Document-aware editing
AI Toolkit gives agents document context and structure so they can make edits that belong in the right place, rather than returning plain text suggestions only.
AI Toolkit helps developers build document-aware AI agents that edit rich-text in place, with reviewable changes, server-side workflows, and real-time collaboration.
Tiptap AI Toolkit is a document-AI product for building agents that understand document structure and edit content in place. It bridges model output and rich-text documents so AI can make targeted changes that are reviewable instead of returning isolated chatbot text.
The toolkit is designed for developers who want to add AI into editing workflows without building the document plumbing from scratch. It works server-side, integrates with Tiptap’s Document Server and Collaboration service, and can also run without a Tiptap Editor when the workflow needs backend processing or long-running jobs.
AI Toolkit gives agents document context and structure so they can make edits that belong in the right place, rather than returning plain text suggestions only.
Edits can be shown as precise tracked changes in a Tiptap Editor, which makes review and approval more practical for users.
The toolkit works server-side, so AI workflows can continue without an active browser session and can run overnight or as batch jobs.
It integrates with Tiptap’s Document Server and Collaboration service so AI-driven changes can appear in users’ editors in real time.
The product supports agentic loops under your control instead of providing a fixed AI layer, and it does not require a specific document-storage or sync system.
The product page describes actions and agent workflows for tasks such as inserting content, rewriting selections, proofreading, summarizing, and applying edits.
Users working on legal contracts can select a section, ask for consistency checks or revisions, and review precise suggested edits before accepting them.
Teams can generate sections, tables, citations, templates, and other structured blocks directly in document workflows.
Organizations can run async or overnight jobs to process large batches of documents without keeping an editor session open.
Product teams can add in-editor AI help that understands the current document and offers context-aware editing actions.
Workflows that need review and traceability can compare AI output, track the source of edits, and keep decisions connected to individual suggestions.
You start by signing up for a Tiptap account and then using the AI Toolkit documentation to integrate it into your product. The release notes point to the docs for implementation details.
Tiptap describes beta products as safe for production use while feedback is still being collected. For AI Toolkit, the release notes say the beta version is production-ready, with Tiptap Shorthand and streaming AI-generated changes still in alpha.
AI Toolkit is designed for document-AI workflows where an AI agent needs document context and the ability to make targeted edits. The release notes highlight legal contracts, review workflows, and long-running backend jobs as examples.
The pricing page says AI Toolkit can be added as a paid add-on. The release notes also mention free lifetime licenses in a promotion, and that paid plans can include unlimited usage and on-premise deployment.
AI Toolkit can work server-side without a Tiptap Editor, and it also integrates with Document Server and Collaboration so changes can appear in editors in real time.
Orca is an Agent Development Environment for shipping with coding agents, running multiple CLI agents in parallel across isolated worktrees, with desktop and mobile workflows.
AI Magicx is a unified AI workspace for chat, image, video, voice, music, email and developer tasks, helping teams and creators manage multiple models in one place.
Paper is a design tool that connects canvas, code, and AI agents so teams can create, share, and ship work in one workflow. Includes desktop app and MCP access.
blop is a QA agent that writes browser tests as code in your repo, runs them in CI, clusters repeated failures, and can open PRs to fix broken tests.
RLAMA is a local AI platform for building RAG systems and intelligent agents on macOS, Linux, and Windows, with HTTP API support.
Kastra authorization infrastructure for AI systems checks prompts, tool calls, shell commands, API requests, and browser actions before execution.