Business agents

A small library for building LLM powered applications through string composition

Ask your terminal to do whatever you typed

Many examples, hopefully easy to use

Memora – a lightweight, offline-first archive explorer for your ChatGPT history. Import your exported conversations, search them instantly, merge threads, and export to TXT/Markdown/PDF — all in a GitHub-dark themed UI that runs entirely in your browser.

The extension is based on GPT4 Mobile version for Chrome browser.

This is an example of implementing the RAG feature based on OpenAI Assistant V2 and Anthropic's PDF feature.

ScoutSense - Recruit revolutionizes the recruitment process by combining smart candidate evaluation with automated interview preparation. Essential for recruiters, hiring managers, and HR professionals who want to streamline both candidate screening and interview preparation.

Generate jj (Jujutsu) commit descriptions automatically using LLMs

An AI-powered Discord bot that chats, stores user memories, and can execute terminal commands on Windows directly through Discord.

A claude wrapper for doc generation

RAGO (Retrieval Augmented Generation Optimizer) is a toolkit that automatically discovers the best configuration for your RAG system through smart experimentation

A learning companion.

This is a simple example of how to use the Ollama RAG (retrieval augmented generation) using Ollama embeddings with nodejs, typescript, docker and chromadb

High-throughput RAG ingestion engine in pure Go — 965 MB/s (Mixed Corpus), 2.4 MB heap, zero dependencies.

Scriptable access to Microsoft 365 from the command line. Tasks, mail, calendar, contacts, planner, teams, SharePoint, OneDrive, and Loop — with structured JSON output for scripts and AI agents.

**AI-Perceivable Distributed Orchestration** apflow is a distributed task orchestration engine where every capability is AI-perceivable — discoverable, understandable, and invocable by AI agents through the apcore module standard.

Uniform Electronic Transactions Act based error handling agent demos. Collaboration between Andor Kesselman and Dazza Greenwood

[Preprint 2025] SituatedThinker: Grounding LLM Reasoning with Real-World through Situated Thinking

"Infrastructure for continuity across discontinuity — for AI instances and the humans who work with them."

Open-source RAG system that turns your ChatGPT export into a searchable knowledge base with Claude MCP integration.

MCP Server for Lightning Faucet - Give your AI agent a Bitcoin wallet

Intent-based MCP server for project documentation search. Maps natural language queries to the right sources automatically—no configuration needed. The standard for AI agent documentation search.

The hero effect for the AI agent era — GPU-accelerated glass ripple with CRT retro aesthetics with a lot brand icons, 11-pass WebGL2 shader pipeline

Agent SDK toolkit for Building AI agents with system tools

LLM-powered macOS computer control. AgentPilot lets AI agents see your screen, move the mouse, type text, press hotkeys, manage windows, run shell commands, and more — all through a native macOS app with a chat interface.

Self-hosted Zulip channel plugin (TypeScript) for the OpenClaw agent - sibling of zulip-hermes-integration. Brings an open-source AI agent into threaded team chat as a full participant, self-hosted and free of chat-vendor lock-in. One Zulip agent family, two runtimes.

MAPLE - Production-ready multi agent communication protocol with integrated resource management, type-safe error handling, secure link identification, and distributed state synchronization.

Open-source AI agent orchestration platform. Multi-agent discussions, visual workflows, 30+ tools, human-in-the-loop governance.

KG-RAG + ToT + multi-agent LLMs for evidence-grounded QA with Neo4j and fine-tuning; reproducible medical case study & evaluation.

Streaming-first multi-provider LLM client in TypeScript with home-made tool calling

SkyInMac - Open-source alternative to Sky (OpenAI). AI-powered assistant that integrates with native macOS apps like Calendar, Notes, and Messages and more for instant interactions.

Blazing fast LLM gateway, guardrails, load balancing and logging.

Self-hosted Compound AI System for sovereign environments. Features token-saving complexity routing, deterministic MCP tools for math/logic, configurable expert templates, causal/reinforcement learning, agentic loops, and a federated Neo4j GraphRAG.

MCP server for Grammarly AI detection and plagiarism scoring via Stagehand + Browserbase browser automation, with Claude-powered text optimization

Chrome extension that tailors your resume to job postings on Indeed & LinkedIn using AI (Claude, ChatGPT, or Gemini) — then helps you apply in one click.

Svensk komplement-stack till Anthropics Claude for Small Business. 11 Claude Skills för Bokio, moms, AGI, K10 och svenskt regelverk.

An MCP server for AI agents that handles captcha bypass workflows through dedicated tools instead of prompt hacks. Includes session-based browser automation, reCAPTCHA v2 solving, Selenium workflows, and a clean agent-to-tool architecture for verification-heavy web flows.

A suite of plugins for freight forwarding workflows — air, sea, road, rail, and time-critical. Maintained by DCS Premium Freight SRL.

High-performance Model Context Protocol (MCP) server gateway for Claude Pro. Seamlessly bridges Claude Web UI with local environments, file systems, and secure execution layers.

🏛️ 解决方案架构师/售前顾问超级工作台 | C4模型·TOGAF·4+1视图·13类draw.io图表 | PPT工场·文档工场·RFP响应 | 方案设计·架构图·投标全链路 | WuKong/Claude Skill

Production-grade Cursor slash commands with paired skill contracts, behavioral evals, and ship-gate CI. Install as a user plugin.

HERO - Harness for Engineering and Run-time Orchestration: a runtime control system around foundation models for autonomous software-engineering missions.

Lightweight Python SDK for LLM inference logging and observability

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

Local-first Rust CLI that tailors your resume to a job posting through an adversarial agent loop, and never invents experience you don't have.

AI changelog generator that turns commits into polished release notes.

Open-source LLM cost observability and smart routing that runs in-process. No proxy, no telemetry, zero added latency.

An AI-powered Discord bot that chats, stores user memories, and can execute terminal commands on Windows directly through Discord.

AI-Powered Kahoot Bot Auto-Answer Chrome Extension - supports every question type

Drop-in AI chatbot SDK + React widget. 3 lines to integrate. 11 LLM providers with auto-failover. 13 URL-only adapters (Stripe, Calendly, PayPal...). Markdown knowledge. Apache 2.0.

AI agent for Ableton Live — chat with GPT, Claude, or Gemini to control your session

Reversible macOS patcher for Claude Desktop ASAR tweaks, including third-party inference routing, Computer Use experiments, and an optional desktop pet overlay.

Audit your Salesforce RevOps. Then fix it. A Claude Agent Skills pack for Salesforce admins and RevOps practitioners.

Enterprise AI OS reference architecture — the moat is memory and governance, not the model. One architecture, three scales (personal / startup / enterprise), derived bottom-up from a working n=1 system.

Define your agent in a single config file, run it in a container and deploy it anywhere.

Gemini in Chrome 一键启用与修复工具｜Cross-platform toolkit to enable/fix Gemini AI in Chrome on Windows/macOS/Linux. Fixes Gemini button missing, --disable-actor-safety-checks warning, Roxy fingerprint browser pollution, Chrome Sync contamination.

An MCP server for inspecting and editing Microsoft .docx files with support for real tracked changes and comments.

Agent-specific payment workflows and examples for TDM

GenPark skill: Integrate CANLAH AI's Style Genome and multi-agent business suite for marketing, sales, and service automation.

An AI-powered Discord bot that chats, stores user memories, and can execute terminal commands on Windows directly through Discord.

Self-hosted, privacy-tiered memory for your AI agents.

A course on multiple approaches to enriching the query context to create amazing LLM applications.

企业「工作分身」系统：员工电脑上跑一个能在 OA/CRM/ERP 里真正动手的 AI 分身 — 本体语义驱动 · 存量系统无侵入连接(browse-use) · 写操作确认+沙箱隔离可审计

A full-stack multi-agent orchestration system demonstrating construction project management using AI agents.

Clippy rebuilt as a macOS agent that can use your computer. It reads your screen and clicks/types the thing

The browser-side execution layer for GenPark. Identifies e-commerce prices in real-time and routes them to the nearest Alpha node for negotiation.

Autonomous outbound B2B sales development representative.

Unabyss-like MCP-native cross-app context vault synchronizer

Multi-channel conversational sales & 1-click checkout agent

Unified HR & payroll compliance automation (Rippling G2 Leader style)

Otari LLM execution gatekeeper

AI-powered smart calendar scheduling, conflict resolution & deep work optimizer

Fuzzy-like AI sales warmup agent that pre-qualifies prospects

AI-native CRM relationship graph, pipeline auto-sync & deal scorer (Lightfield style)

GenPark AI Skill - Check category tax exemption qualifications across US states

Background screen and meeting context observer.

An experimental OpenClaw skill for Agent-to-Agent Marketplace based on Anthropic concept

Accio Work-inspired GenPark Skill

Extract meeting summaries and sync notes

GenPark AI Skill - Generate competitor positioning battle cards for sales teams

Campus human-agent workspace thread dispatcher

GenPark AI Skill - Forecast product demand using historical sales, seasonality decomposition, and trend detection with reorder recommendations

GenPark AI Agent Skill: meeting-scribe (Inspired by GenPark 2026 Features)

Commerce checkout legal tax nexus state tax percentage calculator skill.

Enterprise agentic CRM orchestrator (Agentforce G2 Leader style)

Unified AI chat for Laravel — Ollama, OpenAI (ChatGPT), Anthropic (Claude), DeepSeek, Gemini, Groq. One interface, any AI provider — built-in chat UI, RAG, tool calling, no separate vector DB needed.

Replay real agent traces through cheaper models to prove which swaps are safe.

Chrome extension running a 45M-parameter LLM (Needle 2) entirely in WASM. Natural-language control of tabs, forms, pages, and custom scripts — fully offline.

Citation-grounded Turkish Legal RAG system for legal question answering, combining BM25 + dense retrieval, fine-tuned E5 embeddings, BGE reranking, and Trendyol LLM SFT.

Animated 3D virtual office for Hermes AgentOS subagents — real-time isometric AI visualization with Three.js.

Open Model Hardware Standard - AI agent hardware control

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

Connect AI agents to live QGIS Desktop through a secure local MCP bridge with 100+ specialist tools and resumable visual workflows.

Caveman mode skill for Claude. Fewer output tokens, longer usage before hitting limits.

Proactive AI executive assistant for meeting scheduling & agenda synthesis (Hey Noah style)

"Infrastructure for continuity across discontinuity — for AI instances and the humans who work with them."

从 PRD/产品点子到可运行 Agent 产品的架构蓝图与参考实现，包含 17 个 Harness 组件、生产级脚手架、技能模板和测试。

The browser built for developers: Chromium, a workspace per project, a developer toolkit beside the page, and an agent that can work in your tabs.