Cohort of 75 admitted agents tagged capability:automation. Composite below is the cohort's average AgentScore.
| Cmp | Rank | Agent | 24h | Score | Δ24h | Watch |
|---|---|---|---|---|---|---|
| #28 | mobilerun mitmobilerun: Automate your mobile devices with natural language commands - an LLM agnostic mobile Agent ????. | 5 | 47.3 | 0.00 | ||
| #32 | claude-code claude-code: Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflows - all through natural language commands. | 1 | 46.3 | +3.04 | ||
| #42 | career-ops mitclicareer-ops: AI-powered job search system built on Claude Code. 14 skill modes, Go dashboard, PDF generation, batch processing. | 7 | 43.0 | 0.00 | ||
| #50 | presenton apache-2.0presenton: Open-Source AI Presentation Generator and API (Gamma, Beautiful AI, Decktopus Alternative). | 7 | 41.3 | +0.19 | ||
| #53 | RD-Agent mitRD-Agent: Research and development (R&D) is crucial for the enhancement of industrial productivity, especially in the AI era, where the core aspects of R&D are mainly focused on data and models. We are committed to automating these high-value generic R&D processes through R&D-Agent, whi... | 6 | 40.8 | 0.00 | ||
| #55 | langflow mitlangflow: Langflow is a powerful tool for building and deploying AI-powered agents and workflows. | 6 | 40.7 | 0.00 | ||
| #56 | RuView mitide-pluginRuView: π RuView turns commodity WiFi signals into real-time spatial intelligence, vital sign monitoring, and presence detection — all without a single pixel of video. | 5 | 40.0 | 0.00 | ||
| #71 | MoneyPrinterTurbo mitide-pluginMoneyPrinterTurbo: 利用 AI 大模型和自动化工作流，根据主题或关键词一键生成高清短视频。Generate HD short videos from a topic or keyword with an automated AI workflow. | 38.8 | -0.03 | |||
| #78 | cli apache-2.0clicli: Google Workspace CLI ??? one command-line tool for Drive, Gmail, Calendar, Sheets, Docs, Chat, Admin, and more. Dynamically built from Google Discovery Service. Includes AI agent skills. | 1 | 37.5 | 0.00 | ||
| #84 | cua mitlibrarycua: Open-source infrastructure for Computer-Use Agents. Sandboxes, SDKs, and benchmarks to train and evaluate AI agents that can control full desktops (macOS, Linux, Windows). | 1 | 36.5 | +0.02 | ||
| #88 | skills mitlibraryskills: Public repository for Agent Skills. | 2 | 36.2 | 0.00 | ||
| #103 | owl owl: ???? OWL: Optimized Workforce Learning for General Multi-Agent Assistance in Real-World Task Automation. | 3 | 35.0 | 0.00 | ||
| #104 | UFO mitUFO: UFO??: Weaving the Digital Agent Galaxy. | 23 | 34.8 | +2.61 | ||
| #124 | leon mitleon: ???? Leon is your open-source personal assistant. | 4 | 32.9 | 0.00 | ||
| #127 | harness-anything mitcliharness-anything: CLI harness for WPS Office -- let AI agents control Writer, Calc & Impress via COM automation. | 177 | 32.7 | +10.01 | ||
| #130 | eve apache-2.0libraryeve: The Framework for Building Agents. | 4 | 32.3 | +0.04 | ||
| #131 | llm_wiki mitllm_wiki: LLM Wiki is a cross-platform desktop application that turns your documents into an organized, interlinked knowledge base — automatically. Instead of traditional RAG (retrieve-and-answer from scratch every time), the LLM incrementally builds and maintains a persistent wiki from... | 6 | 32.3 | 0.00 | ||
| #132 | ComfyUI-Copilot mitide-pluginComfyUI-Copilot: An AI-powered custom node for ComfyUI designed to enhance workflow automation and provide intelligent assistance. | 33 | 32.3 | +3.19 | ||
| #148 | Integuru agplInteguru: The first AI agent that builds permissionless integrations through reverse engineering platforms' internal APIs. | 54 | 30.6 | +3.45 | ||
| #174 | zcf mitclizcf: Zero-Config Code Flow for Claude code & Codex. | 7 | 29.0 | 0.00 | ||
| #175 | waoowaoo ide-pluginwaoowaoo: ???????????????????????? AI ?????????????????????Industry-first professional AI Agent platform for controllable film & video production. From shorts to live-action with Hollywood-standard workflows. | 7 | 29.0 | 0.00 | ||
| #245 | review-forge review-forge: review-forge is an Agent Skill for structured, auditable code review workflows. | 30 | 24.9 | -1.30 | ||
| #323 | oh-my-hermes oh-my-hermes: An opinionated workflow layer for building, shipping, and operating apps with Hermes Agent. | 14 | 22.7 | 0.00 | ||
| #375 | andrej-karpathy-skills mitide-pluginandrej-karpathy-skills: Codex-first conversion of Karpathy-inspired coding agent guidelines. | 18 | 20.9 | 0.00 | ||
| #378 | jev-skill mitjev-skill: An awesome collection of Jev use cases, workflows, and agent skills. | NEW | 20.9 | — | ||
| #421 | locoagent mitlocoagent: AI-powered social media agent with real browser automation. | 22 | 19.7 | 0.00 | ||
| #423 | MD_Redactor mitMD_Redactor: A simple Markdown editor for adding inline edits and review notes directly into MD files for AI-assisted workflows. | 49 | 19.7 | -0.73 | ||
| #463 | ctf-wiki mitctf-wiki: 面向 LLM Agent 的 CTF 知识图谱 — 基于 Karpathy/LLM Wiki 三层架构. | 16 | 18.9 | 0.00 | ||
| #470 | machine-learning-library librarymachine-learning-library: A hand-curated library of the best machine learning education — 590 docs (78 arXiv papers, 474 course lectures from Stanford/MIT/Karpathy/fast.ai, 38 explainer articles), normalized to Markdown with full provenance. A clean ML corpus/dataset for learning, RAG, and fine-tuning. | 16 | 18.8 | 0.00 | ||
| #471 | brand-docs mitbrand-docs: BrandDocs turns existing Word, PowerPoint and Excel templates into reusable AI document-generation skills. Unlike generic AI document generators, it preserves brand, structure, styles and formulas by construction. | 16 | 18.8 | 0.00 | ||
| #479 | FableCodex agplFableCodex: 🗿 FableCodex is a Codex-style coding agent workflow that plans like Fable. | 92 | 18.6 | -1.47 | ||
| #516 | workflow-cookbook mitworkflow-cookbook: 《织经》Loom · Claude Code Dynamic Workflows（CLAUDE_CODE_WORKFLOWS）配方手册：29 章 + 6 附录，每个配方都在本机真跑过、附 Run ID，中英双语。 | Loom · a recipe book for Claude Code's Dynamic Workflows. 29 chapters + 6 appendices, every recipe actually run, with its Run ID. | 13 | 18.1 | 0.00 | ||
| #531 | GodModeSkill mitGodModeSkill: Multi-LLM cross-review workflow for Claude Code. /work orchestrates plan/implement/bug-fix with 3 different model families voting on every gate. | 11 | 17.7 | 0.00 | ||
| #540 | harness mitmcp-serverharness: AI-driven user testing for iOS Simulator, macOS apps, and web apps. Write a goal in plain language; an LLM agent drives the UI and reports friction. macOS 14+, Swift 6. | 11 | 17.6 | 0.00 | ||
| #572 | agentic-sop-to-work mitagentic-sop-to-work: Turn human SOPs into deterministic, gated agentic workflows — a Claude Code plugin. | 7 | 17.0 | 0.00 | ||
| #587 | agentwatch mitagentwatch: Apple Watch notifications for Claude Code and AI agent workflows. | 5 | 16.9 | 0.00 | ||
| #604 | HarnessFlow HarnessFlow: Harness coding workflow for codex, claude, github copilot. | 7 | 16.6 | 0.00 | ||
| #745 | LLM-Wiki-Skilled apache-2.0LLM-Wiki-Skilled: This is my implementation of Karpathy's LLM Wiki. A key highlight is the use of agent skills to enforce workflow rigidity and mitigate agent behavioral deviation. | 10 | 14.3 | 0.00 | ||
| #789 | ZeroScript-Free gplmcp-serverZeroScript-Free: ZeroScript Free: Turn DeepSeek into a Roblox Studio agent. Browser extension + local bridge. Read/edit scripts, run Luau, generate assets all from DeepSeek chat. Robust agentic. No terminal needed. | 13 | 13.5 | 0.00 | ||
| #809 | JevRev mitide-pluginJevRev: An LLM + Jev workflow. Boost your vertebrate brain with a spine inside. | 14 | 13.2 | 0.00 | ||
| #828 | ai-landing-consultant mitsaasai-landing-consultant: 让完全不懂技术的人拥有一台真正每天在干活的专属 AI agent ｜ Open-source consulting playbook: ship self-hosted AI agents that non-technical users actually use. | 18 | 13.0 | 0.00 | ||
| #832 | instagram-reels-transcript-api mitmcp-serverinstagram-reels-transcript-api: Instagram Reels Transcript API examples using Apify. Integrations for Python, Node.js, Java, Go, Rust, cURL, batch processing, and MCP workflows for ChatGPT, Claude, and Gemini. | 19 | 12.9 | 0.00 | ||
| #843 | takt takt: TAKT: TAKT Agent Koordination Topology - AI Agent Workflow Orchestration. | 21 | 12.8 | 0.00 | ||
| #867 | stake-engine-skills mitstake-engine-skills: Two Claude Code skills bundling the official Stake Engine Math SDK + Web SDK workflows — bootstrap, distilled docs, approval checklist. | 22 | 12.5 | 0.00 | ||
| #882 | @adminforth/agent @adminforth/agent: AI agent plugin for AdminForth with tool-based workflows and persistent chat sessions. | 29 | 12.2 | 0.00 | ||
| #890 | fayzan123/claude-workflow-composer fayzan123/claude-workflow-composer: discovered AI agent. | 26 | 12.0 | 0.00 | ||
| #907 | unity-coding-skills ide-pluginunity-coding-skills: Skills and an agent for developing Unity projects with Claude Code — maintainable test design, test-first workflow, coding guidelines, scene editing, and more. | 25 | 11.7 | 0.00 | ||
| #925 | langgraph-langchain-agent-setup librarylanggraph-langchain-agent-setup: LangGraph — langchain agent, langchain setup, ai agent workflow. | 385 | 11.5 | -6.00 | ||
| #983 | llm-agent-platform llm-agent-platform: Distributed systems reliability patterns applied to LLM agent workflows. NestJS, PostgreSQL, BullMQ, LangGraph, Python/FastAPI. | 36 | 10.6 | 0.00 | ||
| #1016 | agent-assh mitagent-assh: SSH workflow helper for LLM agents. | 72 | 10.2 | -0.44 | ||
| #1125 | graphflow mitgraphflow: A lightweight, LangGraph-inspired stateful workflow engine for Rust. | 25 | 8.6 | 0.00 | ||
| #1132 | @novu/agent-toolkit @novu/agent-toolkit: Novu Agent Toolkit - expose Novu notification workflows as LLM agent tools. | 22 | 8.5 | 0.00 | ||
| #1169 | la-machina-engine mcp-serverla-machina-engine: Headless, multi-provider LLM agent engine for workflow automation. Pause/resume, MCP, skills, R2/Workers compatible. | 12 | 7.7 | 0.00 | ||
| #1170 | nest nest: LLM agent workflow tool. | 34 | 7.5 | 0.00 | ||
| #1185 | simonjisu/TwinBI librarysimonjisu/TwinBI: Business intelligence (BI) increasingly combines dashboard interaction with LLM-based assistance, but these two modes often fall out of sync during multi-step analysis. As users switch between direct dashboard manipulation and natural-language queries, it becomes difficult to... | 158 | 3.5 | -6.00 | ||
| #1202 | llm-agent-framework libraryllm-agent-framework: Portable governance, workflow, and standards infrastructure for disciplined LLM Agent collaboration. | 79 | 2.4 | -6.00 | ||
| #1265 | simple-llm-agent mitsimple-llm-agent: A minimal ReAct-style LLM Agent with tool use, built for task automation with MiMo V2.5-Pro API | 49 | 1.5 | -6.00 | ||
| #1238 | llm-agentic-workflow-sandbox mitllm-agentic-workflow-sandbox: LangGraph-based sandbox for first steps programming llm-based agentic workflows in pharmacometrics. | 49 | 1.5 | -6.00 | ||
| #1230 | LLM-Agent-Development-Services-for-Intelligent-AI-Automation LLM-Agent-Development-Services-for-Intelligent-AI-Automation: LLM Agent Development Services for Intelligent AI Automation. | 50 | 1.5 | -6.00 | ||
| #1229 | LLM-Agent-Development-for-Intelligent-AI-Automation-Systems LLM-Agent-Development-for-Intelligent-AI-Automation-Systems: Large Language Model (LLM) agent development is rapidly transforming how businesses build intelligent automation systems, streamline workflows, automate customer interactions, and improve operational efficiency. | 50 | 1.5 | -6.00 | ||
| #1371 | or3-workflow-core or3-workflow-core: Headless workflow engine with LLM agent orchestration. | 40 | 0.0 | -6.00 | ||
| #1312 | detect-agent detect-agent: Detect if code is running in an AI agent or automated development environment. | 42 | 0.0 | -6.00 | ||
| #1287 | @ai.ntellect/core @ai.ntellect/core: In-process workflow engine with typed graphs, events, and LLM agent support. | 45 | 0.0 | -6.00 | ||
| #1277 | @agentic-surfaces/connector-jpd @agentic-surfaces/connector-jpd: Jira Product Discovery (JPD) helpers for [agentic-surfaces](https://github.com/dalebaldwin/agentic-surfaces) workflows. | 45 | 0.0 | -6.00 | ||
| #1298 | claude-gombwe mcp-serverclaude-gombwe: Autonomous agent control panel powered by Claude Code ??? orchestrate AI tasks, triggers, workflows, and skills from anywhere. | 44 | 0.0 | -6.00 | ||
| #1412 | @uncaged/workflow-agent-builtin @uncaged/workflow-agent-builtin: `uwf-builtin` agent — built-in LLM agent with file read/write and shell tools. | 39 | 0.0 | -6.00 | ||
| #1374 | 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. | 40 | 0.0 | -6.00 | ||
| #1355 | @lucaperret/tidal-cli cli@lucaperret/tidal-cli: CLI for Tidal music streaming service, designed for LLM agent automation. | 41 | 0.0 | -6.00 | ||
| #1275 | @agentic-surfaces/agent @agentic-surfaces/agent: The agent runner for [agentic-surfaces](https://github.com/dalebaldwin/agentic-surfaces) — a thin wrapper over the Claude Agent SDK used by `agent.run` nodes. Supports capability **profiles** (`constrained` / `surface` / `full`), structured **decision** o | 45 | 0.0 | -6.00 | ||
| #1278 | @agentic-surfaces/core @agentic-surfaces/core: The engine core for [agentic-surfaces](https://github.com/dalebaldwin/agentic-surfaces) — workflow schema + loader, the node executor and handler registry (`task.http`, `task.transform`, `task.branch`, `task.foreach`, `task.cache-unseen`/`task.cache-mark` | 45 | 0.0 | -6.00 | ||
| #1382 | @qase/mcp-server mcp-server@qase/mcp-server: Official MCP server for Qase Test Management Platform. | 41 | 0.0 | -6.00 | ||
| #1380 | PumpFun-Trainer_V1 mitPumpFun-Trainer_V1: An advanced AI‑driven trading utility for Solana meme‑coins, featuring sniper, auto‑sell, MEV protection, multi‑wallet, alerts, and price monitoring. | 40 | 0.0 | -6.00 | ||
| #1362 | MedSkillOS mitcliMedSkillOS: Medical-grade agent skills for clinical and biomedical workflows. | 41 | 0.0 | -6.00 | ||
| #1279 | @agentic-surfaces/server @agentic-surfaces/server: The dashboard server for [agentic-surfaces](https://github.com/dalebaldwin/agentic-surfaces) — an HTTP + SSE API (`/api/workflows`, `/api/run`, `/api/events`, `/api/cache`, …) plus the bundled web UI (workflow graph, live runs, agent activity, cache inspe | 45 | 0.0 | -6.00 | ||
| #1276 | @agentic-surfaces/cli cli@agentic-surfaces/cli: The command-line runner for [agentic-surfaces](https://github.com/dalebaldwin/agentic-surfaces) — a local-first, agent-in-the-loop workflow engine. Loads a project's `agentic-surfaces.config.yaml` + `workflows/*.yaml` + `agents/*.md`, runs the scheduler, | 45 | 0.0 | -6.00 |
Browse all sectors at /sectors.