Cohort of 43 admitted agents tagged capability:vision. Composite below is the cohort's average AgentScore.
| Cmp | Rank | Agent | 24h | Score | Δ24h | Watch |
|---|---|---|---|---|---|---|
| #19 | MinerU MinerU: Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows. | 1 | 50.7 | -0.15 | ||
| #70 | awesome-generative-ai-guide mitide-pluginawesome-generative-ai-guide: A one stop repository for generative AI research updates, interview resources, notebooks and much more!. | 1 | 43.9 | -0.00 | ||
| #148 | esp32-iphone-agent mitesp32-iphone-agent: Let an AI model use a real iPhone with a $7 ESP32: AirPlay eyes, USB HID hands, any OpenAI-compatible vision model. No Mac, no developer account, no jailbreak. | 2 | 37.2 | +0.05 | ||
| #182 | qwen21-nsfw-pose-skill qwen21-nsfw-pose-skill: Qwen-Image 2.1 NSFW/姿势出图 skill：作者级提示词配方 + NSFW LoRA + 136 姿势 VNCCS 人偶控制；适用 Claude Code / Codex / Cursor / OpenClaw | 53 | 35.3 | +1.84 | ||
| #184 | ian-xiaohei-illustrations mitian-xiaohei-illustrations: 中文小黑怪诞正文配图生成 Skill | 16:9 白底手绘 | 少量红橙蓝批注 | Codex Skill. | 2 | 35.3 | +0.00 | ||
| #251 | ppt-master mitide-pluginppt-master: AI generates natively editable PPTX from any document ??? real PowerPoint shapes with native animations, not images ?? by Hugo He. | 3 | 32.7 | +0.00 | ||
| #290 | model:empero-ai/Qwythos-9B-Claude-Mythos-5-1M-GGUF model:empero-ai/Qwythos-9B-Claude-Mythos-5-1M-GGUF: discovered AI agent. | 5 | 31.6 | +0.05 | ||
| #325 | awesome-generative-ai awesome-generative-ai: A curated list of Generative AI tools, works, models, and references. | 10 | 30.7 | +0.00 | ||
| #355 | model:TaichuAI/ZDTaichu5.0-9B ide-pluginmodel:TaichuAI/ZDTaichu5.0-9B: discovered AI agent. | 5 | 30.1 | +0.15 | ||
| #423 | model:orcarouter/Qwen3.8-27B-Uncensored-FP8 model:orcarouter/Qwen3.8-27B-Uncensored-FP8: discovered AI agent. | 6 | 28.7 | +0.02 | ||
| #459 | uni-robot-agent mituni-robot-agent: Democratizing Robot-Use Agents: A Unified Harness with Open Models. | 17 | 28.1 | +0.49 | ||
| #565 | model:HauhauCS/Gemma4-26B-A4B-Uncensored-HauhauCS-Balanced model:HauhauCS/Gemma4-26B-A4B-Uncensored-HauhauCS-Balanced: discovered AI agent. | 7 | 26.8 | +0.04 | ||
| #567 | ARIS-in-AI-Offer mitide-pluginARIS-in-AI-Offer: Bilingual ML / LLM / multimodal / diffusion / agent / generative-model interview cheat sheets (秋招经验手册) — single-file HTML reads anywhere on phone, iPad, and laptop — auto-generated by the ARIS /render-html workflow 🌱. | 8 | 26.8 | +0.02 | ||
| #572 | model:byteshape/Qwen3.8-27B-GGUF model:byteshape/Qwen3.8-27B-GGUF: discovered AI agent. | 2 | 26.7 | +0.03 | ||
| #584 | illo-skill mitide-pluginillo-skill: illo — an AI agent skill that turns ideas and articles into original print-style editorial illustrations, starring a recurring mascot. Ten bundled looks, custom characters, OpenRouter-powered. | 10 | 26.6 | -0.01 | ||
| #611 | model:sensenova/SenseNova-6.8-Code2Video ide-pluginmodel:sensenova/SenseNova-6.8-Code2Video: discovered AI agent. | 7 | 26.3 | +0.01 | ||
| #612 | model:cyjin-yl/Qwen3.8-27B-Uncensored-Cyber-agentic-imatrix-GGUF model:cyjin-yl/Qwen3.8-27B-Uncensored-Cyber-agentic-imatrix-GGUF: discovered AI agent. | 15 | 26.3 | -0.02 | ||
| #625 | model:Jackrong/Qwen3.5-9B-DeepSeek-V4-Flash-GGUF model:Jackrong/Qwen3.5-9B-DeepSeek-V4-Flash-GGUF: An AI agent project. | 12 | 26.2 | +0.01 | ||
| #648 | Hent-ai mitHent-ai: Emotion Image Attachment Plugin for AI agents — Auto-classify emotions via LLM and attach matching images to Discord messages. | 23 | 26.0 | 0.00 | ||
| #659 | Oaklight/zerodep ide-pluginOaklight/zerodep: Third-party Python libraries introduce dependency management overhead, supply chain risk, and deployment friction in constrained environments. A natural question is how much of this ecosystem can be replicated using only Python's standard library -- and at what correctness and... | 19 | 25.9 | +0.03 | ||
| #696 | television television: The missing GUI for personal agents. Television gives you and your agent a visual space for creating and working with artifacts. | 22 | 25.6 | -0.02 | ||
| #700 | division-sh/swarm division-sh/swarm: discovered AI agent. | 255 | 25.6 | +2.40 | ||
| #725 | model:Jackrong/Qwopus3.6-27B-v2-MTP-GGUF model:Jackrong/Qwopus3.6-27B-v2-MTP-GGUF: discovered AI agent. | 30 | 25.3 | -0.11 | ||
| #841 | qwen-image-2.1-skill apache-2.0qwen-image-2.1-skill: 🎨 Agentic skill for Qwen-Image-2.1: Rewrites and optimizes text-to-image and multi-image editing prompts using official Alibaba specifications. Compatible with skills.sh and all AI agents. | 17 | 24.2 | -0.02 | ||
| #864 | model:HauhauCS/Qwen3.6-27B-Uncensored-HauhauCS-Balanced model:HauhauCS/Qwen3.6-27B-Uncensored-HauhauCS-Balanced: discovered AI agent. | 44 | 24.0 | -0.27 | ||
| #880 | model:Jackrong/Qwopus3.6-35B-A3B-v1-GGUF model:Jackrong/Qwopus3.6-35B-A3B-v1-GGUF: discovered AI agent. | 19 | 23.9 | -0.06 | ||
| #892 | awesome-images awesome-images: Try flatkey.ai for 40% saving! Generate practical images ready for all your work needs!!! | 158 | 23.8 | -1.17 | ||
| #1000 | imnotarobot mitmcp-serverimnotarobot: I am not a robot — a captcha solver for macOS: local model, Gemini vision, a stealth browser for checkbox captchas, RuCaptcha as the last resort. 2Captcha-compatible API and an MCP server. | 11 | 22.9 | 0.00 | ||
| #1008 | model:Jackrong/Qwopus3.6-27B-v2-GGUF model:Jackrong/Qwopus3.6-27B-v2-GGUF: discovered AI agent. | 38 | 22.8 | -0.25 | ||
| #1090 | model:lordx64/Qwable-v1 model:lordx64/Qwable-v1: discovered AI agent. | 5 | 22.2 | +0.01 | ||
| #1149 | model:MiniMaxAI/MiniMax-M3-MXFP8 ide-pluginmodel:MiniMaxAI/MiniMax-M3-MXFP8: discovered AI agent. | 87 | 21.7 | +0.77 | ||
| #1154 | RUCBM/TIPS libraryRUCBM/TIPS: Process reward models (PRMs) have become a key component for LLMs, as their step-level feedback supports both post-training and test-time reasoning. However, training strong PRMs remains costly: human step annotation is difficult to scale, while Monte Carlo estimation is compu... | 104 | 21.6 | -0.76 | ||
| #1179 | model:Apexintelligence-AI/Apex-35B-V1.0 model:Apexintelligence-AI/Apex-35B-V1.0: discovered AI agent. | 16 | 21.4 | +0.18 | ||
| #1226 | sleuthline mitide-pluginsleuthline: Windows DFIR pipeline: from a KAPE collection, a memory image and network captures to an evidence-backed incident response report, with an LLM agent. | 10 | 21.0 | 0.00 | ||
| #1398 | model:xtools-at/DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic model:xtools-at/DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic: discovered AI agent. | 56 | 19.6 | +0.63 | ||
| #1603 | Hyu-Zhang/MARS ide-pluginHyu-Zhang/MARS: This report presents MARS, short for Multimodal Agentic Reasoning with Source selection, our system for the CASTLE Challenge at EgoVis 2026. Participants must answer 185 closed-form questions over the CASTLE 2024 dataset. In contrast to prior single-video egocentric benchmarks... | 7 | 18.0 | 0.00 | ||
| #1665 | AstraOS ide-pluginAstraOS: AstraOS is an AI-driven productivity platform built with Flutter, FastAPI, PostgreSQL, and modern LLM integrations. It provides natural-language task management, semantic note search, OCR-powered document processing, intelligent reminders, and personalized planning—designed as... | 4 | 17.5 | 0.00 | ||
| #1721 | Team1-MountainDew-HireForce mitTeam1-MountainDew-HireForce: HireForce is an AI-powered recruitment automation platform that streamlines the end-to-end hiring process using intelligent LLM agents. It automates resume screening, conducts adaptive AI-driven interviews, evaluates candidate responses, and implements a two-stage computer vis... | 11 | 17.2 | 0.00 | ||
| #1795 | model:Jackrong/Qwopus3.6-27B-v2 model:Jackrong/Qwopus3.6-27B-v2: discovered AI agent. | 30 | 15.8 | -0.64 | ||
| #2117 | XiiiiaoT XiiiiaoT: AI Engineering | Computer Vision | LLM & Agents. | 12 | 11.5 | 0.00 | ||
| #2198 | polymarket-copy-trading-bot-clob-ai mitpolymarket-copy-trading-bot-clob-ai: Advanced Polymarket Copy Trading Bot & CLOB Automation Engine. Integrated with Claude 4.0 Omni for AI-driven sentiment analysis, sub-85ms execution, and real-time whale mirroring on Polygon network. Optimized for HFT liquidity provision and algorithmic prediction market trading. | 13 | 10.0 | 0.00 | ||
| #2281 | @gencraft/mcp-server mcp-server@gencraft/mcp-server: MCP server for GenCraft AI image generation. Exposes generate_image / get_task / batch_get_tasks tools to any MCP-compatible LLM agent (Claude Desktop, Cursor, Cline, …). | 54 | 8.2 | +4.01 | ||
| #2324 | @fifthrevision/axle @fifthrevision/axle: Axle core runtime for building agentic LLM applications. | 21 | 6.4 | 0.00 |
Browse all sectors at /sectors.