Persona
Persona is a VanillaJS Agent UI Library that helps developers create agentic front-end experiences for the web in pure JavaScript. Lightweight, extensible, and WebMCP-native, it runs on any stack and can connect to any SSE backend. Developers can start with a floating launcher in the corner, a copilot docked beside an app, or a full-height assistant that owns the page, changing the launcher configuration without changing the agent or app. Persona is designed for support, docs, sales, onboarding, internal tools, and custom agent experiences where the chat UI becomes another way to operate the application. Through WebMCP, developers can expose page actions, search, carts, bookings, forms, and other tools directly in the browser through a document.modelContext; Persona discovers those tools, asks the user before calling them, and streams the result back into the conversation.
Learn more
BayPoint AI
BayPoint AI is an AI-powered software suite built exclusively for eBay sellers. Integrated tools in one dashboard, and growing. Baypoint AI helps sellers optimize listings, automate feedback, and track shipments.
Listing Intelligence — AI scoring and optimization that identifies what's holding your eBay listings back and suggests specific improvements to increase visibility and sales.
Found Listing Discoverability - AEO/SEO: AI-assisted listing optimization, on-page SEO workflows, answer-engine optimization (AEO) content structuring, schema-aware content generation. WebMCP & Agentic Web: WebMCP integrations, agent-ready metadata patterns, browser-automation compatible workflows, AI agent interoperability design
Feedback Manager — Automatically generates personalized responses to seller feedback, saving hours weekly while maintaining a 5-star reputation.
Buyer Feedback Manager — Bulk automation for leaving buyer feedback across all transactions.
Learn more
WebMCP
WebMCP is an open source JavaScript library that allows any website to integrate with the Model Context Protocol, enabling users to connect to and interact with webpages through an LLM or AI agent. Developers can add WebMCP to a site with a simple script, which initializes a small widget that handles the connection between the webpage and an MCP client. Once connected, websites can expose MCP features including tools, prompts, resources, and sampling. Tools let an LLM perform actions on the website through registered functions with defined inputs and outputs. Prompts provide reusable templates for common LLM interactions and can accept dynamic arguments. Resources expose webpage data and content that clients can read and use as context, including page content, individual elements, files, or other structured information. WebMCP also supports sampling, allowing the server to request LLM completions through the connected client while maintaining human oversight.
Learn more
AgentShelf
AgentShelf Platform is a no-code environment for building, deploying, and governing focused AI agents for business workflows. Teams can give each agent approved context, tools, model access, permissions, and a dedicated workspace, then deploy experiences to websites, internal workspaces, products, or external applications. The platform includes reusable agent patterns, widgets, SDKs and APIs, usage and cost visibility, budget policies, activity traces, and public/private access boundaries. It supports use cases such as website visitor qualification, customer support triage, CRM follow-up, research, knowledge retrieval, and recurring reporting.
Learn more
