Business agents

Llama Agent Kit is an open-source Node.js toolkit for building memory-enabled AI agents powered by Ollama. It supports conversation threads, lightweight JSONL memory, and tool calls (e.g., weather, time, reservations), making it easy to integrate LLM agents into your own projects.

Program chat completions from a POSIX shell

MCP server for TDM payment integration. Enables AI agents to handle payments through Model Context Protocol.

A shell widget that generates bash commands from natural language using Claude

🧠🔨 Brain Break is an AI-powered terminal quiz app.

🤖 cool CLI AI powered tool 🤖

TypeScript AI toolkit

AI client for Ollama, Groq, Anthropic and OpenAI

Learn the fundamentals of LLMs & Retrieval-Augmented Generation (RAG) through hands-on notebooks, then build your own AI-powered Q&A chat app using Streamlit. Bring your own documents and get started with our video guide!

Taxonomy Completion with Embedding Quantization and an LLM-based Pipeline: A Case Study in Computational Linguistics

LegalFlow Application for Morgan & Morgan challenge for Knight Hacks 2023 Hackathon

Demo solution of Neo4j Graph DB with Streamlit UI app, powered by Azure AI Foundry models and orchestrated by Langchain.

Production-ready Python framework for AI agents with built-in guardrails, audit logging, cost tracking, and hybrid RAG. Supports OpenAI, Anthropic, Gemini, Ollama. By NichevLabs.

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.

Memory plugin for OpenClaw. Agent's memories strengthen through use, fade when unused, and consolidate overnight.

AI-first subjectivity kernel for agents — persistent emotional state, relation dynamics, adaptive reply loops. Zero extra LLM calls.

Sovereign agentic CLI — Textual TUI, multi-provider LLM mesh, persistent sessions, skills, MCP, Telegram gateway, autonomous yolo mode

SWI-Prolog as a logic calculator for LLMs — MCP server and Python library

Glass Box Framework — runtime constitutional verification for AI answers. Trust Cards with claim-level reasoning chains, formal ECS scoring, the 7-angle Glassbox Court red team, and deterministic audit logs. MCP-native.

A lightweight Rust library for building LLM agents.

Build production AI agent runtimes in Rust with typed tools, provider-neutral LLM adapters, streaming, storage, and observability.

Drop-in OpenClaw/NemoClaw agent configuration for the ibl.ai Higher Education segment — Campus Assistant orchestrator plus 16 specialist subagents.

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

A lightweight (10 MB) AI IDE alternative to Cursor and Windsurf

Agentic AI chat plugin for Obsidian. Two providers, best models, no bloat.

The coordination layer for Multiplayer AI

🐇 The 'RabbitHole' framework provides the tools for asynchronous A2A communication and task management. 📡🐇 ✨ Build powerful AI agents that communicate and collaborate.

1 universal function to do anything with LLMs. Painlessly swap between 100+ LLMs.

🛡️ Safe AI Agents through Action Classifier

My dotfiles. Dedicated to building an AI-native Linux system.

This is a repo where I, OVP, am trying to learn thru allegories...

Multi-agent orchestration runtime with task board, flow engine, budget control, MCP integration and real-time dashboard. Self-hosted on Linux/macOS.

FailSafe: An autonomous fact-checking framework leveraging Multi-Agent LLMs and Structured Argumentation Graphs (SAG) to verify claims with deep-web retrieval and reasoning.

Generate an optimal path on a map a la Traveling Salesman Problem to hit different landmarks in an input city using Cloudflare Workers AI (using LlaMA-3.1), LangChain (for prompt templates and comma separated list output parser), Mapbox to create a map and get information about cities and landmarks in those cities, and Folium to edit the map.

AURA is a universal constitutional AI framework with quantifiable ethics. Created by Mackenzie Clark (Sovereign Architect). Works across any LLM without retraining. Three metrics—Trust Entropy, Value-Transfer Ratio, Purpose Alignment—guide decisions. Includes Vector Inversion Protocol.

An MCP base layer running on ESP32 that exposes hardware capabilities to AI. AI reads logs, pushes scripts, swaps drivers, and iterates device logic directly through MCP tools. The base layer holds steady, AI brings the intelligence.

SFCC UCP Cartridge

计算机网络课程设计, 基于TCP协议的简易聊天机器人, 开发语言Python3, 初期版本只能在终端中运行(CLI), 最终完成版为客户端编写了"简陋"的图形界面, 使用Qt5(即PyQt5)实现

Advocate.ai - The Legal Search Engine of India

Streamlit Multi AI Platform Chat App

create openai assistants and manage threads

AI-powered Chrome tab manager — group, compare, focus and save tabs with Claude, Gemini, GPT or Groq.

Evaluate and compare large language models (LLMs) for chatbot applications, using various LLMs as evaluators, and manage prompt templates and binary preferences.

Meme search and discovery engine using OpenAI CLIP and Salesforce BLIP

Your browser-native AI superpower.

Sample Solution for a Public Speaking Mentor GenAI Assistant using Amazon Bedrock

Claudian brings the power of Claude AI directly into your Obsidian knowledge management workflow. Chat with Claude in a dedicated side panel, process your notes to get smart suggestions for tags and wikilinks, and use Agent Mode to manage your vault with natural language commands.

AI companion with soul, memory, and autonomous inner life

🤖 Native AI agent for your terminal and macOS desktop. Run cloud and local models through one secure runtime.

AI Agent that deepens your understanding of programming languages through experiments that reveal surprising and non-obvious behaviors.

Self-hosted AI agent operations platform. One UI, many agents, your infrastructure. Apache-2.0.

🗃️ A curated catalog of skillshare skills and a reference for building your own. Create your organization's internal hub.

GitHub Issue Resolver Agent with Anthropic Claude 3.7 Sonnet and Haystack

GraphChatAI transforms user interaction with AI using a graph-based interface. It enables dynamic management of multiple conversation threads and structured exploration of ideas, enhancing creativity and efficiency in dialogues.

Interactive Skill that walks you through Anthropic's "Complete Guide to Building Skills for Claude" — ship a working SKILL.md in ~20 min.

This project implements a Retrieval-Augmented Generation (RAG) system using GraphRAG for the novel "86 - Eighty Six"

An advanced, fully local, and GPU-accelerated RAG pipeline. Features a sophisticated LLM-based preprocessing engine, state-of-the-art Parent Document Retriever with RAG Fusion, and a modular, Hydra-configurable architecture. Built with LangChain, Ollama, and ChromaDB for 100% private, high-performance document Q&A.

PhantomEar is a privacy-first, local-only AI meeting assistant that runs invisibly on your machine. No bots, No cloud recording, No admin permissions.

Multi-agent system for drafting and managing GitHub issues. Built with BeeAI Framework, integrated via GitHub MCP, and consumable through Agent Stack CLI & UI via A2A.

Bitrix24 channel plugin and skill for OpenClaw — chat with your AI agent through Bitrix24 Messenger

龙门客栈 - 基于 OpenClaw 的多 Agent 协作管理系统，支持自定义角色、技能与工作流自动化。帮助企业快速搭建 AI 协作团队，提升运营效率。| Multi-Agent Collaboration System based on OpenClaw

基于 DeepSeek 的 AI 智能答题助手，自动识别并解析网页题目，为您提供精准答案与详细解析。一键抓取 · 深度解析 · 学习更轻松！

LiteLLM for the JVM. One Spring Boot gateway for OpenAI, Anthropic, Gemini, Ollama & 12 more providers. Aliases, fallbacks, streaming, RAG - zero SDK juggling.

幫企業在數分鐘內完成合約第一輪審閱：自動標出風險條款、修改建議與法條出處。RAG + 多工具 Agent，支援司法院法條查詢、知識庫問答與 Eval 驗證。

Local OAuth proxy for Anthropic Teams/Enterprise — auto-manages tokens, streams SSE with zero buffering

Personal knowledge graph — 8K+ bookmarks, LinkedIn saves & YouTube videos indexed with pplx-embed, ChromaDB and Neo4j. LangGraph agent + Gradio UI.

Live-proven Cloudflare Project Think contracts — each example deploys to a real Worker, proves its claim against live state, and tears itself down.

Drop-in OpenClaw/NemoClaw agent configuration for the ibl.ai Medical & Healthcare segment — Care Assistant orchestrator plus 12 specialist subagents.

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

MCP server for the Proton privacy suite — Mail, Pass, Drive, Calendar, VPN. 36 tools for Claude and other MCP-compatible AI agents.

A self-hosted context manager. @context organizes your work into a private CRM and knowledge base and helps you stay on top of things.

Production-grade, contracts-first framework for AI agents in Python — vendor-neutral, audit-ready.

Open-source bookkeeping + tax knowledge layer для российских бухгалтеров. Markdown skills + MCP-серверы к ФНС/ПФР/ФСС/1С. Apache 2.0. Sister project to ru-legal.

A curated list of MCP servers for sales automation, LinkedIn outreach, lead generation, and B2B growth

An LLM Council: multiple models answer, anonymously rank each other (Borda), and a chairman synthesizes a consensus/dissent answer — all through one Vercel AI Gateway key. Zero dependencies.

A Go-native framework for LLM agents, with OpenTelemetry observability built in.

RAG-Powered Financial Query Assistant for JPMorgan Chase documents with Hybrid Search, Docker support, and Streamlit UI

The agentic, conversational web browser — talk to Sprig and the open web composes itself into living, cited pages.

Build a Self-Evolving Agent Harness from Scratch | 12 lessons | Anthropic/DeepSeek/Qwen/GLM

Self-hosted, GDPR-safe AI agent for law firms. Zero-cloud, hash-chained audit trail (AI Act art. 12), bring-your-own-model, 9 language editions. Hard fork of willchen96/mike, AGPL-3.0.

Persistent local memory for Claude and ChatGPT. No cloud, no subscription. Self-hosted RAG over MCP.

GenPark skill: Utilize GenSpark Workspace 4.0 for desktop automation, MS Office integration, and AI meeting notes.

An intent-based language for agentic systems. Write agents in English. Transpile to async Python.

GenPark skill: Learn practical AI skills step-by-step through beginner-friendly, habit-forming lessons and structured challenges inspired by Coursiv.io.

Workspace for humans and AI agents. Every block is a doc, a task, a discussion, and agent context — one object, not three copies your agent has to choose between. Context is lexically scoped: pin a rule at the root, every task below inherits it. Self-hosted, MCP-native.

ULA – 从收案到文书的律师诉讼全流程 AI 工作台 · WorkBuddy多Expert并行 · 元认知自蒸馏 · 非代码律师友好

Federated MCP gateway: one OAuth 2.1-protected, spec-compliant MCP server in front of all your apps. Backends stay plain HTTP (~120-line contract) or proxied native MCP servers with a per-user token vault. Scope-filtered tools, live discovery, audit trail. Give agents curated, governed access to your whole stack — one URL, one token.

Production-ready agentic AI framework in Go; build scalable reasoning agents with native tool calling, memory & observability. Anthropic · OpenAI · Gemini · Groq

Run xAI's Grok CLI from any project, with all traffic routed through a VPN (Docker + gluetun, Mullvad by default)

A Langchain integration for FalkorDB

Production-ready WhatsApp AI assistant (RAG + multi-LLM). Free core + Pro CRM/app integrations. Nice dashboard, Docker, Pinecone. Contact: [email protected] | +255 692 654 000

Open-source LLM control plane: observe every call, recommend savings, then apply only human-approved, reversible routing.

Multi-upstream OpenAI-compatible AI proxy for free models, routed through Tor. HTMX dashboard.

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

Open Source version of Claude Managed Agents. Anthropic SDK compatible. Supports agents, sessions, environments, files, memory stores, skills, deployments, message batches, vaults, and webhooks.

Glasses MCP is a simple MCP server that lets your AI agent see and capture the web 👓

LLM RAG enabled bookshelf

Fill up the `model_list` field in your LiteLLM proxy configuration file

Pure Go SDK for building Claude AI agents with pluggable team topologies — no subprocess, goroutine-native concurrency