Best AI agents for images and design (2026)
AI agents for visual work: design agents that build graphics and brand assets from a brief, image generators you can direct by chat, diagram makers, and MCP servers that let agents work in Figma, Canva and Penpot. We list 45 tools for images and design below, each with a link-checked page, pricing as the maker states it and alternatives.
Updated
45 tools: 16 open source, 19 free or freemium, 9 paid, usage-based or enterprise, 1 pricing on the maker's site.
This page lists AI agents and MCP servers that create or edit visuals for you. For every art, design, 3D and photo tool, see Image generation, Graphic design & branding, 3D & concept art and Photography & photo editing.
PR Lens
PR Lens helps people review code that agents wrote. For each pull request it draws animated architecture and data-flow diagrams inside the PR, showing which parts of the app were added, changed or removed, what else depends on the change and how a request now moves through the system. It also flags likely bugs, security holes and design problems in the same review comment, with a ready prompt to hand each fix to your coding agent or an autofix. The open-source core runs locally and installs as an agent skill.
Added
WaveSpeed MCP
WaveSpeed MCP is WaveSpeedAI's official MCP server and CLI, which lets an AI agent run any model in WaveSpeed's live catalog of over a thousand image, video, audio and 3D generation models from one connection. Agents can pick a model, submit a generation job and get the result back without switching tools. It is available as a hosted remote server or a local install, and usage is billed per generation at WaveSpeed's API prices.
Added
OpenKnowledge
OpenKnowledge is a free, local-first markdown editor and knowledge base built for working alongside AI agents. It looks and feels like a Notion-style WYSIWYG editor, with callouts, tabs, Mermaid diagrams and media blocks, but every page stays a plain markdown file on your disk. Coding agents such as Claude Code, Codex, Cursor, Gemini CLI and dozens of others can read and write the same files through its integrations, so specs, team wikis and LLM wikis stay in one place that both people and agents keep up to date. It ships as a desktop app plus a web UI and CLI.
Added
draw.io MCP
The official draw.io MCP server, so Claude, ChatGPT, Cursor and other assistants can create and edit flowcharts, architecture diagrams and other draw.io diagrams right in the chat. Free and needs no sign-in.
Added
Onlook
An open-source visual editor for React and Tailwind apps where you design on a canvas and an AI agent writes the code. Edit layouts like in Figma, then export clean code to your own repo.
Added
nodeterm
A node-based terminal manager for macOS and Linux that shows real terminals and coding agents like Claude Code, Codex and Gemini as live nodes on an infinite canvas you can wire together.
Added
shadcn/lint
Linter for Tailwind design systems from shadcn that turns your design rules into checks coding agents can run and fix against.
Added
Pixeltable
Multimodal data layer that combines storage, transforms, indexing and retrieval in one Python library for building agents over images, video and documents.
Added
Novastart
Novastart is an infinite-canvas operating system where your apps, AI agents and teammates work together on one shared whiteboard space; Free, Pro $10 and Team $20 per user.
Added
Penpot
Open-source design and prototyping tool with an official MCP server so AI agents can read and edit design files.
Added
Adobe Express
Quick design, social and video app with Firefly generation and a conversational AI Assistant that edits for you.
Added
Canva AI
Canva's design agent: describe a goal and it plans and builds the designs with Canva's tools, brand kit and connectors.
Added
Figma Make
Prompt-to-prototype and app builder inside Figma that works from your designs and components.
Added
Google Stitch
Google Labs tool that turns a prompt or sketch into UI designs and front-end code.
Added
Lovart
AI design agent that turns one brief into a brand kit, posters, social posts and video.
Added
Pencil
AI creative tool that generates, tests and iterates ad creatives for brands.
Added
Picsart
Photo and design editor with AI agents that make social content and edits from a voice or text request.
Added
Pomelli
Google Labs agent that reads your website, builds your brand profile and makes on-brand marketing campaigns.
Added
Simplified
AI marketing agent that plans and produces full campaigns: copy, designs and social posts.
Added
Typeface
Enterprise platform with AI agents that make on-brand marketing images and copy at scale.
Added
Zoo Zookeeper
Zoo's prompt-driven CAD assistant (formerly Text-to-CAD): describe a part and it builds an editable CAD model you can refine in Zoo Design Studio.
Added
Photoshop MCP
Community MCP server that lets AI agents drive Adobe Photoshop: layers, adjustments, text and exports.
Added
Meshy
Text and image to textured 3D models, with rigging and animation, plus an official MCP server for AI agents.
Added
Adobe Lightroom
Photo editor with AI masks, denoise, generative remove and assisted culling, plus batch edits through the Firefly AI Assistant.
Added
Adobe Photoshop
Photoshop with Generative Fill and an AI Assistant agent that carries out multi-step edits on request.
Added
ComfyUI
Node-based open-source engine for image and video generation workflows. Run models like Wan, LTX and Hunyuan locally or in Comfy Cloud, with an agent that builds workflows.
Added
Framelink Figma MCP
MCP server that gives Cursor and other coding agents Figma layout data so they can implement designs accurately in one shot.
Added
Figma Console MCP
Design-system-focused MCP server that reads and writes Figma and checks design-code parity and accessibility.
Added
Brandfetch MCP
Brandfetch's MCP server for searching brands and retrieving logos, design assets and company data.
Added
Adobe Firefly
Adobe's generative app for images, video and audio, with 30+ models including Adobe's commercially safe ones and a creative agent.
Added
Higgsfield
Create images, videos and voice from prompts or references using many models, with camera-move presets and an AI agent that automates workflows.
Added
Icons8 MCP
Icons8 MCP server for searching and fetching Icons8 icons and Ouch illustrations as SVG, PNG or animations.
Added
Logo.dev MCP
Official Logo.dev MCP server for finding brand logos and brandmarks and managing brand subscriptions.
Added
Luma Dream Machine
Luma AI's video and image generation platform, built on its Ray models, with creative agents that handle end-to-end workflows.
Added
Picsart GenAI MCP
Picsart's MCP server for generating and editing images, video and audio with 150+ models from 20+ vendors.
Added
MiniMax MCP
Official MiniMax MCP server that lets agents call MiniMax text-to-speech, voice cloning, image and video generation.
Added
Genspark
All-in-one AI workspace whose agents research and produce slides, docs, sheets, images, video and code for you.
Added
Next AI Draw.io
Create and edit draw.io diagrams by chatting with AI, as a web app, desktop app or MCP server.
Added
Talk to Figma MCP
MCP integration that lets coding agents read and edit Figma designs.
Added
CodeBoarding
Generates interactive architecture diagrams of codebases.
Added
Figma MCP Server
Figma's MCP server that brings design context from Figma files into coding agents.
Added
Canva MCP
Canva's MCP server for creating, searching, editing and exporting designs from AI assistants.
Added
ExcaliClaw
Hand-drawn diagram workspace your agent can draw in via MCP (Claude, Cursor, VS Code).
Added
Webflow MCP
Webflow's MCP server for designing and managing Webflow sites.
Added
Ludo.ai
AI assistant for game designers: market research, concept ideas, game design docs and asset generation.
Added
GitHub repos (22)
| Repo | GitHub stars | Licence | Last push |
|---|---|---|---|
| ComfyUI ↗ | 138,580 | GNU General Public License v3.0 | 2026-10-21 |
| Penpot ↗ | 61,335 | Mozilla Public License 2.0 | 2026-10-21 |
| Next AI Draw.io ↗ | 36,280 | Apache License 2.0 | 2026-10-18 |
| Onlook ↗ | 26,963 | — | 2026-07-22 |
| Framelink Figma MCP ↗ | 16,002 | MIT | 2026-06-24 |
| Talk to Figma MCP ↗ | 7,059 | MIT | 2026-07-26 |
| draw.io MCP ↗ | 5,669 | — | 2026-10-20 |
| OpenKnowledge ↗ | 4,646 | — | — |
| shadcn/lint ↗ | 3,225 | — | 2026-10-19 |
| CodeBoarding ↗ | 2,590 | MIT | 2026-10-15 |
| Figma Console MCP ↗ | 2,518 | — | 2026-10-02 |
| PR Lens ↗ | 2,167 | — | — |
| Figma MCP Server ↗ | 2,079 | — | 2026-10-20 |
| nodeterm ↗ | 2,043 | — | 2026-10-21 |
| Pixeltable ↗ | 1,641 | — | 2026-10-21 |
Top 15 of 22 by stars. Stars and licence come from each repo, checked when the listing was last verified.
Related tasks
Popular with: Marketers · Designers · Artists · Related searches: Free AI image and design agents
Tools are matched to tasks by category, use cases and what each tool says it does. Missing one? Submit it free.