, and note management. Bridges AI assistants to external services through standardized protocol with secure authentication.

A lightweight LiteLLM server boilerplate pre-configured with uv and Docker for hosting your own OpenAI- and Anthropic-compatible endpoints. Includes LibreChat as an optional web UI.

Tools, libraries, papers, and patterns for reducing the cost of running large language models in production.

A Telegram bot that allows you to create your own ChatGPT in Telegram.