AI tools for images and design: images and design
Agents and tools for visual work: generating images, diagrams and designs. Of the 70 tools on our images and design page, 49 fit this narrower job. By pricing: 28 open source, 3 source-available, 10 free or freemium, 2 paid, usage-based or enterprise, 6 pricing on the maker's site. The most-starred open repos here are MarkItDown (190,824 stars), Dify (158,410 stars), Langflow (155,757 stars). Most come from the MCP & infra (12), no-code builders (9), vision (7) categories.
MarkItDown
Microsoft's Python tool and MCP server that converts PDFs, Office documents, images, audio and web pages to Markdown for LLM and agent pipelines.
Added
Dify
Open-source platform for building LLM apps and agents visually.
Added
Langflow
Visual drag-and-drop builder for AI agents and workflows that you can run locally, deploy as an API or expose as an MCP server.
Added
LocalAI
Self-hosted engine with an OpenAI-compatible API for running LLM, vision, voice and image models on your own hardware, including agents.
Added
OpenHuman
Lightweight open-source agent harness designed to run many agents cheaply on small servers.
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
AgentScope
Framework for building and running transparent multi-agent applications with visual debugging.
Added
FastGPT
AI agent building platform with knowledge-base RAG, data processing and a visual workflow editor for deploying question-answering and automation apps.
Added
Sim Studio
Workspace for visually building, deploying and monitoring AI agents and 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
Botpress
Platform for building and deploying LLM-powered chatbots and agents, with a visual studio, integrations hub, CLI and SDK.
Added
Plannotator
Visually annotate and review coding-agent plans and diffs, then send feedback back to the agent.
Added
BAML
Typed programming language for agents and LLM functions, with runtime types, typed errors and structured outputs designed to reduce agent mistakes.
Added
Activeloop
Deep Lake, a multimodal database for AI that stores vectors, images, text and video so agents and RAG apps can search and retrieve them.
Added
Talk to Figma MCP
MCP integration that lets coding agents read and edit Figma designs.
Added
Kun
Local-first agent workspace for coding, writing, design, research and automation.
Added
Dograh
Self-hostable voice agent platform with a visual call-flow builder, bring-your-own speech and LLM providers and MCP control, pitched as an open alternative to Vapi and Retell.
Added
PySpur
Visual playground for building and iterating on agent workflows.
Added
AstronRPA
iFlytek's open-source enterprise RPA desktop app with a low-code visual designer whose workflows can be called by AI agents.
Added
Sparrow
Open-source tool for structured data extraction from documents and images with ML, LLMs and vision LLMs, plus agentic workflows.
Added
Pezzo
Cloud-native LLMOps platform for prompt design, versioning, delivery, observability and cost monitoring.
Added
Cheshire Cat
Open-source AI agent microservice designed to be easy to understand and extend, with plugins and memory.
Added
Autodistill
Roboflow's open-source library that uses large foundation models to auto-label images and then trains small, deployable detection or classification models with no manual labeling.
Added
CodeBoarding
Generates interactive architecture diagrams of codebases.
Added
Pinvou Agent
Open-source desktop AI agent workspace for work, design and coding tasks that end in finished deliverables.
Added
Figma Console MCP
Design-system-focused MCP server that reads and writes Figma and checks design-code parity and accessibility.
Added
Ui.Vision RPA
Browser and desktop automation extension with OCR and image recognition, plus an MCP server so AI agents can create and run macros.
Added
Figma MCP Server
Figma's MCP server that brings design context from Figma files into coding agents.
Added
Nimbalyst
Visual workspace for working with coding agents like Claude Code on docs, code and plans.
Added
Brave Search MCP
Brave's official MCP server for web, image, video, news and local search through the Brave Search API.
Added
Giselle
Open-source AI agent studio for building agentic workflows with a visual builder.
Added
Webflow MCP
Webflow's MCP server for designing and managing Webflow sites.
Added
Ultralytics Agents
Visual canvas in Ultralytics Platform that chains YOLO models, vision-language models, conditions and actions like Slack alerts, plus official agent skills that let coding agents train, tune and export YOLO models.
Added
Encord Agents
Encord's agents that plug foundation models or your own models into labeling workflows to pre-label, segment, track, route and QA image, video and multimodal data, with a no-code catalog and an open-source SDK.
Added
Almanak
Agentic hedge-fund platform to design and deploy non-custodial strategies across crypto, stocks and commodities.
Added
Brandfetch MCP
Brandfetch's MCP server for searching brands and retrieving logos, design assets and company data.
Added
BuildShip
Visual AI workflow builder for automating backends, building tools for AI agents and spinning up APIs.
Added
Canva MCP
Canva's MCP server for creating, searching, editing and exporting designs from AI assistants.
Added
Coddo
Desktop app that puts a visual interface and voice input on top of terminal coding agents.
Added
ExcaliClaw
Hand-drawn diagram workspace your agent can draw in via MCP (Claude, Cursor, VS Code).
Added
Google Deep Review
Google Research's multi-agent system that checks research papers, design docs, and legal or financial documents for logical gaps and unsupported claims.
Added
Ludo.ai
AI assistant for game designers: market research, concept ideas, game design docs and asset generation.
Added
Magia Trade
No-code visual strategy lab with AI agents that send signals and deploy live trading on Binance and B3.
Added
Make
Visual automation platform with AI agents.
Added
Picsart GenAI MCP
Picsart's MCP server for generating and editing images, video and audio with 150+ models from 20+ vendors.
Added
Restack
Platform for designing, testing and running reliable agents at enterprise scale on Kubernetes.
Added
TwelveLabs Jockey MCP
TwelveLabs' hosted MCP server for Jockey, a video-understanding agent that searches, tracks entities and answers questions across your videos and images with clip citations.
Added
Valossa Assistant MCP
EU-based video AI MCP server that lets Claude and other agents upload and search videos and pull transcripts, visual scenes, soundbites and ready-made clips.
Added
YRIKKA Text-to-Model
YRIKKA's ORION workflow that turns a plain-language mission description and a few unlabeled images into generated training data, candidate models and an evaluated, selected vision model.
Added
GitHub repos (34)
| Repo | GitHub stars | Licence | Last push |
|---|---|---|---|
| MarkItDown ↗ | 190,824 | — | — |
| Dify ↗ | 158,410 | Modified Apache License 2.0 with additional conditions | 2026-10-18 |
| Langflow ↗ | 155,757 | MIT | 2026-10-16 |
| LocalAI ↗ | 49,586 | MIT | 2026-10-17 |
| OpenHuman ↗ | 42,113 | GNU GPL v3.0 | 2026-10-18 |
| Next AI Draw.io ↗ | 36,280 | Apache License 2.0 | 2026-10-18 |
| AgentScope ↗ | 33,376 | Apache License 2.0 | 2026-10-15 |
| FastGPT ↗ | 29,851 | — | — |
| Sim Studio ↗ | 29,835 | Apache License 2.0 | 2026-10-17 |
| Framelink Figma MCP ↗ | 16,002 | — | — |
| Botpress ↗ | 14,956 | — | — |
| Plannotator ↗ | 9,468 | Apache License 2.0 | 2026-10-17 |
| BAML ↗ | 9,421 | — | — |
| Activeloop ↗ | 9,252 | Apache License 2.0 | 2026-05-21 |
| Talk to Figma MCP ↗ | 7,059 | MIT | 2026-07-26 |
Top 15 of 34 by stars. Stars and licence come from each repo, checked when the listing was last verified.
FAQ
What are the best AI tools for images and design focused on images and design?
We list 49. The first three by GitHub stars and featured status are MarkItDown: Microsoft's Python tool and MCP server that converts PDFs, Office documents, images, audio and web pages to Markdown for LLM and agent pipelines.; Dify: Open-source platform for building LLM apps and agents visually.; Langflow: Visual drag-and-drop builder for AI agents and workflows that you can run locally, deploy as an API or expose as an MCP server.
Are there free or open-source options?
Yes: 28 open source, 3 source-available, 10 free or freemium, 2 paid, usage-based or enterprise, 6 pricing on the maker's site. Pricing is as each maker states it.
More from images and design
Tools are grouped by what each says it does. Missing one? Submit it free.