← Use cases · Coding agents & IDE assistants
AI agent tools for image generation
Short answer: Our top pick for image generation: LocalAI, with the highest AgentPick Score (88/100) among tools tagged "image-generation". Runners-up: locally-uncensored (70) and mlx-serve (69). Compare what each does, its license and how recently it was updated below.
| # | Tool | What it does | Score | Stars | License | Updated |
|---|---|---|---|---|---|---|
| #1 | LocalAI | LocalAI is the open-source AI engine. Run any model - LLMs, vision, voice, image, video - on any hardware. No GPU required. | 88/100 | ★ 50k | MIT | 14 Oct 2026 |
| #2 | locally-uncensored | The all-in-one local AI studio for your desktop: chat, image and video generation and a coding agent in one free, open source app. Windows and Linux. … | 70/100 | ★ 2.3k | AGPL-3.0 | 14 Oct 2026 |
| #3 | mlx-serve | Native LLM inference server for Apple Silicon. OpenAI + Anthropic API compatible. No Python. Zig backend, Swift frontend macOS app with chat, music, v… | 69/100 | ★ 1.9k | See repo | 14 Oct 2026 |
| #4 | skills | Get production-ready images, video, audio, and 3D from any AI agent: skills that pick the right model, price before spending, and keep characters and … | 69/100 | ★ 1k | MIT | 14 Oct 2026 |
| #5 | ima2-gen | Local-first visual generation runtime and studio for people and coding agents, with reproducible image and video workflows across multiple providers. | 69/100 | ★ 870 | MIT | 12 Oct 2026 |
| #6 | comfyui-mcp | Local-first, agent-native control plane for ComfyUI — MCP server + sidebar agent that generates images, video & audio, authors and runs workflows, and… | 69/100 | ★ 824 | MIT | 14 Oct 2026 |
| #7 | Nomi | Open-source AI video workbench. Bring any model or your local ComfyUI, and let Claude Code / Codex / Cursor direct it over MCP — storyboard, reference… | 65/100 | ★ 571 | AGPL-3.0 | 14 Oct 2026 |
| #8 | OpenMontage | World's first open-source, agentic video production system. 12 production pipelines, 100+ tools, 700+ agent skill and production-knowledge files. Turn… | 63/100 | ★ 68k | AGPL-3.0 | 12 Oct 2026 |
| #9 | guaardvark | Self-hosted AI studio on your own GPU: chat with your files (RAG), screen and browser agents, coding swarms, LoRA training, an MCP server for Claude C… | 63/100 | ★ 263 | MIT | 14 Oct 2026 |
| #10 | dsh-image-gen | AI image studio for DeepSeek Harness — generate, edit & compare images in chat, with 500+ prompts, gallery, multi-model workflows and ComfyUI. | 62/100 | ★ 598 | Apache-2.0 | 13 Oct 2026 |
| #11 | AI-Canvas-tauri | Local-first AI canvas for visual workflows, AI short drama, image/video generation, storyboarding and asset management. ComfyUI, AI agents, MCP & Blen… | 56/100 | ★ 226 | See repo | 14 Oct 2026 |
| #12 | guizang-ppt-skill | AI-agent Skill for generating polished HTML slide decks: editorial magazine and Swiss layouts, image prompts, social covers, and a WebGL/low-power pre… | 51/100 | ★ 28k | AGPL-3.0 | 7 Aug 2026 |
| #13 | open-webui-tools | Open‑WebUI Tools is a modular toolkit designed to extend and enrich your Open WebUI instance, turning it into a powerful AI workstation. With a suite … | 40/100 | ★ 822 | MIT | 11 Oct 2026 |
| #14 | nano-banana-pro-prompts-recommend-skill | AI skill for OpenClaw & Claude Code — recommend from 10000+ Nano Banana Pro (Gemini) image prompts. Smart search by use case, content remix, sample im… | 39/100 | ★ 1.9k | See repo | 14 Oct 2026 |
| #15 | codex-slides | 🎨 Open-source AI slide studio inside Codex: image-native decks, every slide a full visual canvas. ⚡ 10+ high-quality slides in ~4–5 minutes — Fast mo… | 39/100 | ★ 938 | MIT | 21 Jul 2026 |
| #16 | MiniMax-MCP | Official MiniMax Model Context Protocol (MCP) server that enables interaction with powerful Text to Speech, image generation and video generation APIs… | 37/100 | ★ 1.6k | MIT | 20 Aug 2026 |
| #17 | guizang-social-card-skill | 🪧 Claude Code / Codex skill — generate Xiaohongshu carousels & WeChat 21:9+1:1 cover pairs. Editorial × Swiss visual systems, 28 layouts, 10 themes, … | 31/100 | ★ 7.5k | AGPL-3.0 | 1 Jul 2026 |
| #18 | ian-xiaohei-scenes | Xiaohei 2.0 Codex Skill for Chinese real-object article illustrations and long-scroll story images | 31/100 | ★ 533 | MIT | 4 Jun 2026 |
| #19 | guizang-yingzao-skill | 🏯 Claude Code / Codex skill — transform Chinese architecture, cultural places & travel photos into art-directed editorial posters with GPT Image. 中国古… | 21/100 | ★ 503 | See repo | 3 Sept 2026 |
| #20 | comfy-pilot | MCP server + embedded terminal that lets Claude Code see and edit your ComfyUI workflows | 17/100 | ★ 231 | MIT | 16 Feb 2026 |
Source: each project's public GitHub repository (description, stars, license, last push). Listed tools aren't tested or ranked by AgentPick.
How to choose
- Check which models and providers it supports.
- Prefer tools that show diffs and ask before running commands.
- Look for recent commits: coding agents change fast.
Get the best new agent tools every week. Free, with a verdict on each. Get the weekly digest
Related
AI agent tools for agent skills →
Coding agents & IDE assistants
AI agent tools for developer tools →
Coding agents & IDE assistants
AI agent tools for the terminal →
Coding agents & IDE assistants
AI agent tools for macOS →
Coding agents & IDE assistants
AI agent tools for agent harnesses →
Coding agents & IDE assistants
AI agent tools for agent orchestration →
Coding agents & IDE assistants
AgentPick Weekly
The week's new agent tools with a verdict on each, every week. Free. We'll email you a link to confirm, and you can unsubscribe any time. See our Privacy Policy.