Business agents

One lib to rule them all (gen ai)

Context Management processor for Pydantic AI agents, providing LLM-powered summarization or zero-cost sliding window trimming to handle infinite/long-running conversations without context overflow. Supports flexible triggers, safe cutoffs, and custom prompts for efficient AI apps.

OpenAI PHP asynchronous client for workerman and webman.

A seed for growing a personal AI that improves through use and continues through failures.

OpenBrowser is an open-source, AI-native browser built on Chromium — a truly privacy-first alternative to ChatGPT Atlas, Perplexity Comet, and Dia.

Lab Walkthrough and Demo for the "Collaborating with agents in your software development workflow" workshop

Radicalbit AI Gateway

A scalable browser for building intelligent AI agents

Turn any skill into a standalone, runnable RAG-native AI Agent

Monorepo for a multi-agent workspace: protocol-first agent runtime with plugin hooks, four child-process adapters behind one AgentBackend contract, an Elysia backend (auth, run pool, SSE), an agentic workflow engine │ │ (agent/script/human nodes, JSON-Logic routing, cron triggers)

The open-source thread-plane for agents: chat, durable threads, persistence, human approvals, and generative UI for Angular, on LangGraph and AG-UI.

🤖 Build powerful AI agents with TypeScript. Agenite makes it easy to create, compose, and control AI agents with first-class support for tools, streaming, and multi-agent architectures. Switch seamlessly between providers like OpenAI, Anthropic, AWS Bedrock, and Ollama.

构建一个医疗知识图谱并基于此实现 RAG，并以此实现医学试题的生成

FinchBot is an AI Agent framework that empowers agents with true autonomy, built on LangChain v1.2 and LangGraph v1.0. With fully async architecture, agents gain the ability to self-decide, self-extend, and self-evolve

Iterative specification refinement tool: feeds your docs through GPT Pro Extended Reasoning via Oracle for multiple revision rounds until production-ready

An independent .NET implementation of a Neo4j-backed memory provider for AI agents. Persistent graph-native memory for Microsoft Agent Framework, with GraphRAG interoperability for Neo4j.

Shakti — AI-first Python web framework. Born in India, built for the world.

A curated directory of Model Context Protocol servers, plus runnable reference implementations in Python.

Obsidian vault intelligence

An open-source travel agent that works on real websites: plan trips, book in a browser beside the chat, stop at the payment page. Desktop app for macOS, Windows and Linux.

A Chrome extension that helps you batch connect with LinkedIn suggestions and send AI-generated personalized messages.

针对 coze （目前可免费使用 GPT-4）https://www.coze.com （海外版） 和 https://www.coze.cn （大陆版） 的 bot 界面优化的 Chrome 插件

"简历匹配智能体"是一个AI驱动的平台，旨在逆向工程招聘算法，向您展示如何精准定制简历。获取那些能让你通过初步筛选、进入人工审阅阶段的关键词、格式和洞察。resume-matcher-agent意思就是模拟HR怎样筛选你的简历，提前给你展示筛选的结论，方便你尽快修改好你的简历，以增加通过的可能性。

KGB-RAG是一个基于neo4j图数据库和其他图数据库的知识图谱检索系统，它可以根据用户的自然语句提问，从原数据库获取相关实体信息，并通过知识图谱检索技术以及结合大模型自身能力来增强回答用户的自然语言提问。

An open source implementation of the paper: "Sequential Diagnosis with Language Models" From Microsoft Built with Swarms Framework

A Self-Evolving Framework Through Executable Subagent Accumulation and Reuse

⚡ CloakBrowser MCP server for AI agents: Playwright-powered browsing, clean tool forwarding, Docker support, and multi-session HTTP transport.

CLI for Grok Bot agents and groups: create, update, message, inspect threads, and automate cleanup

Deep reinforcement learning using an asynchronous advantage actor-critic (A3C) model.

A toolbox for benchmarking Multimodal LLM Agents trustworthiness across truthfulness, controllability, safety and privacy dimensions through 34 interactive tasks

A self-organizing network that combines cellular automata, coherence, and language models to explore emergent collective intelligence through cellular agents that think, plan, and evolve in a multi-dimensional space.

An AI-backed threat hunting assistant that aligns to the PEAK framework.

Homekit gives any AI agent direct, physical control over Apple Home. Flip lights. Lock doors. Read sensors. Through a single open interface.

A lightweight Python library that allows any LLM agent to self-improve through feedback, without retraining models.

An AI HR Agent who lives in Slack (GPT-powered)

An AI girlfriend or boyfriend that lives inside your terminal. Real personas, real conversations, your shell as a chat room.

🎬 The first AI-powered MCP server for Final Cut Pro XML. Control your edits with natural language.

OneCamp: self-hosted all-in-one workspace (chat, tasks, video calls, docs, calendar & AI)

The long-term memory for your Superagents 🥷and LLMs 🤖. Built with GraphRAG, Knowledge graphs and autonomous ai agents

Tilly is a relationship journal. An offline capable PWA that feels really good. It has an AI agent for maximum convenience.

A Model Context Protocol (MCP) server implementation exposes document processing capabilities through natural language, supporting both direct human interaction and AI agent tool calling.

A high-performance Model Context Protocol (MCP) server that provides secure filesystem access for Claude and other AI assistants.

A production-grade control layer that sits between your application logic and any LLM — input validation, schema enforcement, circuit breaking, targeted retry, and audit logging in one composable pipeline.

[ARCHIVED 2026-05-18] Superseded by anthropic-docs (multi-skill, 30-min refresh)

Multi-agent memory governance demo using MemClaw + OpenClaw. Three agents (Sales, Legal, Admin) share one memory backend with hard fleet boundaries enforced at the query layer. Shows scoped writes, blocked recall, cross-fleet synthesis, and conflict detection.

A chain for agents, on BNB Smart Chain. Genesis carries three system contracts and three neutral tools — Multicall3, a CREATE2 deployer and Wrapped BAC. Every token, pool and market beyond that is deployed by an agent. Agents never sleep, so they find each other's contracts in seconds. Pre-launch: nothing is deployed.

Asynchronous Spatial Allocation Protocol for Heterogeneous Multi-Agent Trajectory Planning

In every factory there's one person who knows when a machine is about to fail — they hear it. When they retire, that knowledge disappears forever. ARIA captures it, watches the equipment, and diagnoses what goes wrong — so the one who knows is never the last.

AutoApplyMax — AI-powered Chrome extension. Auto-apply to jobs on LinkedIn, Indeed & more. AI Resume Generator, Cover Letters, ATS Score Checker & Dashboard.

Convert LangChain tools to FastMCP tools

MCP server for Denmark's Aula school platform — TypeScript MitID auth, no headless browser. Exposes profiles, calendar, messages, ugeplaner to AI agents (Claude/Cursor/etc) via Model Context Protocol.

A Model Context Protocol (MCP) server that enables Claude Desktop to check domain availability across 50+ TLDs. Features DNS/WHOIS verification, bulk checking, and smart suggestions. Zero-clone installation via uvx.

AI work that doesn't evaporate. A workspace for building, tuning, and publishing governed AI products.

A privacy-first, provider-neutral personal AI workbench with chat, memory, auditable tools, MCP, and isolated project plugins.

Fully local AI for Polish legal case files - zero fabricated citations by construction. Free; please support a Wroclaw animal shelter instead.

Running llama3 using Ollama-Python, Curl, LangChain, Chroma, and User interface.

OpenBrowse is a macOS browser agent that gets things done on the web through autonomous task execution, chat-based clarification, and resumable local workflows.

SyncTrek is an AI-powered travel assistant that creates personalized itineraries using a multi-agent AI system. It learns your preferences through an intelligent questionnaire and provides tailored travel plans quickly and efficiently.

AI knowledge workbench for Neovim.

📚 Lama Loca — локальный ИИ-ассистент для учёбы. Учится по вашим книгам, создаёт отчёты, презентации, конспекты. Полностью офлайн.

The benchmark tasks and evaluation harness for "PhysicianBench: Evaluating LLM Agents in Real-World EHR Environments".

企业级5-Agent智能会议助手系统 | Pipeline+并行编排 | Python/Java/Go三语言实现 | 面试宝典(八股文+STAR法+简历模板)

Tokio pipeline for serving LLM requests: bounded five-stage flow with dedup, circuit breakers, retries, rate limits and a dead-letter queue in front of Anthropic, OpenAI, llama.cpp or vLLM. REST, SSE, MCP, TUI.

This project is a meal planning app that generates personalized meal plans based on a user's caloric needs and Personal Information. It utilizes natural language processing to generate creative meal ideas using ingredients selected by the greedy algorithm.

A multi-room chat application in C++ using Winsock. Supports real-time messaging, private chats, undo/redo, history, and search. Built with threads, mutexes, and socket programming for concurrent multi-client communication.

One chat interface across OpenAI, Anthropic and Gemini — with tools, web browsing and shared threads. Built on LangChain.

Local-first adaptive LLM runtime for Hermes Agent. Matches 8–300 GB hardware, acquires pinned GGUFs through Turbohaul, and safely contracts and heals under VRAM pressure—no remote fallback by default.

TypeScript SDK to call 100+ LLM Providers in OpenAI format.

[EMNLP 2025] HydraRAG: Structured Cross-Source Enhanced Large Language Model Reasoning

A chat alfred-workflow that integrates multiple popular large language model (LLM) services, including OpenAI, Anthropic, Gemini, etc

A miniature isometric 3D office where 9 AI agents work, walk, talk, and hold meetings. Built with React 19 + Three.js.

Give Claude semantic memory of your Obsidian vault — local semantic search over Smart Connections embeddings via MCP. Multi-vault, block-level, 100% private.

A 5-layer asynchronous AI agent framework with Docker-in-Docker sandboxing and hybrid memory.

An AI SDK for building agents and tools in Laravel applications

Benchmark for evaluating LLM agents on smart-contract vulnerability discovery and exploitation

Run Large Language Model "Agents" in Salesforce apex

RinAI agentic chat stack. Includes graphRAG memory, parallel tool calling, DeepSeek R1 powered web search, advanced LLM gateway and active context summarization.

[ToN 2024] Ensuring Threshold AoI for UAV-assisted Mobile Crowdsensing by Multi-Agent Deep Reinforcement Learning with Transformer

🚀 AI-Powered Windows Automation Server using Model Context Protocol (MCP) | Control Windows apps, automate tasks, and manage systems through natural language commands with Claude, ChatGPT & other AI assistants | 80+ automation tools

Thread Dispatcher is an open source tool to pass the execution of a Delegate, Coroutine or Task from a background thread to the main thread, and await its completion or result on the calling thread as needed.

Open Chat Playground (OCP) is a web UI that is able to connect virtually any LLM from any platform.

This project demonstrates how to use AWS Bedrock with Anthropic Claude and Amazon Nova models to create a web automation assistant with tool use, human-in-the-loop interaction, and vision capabilities.

📤 Claude 对话导出工具、📊 Mermaid 图表查看器、🎬 B站UP主过滤器、⏱️ 网站时长统计和🎛️ 视频播放控制器等多种实用 Tampermonkey 脚本，提升你的网页浏览体验。 ⭐ 如果这个项目对你有帮助，请点个 Star！

HTML output skill for Claude agents — 4 levels (Static Doc / Visual Artifact / Two-Way Interactive / Throwaway Tool). Based on Thariq Shihipar's framework.

[Agentic AI-RPG] Agentic AI role-playing game framework — narration, NPCs, lore, and character creation are autonomous plugin agents. Build interactive fiction with DeepSeek / OpenAI / Anthropic / Qwen.

An agent that edits your Word and Excel files — then looks at them, through real Microsoft Office, to check its own work

An open-source AI agent for the browser. Bring any model. It plans in the side panel, acts on real pages through tools, and verifies every claimed result against the live DOM — with guardrails and reusable skills.

Kuberna Labs - The Full-Stack Platform for Agentic Web3. Build, deploy, and monetize autonomous AI agents across decentralized networks with TEEs, zkTLS, and cross-chain intents.

💸 Shrink your token bill in herdr: compresses every agent pane's requests (-31% input / -74% output, measured live) and shows the savings on a per-pane badge

Fully Configurable RAG Pipeline for Bengali Language RAG Applications. Supports both Local and Huggingface Models, Built with Langchain.

Anthropic’s Model Context Protocol implementation for Oat++

A conversational chatbot powered by CrewAI, Groq, Chromadb and Mem0

File-based context resolution for AI agent DAG workflows. Three primitives, zero dependencies.

The official repo for our paper: LegalAgentBench: Evaluating LLM Agents in Legal Domainl

自主实现面向医学知识的GraphRAG应用系统#大模型LLM#RAG#GraphRAG#Agent智能体#知识图谱KG

A self-hosted Claude agent that actually remembers — verbatim memory palace at zero retrieval cost, Discord + web UI, and 90%-cheaper repeat calls via prompt caching.

Multi Agent for Business Automation is a multi-agent orchestration platform for business automation and decision support. It coordinates specialized AI agents—each with distinct roles, personalities, and tools—through LangGraph workflows, shared memory, and human-in-the-loop (HITL) approval gates.

Agent skill package that gives your agent persistent memory via an [Obsidian](https://obsidian.md) knowledge vault. Your agent automatically orients itself at session start, navigates project architecture through graph traversal, writes discoveries back to the vault.

Self-hosted team chat where humans and agents are first-class members — channels, DMs, threads, reactions, file uploads, and an agent runtime.