Week 42, 2026: the AI agents gaining momentum
Oct 12 to Oct 18, 2026. The top three were REA, Anatomy, Our Free Model.
Frozen Oct 29, 2026 with scoring method v1. This week was rebuilt from star history collected before the site launched. Methodology
| Rank | Change | Agent | Type | Setup | Stars this week | Stars |
|---|---|---|---|---|---|---|
| 1 | = | REA REA is an MCP server that lets AI agents reverse engineer apps and native binaries to explain how a feature works. | MCP server or connector | Setup level 4 of 5: Guided command-line setup | +207,236 | 421k |
| 2 | ↑1 | Anatomy Anatomy is a skill that builds interactive isometric illustrations of machines and systems to explain technical ideas for anyone using Claude or Codex. | Skill or plugin | Setup level 4 of 5: Guided command-line setup | +12,225 | 24k |
| 3 | ↓1 | Our Free Model 在 dsh 里装上这个插件即可,无需登录、注册或填 API Key,就能使用包括 DeepSeek V4.1 Flash、Kimi K3 在内的前沿模型, 完全免费,不限量。 All you do is install this plugin in dsh: no login, no sign-up, no API key, the frontier models are just there, DeepSeek V4.1 Flash and Kimi K3 among them. Completely free, with no usage cap. | Not yet described | Not stated | +15,522 | 56.5k |
| 4 | ↑29 | SolidCraft SolidCraft: an open-source parametric 3D CAD application built in pure Rust. Desktop, web, and automation through MCP. | Not yet described | Not stated | +5,324 | 13k |
| 5 | ↑37 | XERJ XERJ is a local search engine and MCP server that lets AI agents search code, docs and logs without reading files one by one, for developers and coding-agent users. | Agent app | Setup level 4 of 5: Guided command-line setup | +4,865 | 18.7k |
| 6 | New | Clean Your TV Clean Your TV is a set of instructions for a coding assistant that removes bloat and ads from Android and Google TVs and adds a simpler home screen for people who want less clutter. | Skill or plugin | Setup level 4 of 5: Guided command-line setup | +2,609 | 49.7k |
| 7 | ↑68 | Concat The truly free, open-source, local-first, cross-platform CapCut replacement. Scriptable through a JSON-RPC API & MCP. | Not yet described | Not stated | +4,289 | 13.7k |
| 8 | New | Harvey Harvey is an agent app that finds prospects, writes and sends cold emails, and books meetings for small businesses, using your existing Claude or ChatGPT subscription. | Agent app | Setup level 4 of 5: Guided command-line setup | +1,424 | 3,963 |
| 9 | New | ARTEX ARTEX is an agent app that runs autonomous penetration tests in an isolated lab for security teams. | Agent app | Setup level 4 of 5: Guided command-line setup | +1,259 | 1,269 |
| 10 | ↓4 | magpie magpie is a local gateway app that lets you switch the AI model behind each coding agent from one menu bar for users with several agents or providers. | Agent app | Setup level 3 of 5: Install a desktop app or browser extension | +6,612 | 28.1k |
| 11 | New | new-term-radar new-term-radar is a Python tool that finds new AI product and model names early, before keyword tools list them, for people who publish pages or posts about AI tools. | Agent app | Setup level 4 of 5: Guided command-line setup | +1,103 | 2,034 |
| 12 | New | earshot earshot is an agent app that lets coding agents hear and check sound for films, demos, and games for developers making sound in code. | Agent app | Setup level 4 of 5: Guided command-line setup | +968 | 3,482 |
| 13 | New | PentAGI PentAGI is a self-hosted agent app that runs automated penetration tests against a target you describe in plain language, for security professionals. | Agent app | Setup level 4 of 5: Guided command-line setup | +5,749 | 33k |
| 14 | New | roast-room Roast Room is a council of AI advisor personas that debates a business decision in Claude Code and returns a scored verdict for business owners. | Agent app | Setup level 4 of 5: Guided command-line setup | +790 | 1,736 |
| 15 | New | Eleven Eleven is a reverse-engineering app that lets an AI agent read, explain, and patch compiled programs and Android apps for developers and security researchers. | Agent app | Setup level 3 of 5: Install a desktop app or browser extension | +762 | 954 |
| 16 | ↑25 | iFixAi iFixAi is an auditing tool that tests whether an AI agent does what it is supposed to do for businesses that run agents. | Other | Setup level 4 of 5: Guided command-line setup | +5,857 | 42.9k |
| 17 | New | my-claude-code-mods Custom Claude Code Mods that I need | Not yet described | Not stated | +1,000 | 1,105 |
| 18 | New | baoyan-agent-benchmark Sprix AI at 屿智同行 × 保研岛, an open-source benchmark for AI agents in Baoyan advising and application planning. | Not yet described | Not stated | +698 | 699 |
| 19 | ↓10 | DS Bot DS Bot is a plugin that gives you a team of long-lived bots that hand work to each other in group chats. | Skill or plugin | Setup level 3 of 5: Install a desktop app or browser extension | +1,447 | 5,012 |
| 20 | New | motionmaxxing motionmaxxing is an agent skill that turns plain AI-generated videos into motion graphics that look designed, for people making launch films and promos. | Skill or plugin | Setup level 4 of 5: Guided command-line setup | +742 | 1,265 |
| 21 | New | Andee Andee is an agent app that lives on your Android phone or Mac and operates any app for you, without integrations. | Agent app | Setup level 3 of 5: Install a desktop app or browser extension | +628 | 3,410 |
| 22 | ↑65 | codeAgent CodeAgent is an open-source coding agent that lives in your terminal. It understands your repository, plans multi-step changes, writes and edits files, runs commands and tests, and iterates until the task is done, all with a transparent, extensible tool loop. | Not yet described | Not stated | +759 | 1,018 |
| 23 | New | Ling Stack Ling Stack is a self-hosted workspace that brings AI teammates and their tool approvals into one local project channel for developers and multi-model users. | Agent app | Setup level 4 of 5: Guided command-line setup | +795 | 992 |
| 24 | ↑64 | Folkbench Folkbench is a desktop tool that switches API providers for Claude Code and Codex and ranks relay services by uptime, latency, and price for developers. | Other | Setup level 3 of 5: Install a desktop app or browser extension | +1,451 | 4,191 |
| 25 | New | context-mode context-mode is an MCP server that keeps raw tool output out of an AI coding agent's context window for developers running long coding sessions. | MCP server or connector | Setup level 2 of 5: Adds to an AI app you already use | +4,161 | 33.2k |
| 26 | New | OpenFilm OpenFilm is an agent app that lets a coding agent make videos and lets you edit them by hand for anyone making films with AI. | Agent app | Setup level 4 of 5: Guided command-line setup | +884 | 4,180 |
| 27 | ↓13 | diagram-design Diagram Design is a skill that draws editorial diagrams as single HTML files for people using AI coding agents. | Skill or plugin | Setup level 2 of 5: Adds to an AI app you already use | +7,024 | 64.2k |
| 28 | ↓21 | Replica Skill Replica skill is a set of eleven free Claude skills that clone an existing app's features and fix what its users dislike, for people building a sellable app. | Skill or plugin | Setup level 3 of 5: Install a desktop app or browser extension | +1,474 | 7,041 |
| 29 | = | Lemo-Opuscar Lemo-Opuscar is a Claude Code skill that makes short films entirely in code, with 66 film styles, for people who want a finished video without filming. | Skill or plugin | Setup level 4 of 5: Guided command-line setup | +1,345 | 10.8k |
| 30 | New | Scenario for Blender Scenario for Blender is an add-on that brings AI image, video, 3D and material generation into Blender for 3D artists and game asset makers. | Agent app | Setup level 3 of 5: Install a desktop app or browser extension | +502 | 933 |
| 31 | New | imozuru imozuru is a Claude Code skill that digs into an unfamiliar topic until it reaches the original sources, for people researching a field they do not know. | Skill or plugin | Setup level 4 of 5: Guided command-line setup | +488 | 1,408 |
| 32 | New | Orbital Context is yours. Agents are replaceable. | Not yet described | Not stated | +616 | 970 |
| 33 | ↓22 | geo-sleuth geo-sleuth is a skill that finds where a photo was taken using map geometry, elevation skylines and satellite imagery, and shows its evidence. | Skill or plugin | Setup level 4 of 5: Guided command-line setup | +1,385 | 5,475 |
| 34 | ↑14 | founder-skill founder-skill is a set of eleven free Claude skills that test a business idea before launch for solo founders and small business owners. | Skill or plugin | Setup level 3 of 5: Install a desktop app or browser extension | +688 | 2,329 |
| 35 | New | mcd-saver-strategist mcd-saver-strategist is a skill that finds the cheapest combination of McDonald's China menu items and coupons for a given order. | Skill or plugin | Setup level 4 of 5: Guided command-line setup | +580 | 1,544 |
| 36 | ↑36 | pstack-claude pstack-claude is a set of skill plugins that adds rigorous, verified agent workflows to coding agents like Claude Code and Codex for developers. | Skill or plugin | Setup level 4 of 5: Guided command-line setup | +1,166 | 3,746 |
| 37 | New | Cloudroom Cloudroom is a desktop app that runs AI coding agents on your Mac or in the cloud, so they keep working when your laptop is closed, for developers and vibe coders. | Agent app | Setup level 3 of 5: Install a desktop app or browser extension | +594 | 1,245 |
| 38 | New | Cloudroom Cloudroom is a desktop app that runs AI coding agents on your Mac or in the cloud, so they keep working after you close your laptop. | Agent app | Setup level 3 of 5: Install a desktop app or browser extension | +594 | 1,245 |
| 39 | New | seo-skills seo-skills is a set of SEO instruction files that teach Claude Code, Cursor, and Codex to run SEO tasks for website owners and marketers. | Skill or plugin | Setup level 4 of 5: Guided command-line setup | +478 | 698 |
| 40 | ↑15 | Orca Orca is a desktop app that runs and tracks several coding agents at once, each in its own worktree, for developers and vibe coders. | Agent app | Setup level 3 of 5: Install a desktop app or browser extension | +7,215 | 113k |
| 41 | New | Reason Network Reason Network is an agent app that lets your team's coding agents message each other across computers for developers working in separate sessions. | Agent app | Setup level 3 of 5: Install a desktop app or browser extension | +441 | 1,452 |
| 42 | New | Scientific Agent Skills Scientific Agent Skills is a collection of 177 skills that teaches an AI agent scientific tools and databases for research work. | Skill or plugin | Setup level 4 of 5: Guided command-line setup | +4,291 | 55.8k |
| 43 | New | ai-data-extractor Free open-source extractor for AI coding assistant chat histories. Supports Claude Code, Cursor, Windsurf, Aider, Cline/Roo Code and more | Not yet described | Not stated | +417 | 526 |
| 44 | New | mcd-budget-meal mcd-budget-meal is a skill that compares up to three official McDonald's China meal prices within a set budget for solo pickup orders. | Skill or plugin | Setup level 3 of 5: Install a desktop app or browser extension | +442 | 1,620 |
| 45 | ↑45 | workbuddy2api-hub workbuddy2api-hub is a self-hosted gateway that lets tools like Codex and Claude Code use WorkBuddy and CodeBuddy accounts through standard OpenAI-style connections. | Agent app | Setup level 4 of 5: Guided command-line setup | +788 | 3,394 |
| 46 | New | awwwards Awwwards is a skill that builds polished, award-style websites from a one-line brief for people who want a distinctive site without design work. | Skill or plugin | Setup level 4 of 5: Guided command-line setup | +402 | 1,055 |
| 47 | New | AI Cross Border Ecommerce Agent Toolkit A toolkit of seven reusable AI agent workflows with prompts and templates that help cross-border ecommerce sellers run listings, ads, and reviews for Shopee and Mercado Livre. | List or tutorial | Setup level 2 of 5: Adds to an AI app you already use | +396 | 898 |
| 48 | New | Grandet Grandet is a skill and MCP server that finds the lowest listed API price for an AI model and helps connect it for people who need cheap model access. | Skill or plugin | Setup level 3 of 5: Install a desktop app or browser extension | +396 | 1,045 |
| 49 | New | scout Scout: the open-source browser agent, by Outcrawl. Mirrored automatically from Outcrawl's own repository. | Not yet described | Not stated | +909 | 948 |
| 50 | New | AI Security Tool 🛡️ Free open-source AI-powered security terminal & vulnerability scanner (CVE, SBOM). Supports SSH, SFTP, RDP, VNC, Serial, and 12+ autonomous AI agents (DeepSeek, OpenAI) for automated security workflows, CTF & DevSecOps. Cross-platform & Web UI. | Not yet described | Not stated | +503 | 1,288 |
| 51 | New | UX/UI Agent Skills UX/UI Agent Skills is a skill that helps coding agents design interfaces to a professional standard and checks the result with 52 gates for developers. | Skill or plugin | Setup level 4 of 5: Guided command-line setup | +757 | 3,074 |
| 52 | New | cinetic cinetic is a skill that makes a coding agent direct cinematic launch films and motion design for product teams. | Skill or plugin | Setup level 4 of 5: Guided command-line setup | +411 | 961 |
| 53 | New | huashu-motion huashu-motion is a skill that lets a coding agent build product launch films from a one-line request, with a browser editor for point-and-comment edits, for people making promo videos. | Skill or plugin | Setup level 4 of 5: Guided command-line setup | +580 | 2,034 |
| 54 | New | dsh-blender-plugin dsh-blender-plugin is a skill that lets an AI agent model, check, and export 3D scenes in Blender for DSH users. | Skill or plugin | Setup level 4 of 5: Guided command-line setup | +414 | 1,546 |
| 55 | New | Stealth Browser MCP Stealth Browser MCP is an MCP server that lets AI apps control a real Chrome browser that avoids common bot checks, for developers and automation builders. | MCP server or connector | Setup level 4 of 5: Guided command-line setup | +779 | 3,315 |
| 56 | New | B B is a desktop companion app that watches your screen, listens, and speaks up with context-aware help while you work. | Agent app | Setup level 4 of 5: Guided command-line setup | +1,002 | 5,139 |
| 57 | ↓29 | yovoice yovoice is an agent app that turns text into speech, cloned voices, and songs on your own computer for creators who want to avoid per-character cloud fees. | Agent app | Setup level 3 of 5: Install a desktop app or browser extension | +710 | 2,025 |
| 58 | ↓19 | skills Skills is a set of small agent instruction files that help coding agents like Claude Code and Codex build real software without losing the developer's control. | Skill or plugin | Setup level 3 of 5: Install a desktop app or browser extension | +10,080 | 310k |
| 59 | New | muxin All your machines, one app. For you and your AI agents: agent sessions, desktops, files, logs and GitHub across your Macs, Linux and Windows machines, with an MCP server. | Not yet described | Not stated | +313 | 385 |
| 60 | New | coop-anything Coop-anything is a set of playbooks and an MCP server that let an AI coding agent add co-op play to single-player games for friends. | List or tutorial | Setup level 4 of 5: Guided command-line setup | +446 | 1,795 |
| 61 | New | Baize Baize is a command-line coding agent that redacts personal data before it reaches the model, for people who vibe code or analyze data. | Agent app | Setup level 4 of 5: Guided command-line setup | +366 | 594 |
| 62 | New | mcd-wrapped M-CODE WRAPPED · 麦当劳数据全景报告 + 个人年报 + 方言播报 | Not yet described | Not stated | +308 | 517 |
| 63 | New | Free Claude Code Free Claude Code is an agent app that lets you run Claude Code, Codex, and other coding agents on many free or low-cost models for developers and vibe coders. | Agent app | Setup level 4 of 5: Guided command-line setup | +3,638 | 65.8k |
| 64 | ↓2 | open-seo-mcp-skills Open-source SEO and GEO skills for Claude that analyze your own Search Console and GA4 data for marketers and site owners. | Skill or plugin | Setup level 2 of 5: Adds to an AI app you already use | +1,220 | 8,654 |
| 65 | New | youtube-skills YouTube transcript skills for Claude Code, Cursor and Codex. Agent Skills to get transcripts, search YouTube, read channels and playlists, and bulk export. | Not yet described | Not stated | +300 | 344 |
| 66 | New | Carrel Carrel is a self-hosted knowledge base that lets AI agents search your own documents and their related facts for accurate answers. | Agent app | Setup level 4 of 5: Guided command-line setup | +294 | 681 |
| 67 | ↑12 | SeeCode SeeCode is a skill that turns a short text spec into an animated, clickable diagram for people who build software with AI coding agents. | Skill or plugin | Setup level 2 of 5: Adds to an AI app you already use | +410 | 835 |
| 68 | ↓8 | logo-design-skill Logo-design-skill is a skill that guides Claude and other AI agents through logo design, from brief to SVG files, for people creating brand identities. | Skill or plugin | Setup level 2 of 5: Adds to an AI app you already use | +927 | 5,767 |
| 69 | New | Agent Manager Lite Agent Manager Lite is a macOS app that runs multiple separate Codex, Claude Code CLI, and Claude Desktop instances with their own accounts, keys, and sessions. | Agent app | Setup level 3 of 5: Install a desktop app or browser extension | +280 | 547 |
| 70 | New | Noria Noria is an agent app that finds jobs and scholarships from web pages and scores them against your profile, sending results to WhatsApp. | Agent app | Setup level 4 of 5: Guided command-line setup | +978 | 4,571 |
| 71 | New | vibe-knowledge-film vibe-knowledge-film is a skill that turns a script or topic into a short explainer video in the style of popular Douyin knowledge clips, for people who want to make such videos without a video editor. | Skill or plugin | Setup level 4 of 5: Guided command-line setup | +295 | 917 |
| 72 | New | taste-skill Taste Skill is a skill that makes coding agents design websites and app screens with real pictures and a browser check, instead of generic pages. | Skill or plugin | Setup level 4 of 5: Guided command-line setup | +4,281 | 108k |
| 73 | ↓47 | security-audit-skill security-audit-skill is a skill that makes a coding agent run multi-phase security audits of a codebase and write verified findings for developers reviewing their own code. | Skill or plugin | Setup level 4 of 5: Guided command-line setup | +2,872 | 56.8k |
| 74 | New | Rakazo Rakazo is a self-hosted AI assistant that runs persistent bots with memory and routines for people who want to pick their own model and computer. | Agent app | Setup level 4 of 5: Guided command-line setup | +886 | 6,635 |
| 75 | New | harness-mix | Not yet described | Not stated | +333 | 621 |
| 76 | New | claude-share claude-share is a plugin that lets a teammate join your live Claude Code session through a shared link for developers pair programming. | Skill or plugin | Setup level 4 of 5: Guided command-line setup | +267 | 804 |
| 77 | New | It's a Plan It's a Plan is a self-hosted project tracker where AI agents take issues alongside your team, for teams that want a Linear or Jira alternative. | Agent app | Setup level 3 of 5: Install a desktop app or browser extension | +448 | 2,134 |
| 78 | ↓19 | Ponytail Ponytail is a skill that makes an AI coding agent write less code and reuse what already exists, for developers using Claude Code or Codex. | Skill or plugin | Setup level 4 of 5: Guided command-line setup | +6,201 | 182k |
| 79 | ↓43 | text-to-cad text-to-cad is a plugin that lets an AI agent design physical products as 3D CAD models from text descriptions for makers and engineers. | Skill or plugin | Setup level 4 of 5: Guided command-line setup | +2,151 | 24.9k |
| 80 | ↓57 | winutil-cn 面向 Windows 11 的中文软件管理与系统维护工具,支持 Windows 10 / 11 x64 镜像制作与默认只读的 MCP 接口。基于 Chris Titus Tech Windows Utility。 | Not yet described | Not stated | +491 | 1,061 |
| 81 | New | Horizon Horizon is a self-run news radar that collects articles from many sources and writes daily briefings in English and Chinese for people who want to keep up without endless scrolling. | Agent app | Setup level 4 of 5: Guided command-line setup | +1,132 | 11.5k |
| 82 | New | neckbeard Agent plugin that scaffolds tested, cost-honest cloud infrastructure from a versioned module catalog | Not yet described | Not stated | +253 | 276 |
| 83 | New | Droidline Droidline is a tool that automates real Android phones from code, for testing apps and repeating phone tasks. | Framework or SDK | Setup level 4 of 5: Guided command-line setup | +255 | 442 |
| 84 | New | mcd-coupon-strategist Mcd-coupon-strategist is a skill that finds the cheapest McDonald's China order at the current store and warns about coupon traps, for people who order there often. | Skill or plugin | Setup level 4 of 5: Guided command-line setup | +334 | 991 |
| 85 | New | ARTEMIS ARTEMIS is an Android automation agent that runs phone tasks from plain instructions for testers and developers. | MCP server or connector | Setup level 4 of 5: Guided command-line setup | +1,271 | 16.2k |
| 86 | New | Gravitas Gravitas is a skill that makes Gemini read files before editing, keep changes in scope, and prove its work with test results for developers using AI coding agents. | Skill or plugin | Setup level 2 of 5: Adds to an AI app you already use | +248 | 415 |
| 87 | ↓37 | pstack pstack is a set of Agent Skills that makes AI coding agents write less, higher quality code for developers and engineering teams. | Skill or plugin | Setup level 4 of 5: Guided command-line setup | +648 | 3,378 |
| 88 | ↓78 | Talorys Talorys is a self-hosted personal AI assistant that chats, keeps memory, manages tasks and sends reminders for individuals, deployed to their own Cloudflare account. | Agent app | Setup level 4 of 5: Guided command-line setup | +548 | 1,432 |
| 89 | New | Squadra Squadra is a local coordination tool that keeps several Claude, Codex and Cursor coding windows on one shared task list with proof and independent review for developers. | Agent app | Setup level 4 of 5: Guided command-line setup | +243 | 1,182 |
| 90 | New | Codex Codex is a coding agent that runs in your terminal and writes or fixes code on your computer for developers. | Agent app | Setup level 4 of 5: Guided command-line setup | +1,197 | 133k |
| 91 | New | ThinkRail ThinkRail is an agentic IDE that runs the pi coding agent in isolated workspaces for developers who vibe code. | Agent app | Setup level 3 of 5: Install a desktop app or browser extension | +335 | 7,081 |
| 92 | New | Blender Agent Skills Blender Agent Skills is a set of instruction packs that teach AI coding agents to do 3D modeling, rigging, and export work in Blender. | Skill or plugin | Setup level 4 of 5: Guided command-line setup | +231 | 658 |
| 93 | New | TencentDB-Agent-Memory TencentDB-Agent-Memory is a self-hosted memory hub that lets a team's AI agents share saved chats, skills, docs, and code context for developers. | Agent app | Setup level 4 of 5: Guided command-line setup | +1,695 | 30.3k |
| 94 | New | esp32-thinks A multi-model Muse: personal AI voice assistant on ESP32 - wake word or knob, any OpenAI-compatible brain (STT/chat/TTS mix-and-match), streaming replies, out of the box. Built on muse-gadget-sdk. | Not yet described | Not stated | +223 | 260 |
| 95 | New | ECC ECC is a plugin and toolkit that adds planning, testing, review, and memory routines to coding agents like Claude Code for developers building software. | Skill or plugin | Setup level 4 of 5: Guided command-line setup | +6,416 | 295k |
| 96 | ↓78 | API Anything API Anything is an MCP server that turns websites without an API into callable operations for AI agents, so agents can skip the browser. | MCP server or connector | Setup level 4 of 5: Guided command-line setup | +478 | 2,034 |
| 97 | New | Hycli Websites, ready for AI. Turn website tasks into verified CLI and MCP actions, with a local dashboard and 20 languages. | Not yet described | Not stated | +219 | 444 |
| 98 | New | Paperclip Paperclip is an open-source app that manages a team of AI agents, tracking their tasks, budgets, and org chart for business owners and developers. | Agent app | Setup level 4 of 5: Guided command-line setup | +3,864 | 110k |
| 99 | New | Remory Remory is a code library that adds learned memory to an agent's compaction summary so long sessions keep going for developers. | Framework or SDK | Setup level 4 of 5: Guided command-line setup | +230 | 644 |
| 100 | New | Apify MCP server Apify MCP server is a connector that lets AI agents scrape websites and pull data from social media, maps, and online stores for businesses and researchers. | MCP server or connector | Setup level 2 of 5: Adds to an AI app you already use | +1,272 | 14.3k |
No entries match these filters this week. Try a wider setup level or another task.
Builder tools that week
| Rank | Change | Agent | Type | Setup | Stars this week | Stars |
|---|---|---|---|---|---|---|
| 1 | New | harness2 A Python framework that tunes the setup around an AI agent so it does better on unfamiliar professional tasks, for developers running benchmarks. | Framework or SDK | Setup level 4 of 5: Guided command-line setup | +8,090 | 22k |
| 2 | New | esp32-iphone-agent ESP32 iPhone Agent is a hardware and app setup that lets an AI model operate a real iPhone for hands-free phone tasks, using a small board instead of a computer. | Agent app | Setup level 5 of 5: Requires programming | +3,136 | 4,219 |
| 3 | ↑17 | RSI-Anything RSI-Anything is a research framework that lets AI agents predict outcomes, test actions, and improve over repeated rounds for developers and researchers. | Framework or SDK | Setup level 5 of 5: Requires programming | +716 | 1,101 |
| 4 | New | git-ai git-ai is a version control server built for coding agents that land many small changes at once. | Framework or SDK | Setup level 5 of 5: Requires programming | +560 | 1,044 |
| 5 | = | HyperFrames HyperFrames is a skill set that lets AI coding agents write HTML and render it into MP4 videos for creators and developers. | Skill or plugin | Setup level 4 of 5: Guided command-line setup | +5,859 | 77.4k |
| 6 | ↑3 | Tracely Tracely is a self-hostable tool that turns failed AI agent runs into regression tests that block bad pull requests for developers. | Framework or SDK | Setup level 5 of 5: Requires programming | +685 | 1,213 |
| 7 | ↓5 | Moli Moli is a headless browser that lets AI agents fetch pages, extract content, and automate browser tasks with low resource use. | Framework or SDK | Setup level 4 of 5: Guided command-line setup | +2,941 | 22.1k |
| 8 | ↑18 | Corsair Corsair is a TypeScript integration platform that lets developers connect their apps and their users' apps to agents and backend services through one syntax. | Framework or SDK | Setup level 5 of 5: Requires programming | +1,667 | 15.7k |
| 9 | ↓1 | Hypit Hypit is a skill that lets Claude Code or Codex clone viral videos and make variants of them for social media creators. | Skill or plugin | Setup level 4 of 5: Guided command-line setup | +2,373 | 27.5k |
| 10 | ↑24 | layerfs LayerFS is a filesystem layer that gives each AI agent its own writable workspace over shared history for developers running parallel agents. | Agent app | Setup level 4 of 5: Guided command-line setup | +380 | 2,628 |
| 11 | ↑13 | AutoSwarm-Shadow-Adapter AutoSwarm-Shadow-Adapter is a human review add-on that lets AI agent workflows pause for a person's sign-off without stalling. | Other | Setup level 5 of 5: Requires programming | +980 | 5,130 |
| 12 | ↑31 | CLI-Anything CLI-Anything is a toolkit that builds command-line interfaces so AI agents can control existing software for developers and power users. | Other | Setup level 4 of 5: Guided command-line setup | +2,883 | 58.1k |
| 13 | ↓9 | monid Monid is a connector layer that gives AI agents one key to over 2,000 tools from 72 providers for web search, enrichment, and media generation. | Framework or SDK | Setup level 5 of 5: Requires programming | +1,045 | 6,138 |
| 14 | ↓1 | AntOmniEvo AntOmniEvo is a framework that automatically improves AI agent systems by having AI coding agents rewrite their tunable files based on failure results. | Framework or SDK | Setup level 5 of 5: Requires programming | +425 | 1,222 |
| 15 | ↓5 | Hindsight Hindsight is an agent memory system that helps AI agents learn over time instead of only recalling chat history, for developers building agents. | Framework or SDK | Setup level 4 of 5: Guided command-line setup | +2,899 | 57.9k |
| 16 | ↓4 | dsh dsh is an open-source agent platform built on plugins, for developers who want to build and run their own AI agents. | Framework or SDK | Setup level 4 of 5: Guided command-line setup | +6,089 | 269k |
| 17 | ↓3 | WeKnora WeKnora is a self-hosted knowledge platform that turns a team's documents into searchable answers, an autonomous agent, and a wiki for businesses. | Framework or SDK | Setup level 4 of 5: Guided command-line setup | +1,358 | 36.2k |
| 18 | ↓17 | Shaders Shaders is a library of WebGPU visual effect components for web developers building animated backgrounds and cursor effects for websites. | Framework or SDK | Setup level 5 of 5: Requires programming | +606 | 5,779 |
| 19 | ↓13 | Open Intelligent UI Open Intelligent UI is a code library that builds chat answers as interactive maps, charts, and tools for developers adding AI features to their apps. | Framework or SDK | Setup level 5 of 5: Requires programming | +223 | 907 |
| 20 | ↑1 | Scrapling Scrapling is a Python web scraping framework that collects data from websites, including JavaScript-heavy and bot-protected ones, for developers. | Framework or SDK | Setup level 5 of 5: Requires programming | +1,714 | 92k |
| 21 | ↑20 | xiaozhi-esp32 xiaozhi-esp32 is a firmware for a voice chatbot device that controls smart gadgets through MCP for hobbyists building AI hardware. | Agent app | Setup level 5 of 5: Requires programming | +833 | 32.5k |
| 22 | ↓7 | pi Pi is a minimal, extensible coding agent CLI that runs in your terminal for developers who want to customize their own agent setup. | Agent app | Setup level 4 of 5: Guided command-line setup | +1,943 | 119k |
| 23 | ↓6 | Firecrawl Firecrawl is an API that searches the web and pulls clean page content for AI agents and apps. | Framework or SDK | Setup level 5 of 5: Requires programming | +2,441 | 198k |
| 24 | ↑1 | TradingAgents TradingAgents is a multi-agent framework that simulates a trading firm of LLM analysts, researchers, and managers to evaluate stock trades for researchers and developers. | Framework or SDK | Setup level 5 of 5: Requires programming | +1,357 | 120k |
| 25 | ↓6 | Jev Ultrafast Jev Ultrafast is a Python browser agent that completes web tasks from one plain-language goal for developers and technical users who want fast, low-cost automation. | Agent app | Setup level 4 of 5: Guided command-line setup | +624 | 24.1k |
| 26 | ↓3 | CLIProxyAPI CLIProxyAPI is a proxy server that lets apps use AI coding accounts from Claude Code, Codex, and other tools through one standard API for developers. | Agent app | Setup level 4 of 5: Guided command-line setup | +826 | 57.3k |
| 27 | ↑6 | AgentScope AgentScope is a framework that helps developers build and run AI agents they can monitor and trust. | Framework or SDK | Setup level 5 of 5: Requires programming | +394 | 35.2k |
| 28 | ↓6 | OpenViking OpenViking is a context database that gives AI agents organized memory, documents, and skills they can browse like files. | Framework or SDK | Setup level 4 of 5: Guided command-line setup | +637 | 41.4k |
| 29 | ↓18 | fframes fframes is a skill that lets a coding agent write, check and render motion-graphics videos in Rust and SVG for people who want a programmatic video tool. | Skill or plugin | Setup level 4 of 5: Guided command-line setup | +211 | 3,118 |
| 30 | ↓23 | shrt shrt is a regression test tool that replays saved API call chains against a backend after each release for developers and vibe coders, and names the step and field that changed. | Skill or plugin | Setup level 4 of 5: Guided command-line setup | +124 | 1,986 |
| 31 | ↑8 | Graphiti Graphiti is a Python framework that builds memory graphs for AI agents, tracking how facts change over time for developers. | Framework or SDK | Setup level 5 of 5: Requires programming | +365 | 32.4k |
| 32 | ↓29 | Cayu Cayu is a Python framework that runs long-running AI agents durably, with restart recovery, approvals and spend caps, for developers building domain-specific agents. | Framework or SDK | Setup level 5 of 5: Requires programming | +112 | 962 |
| 33 | ↓4 | browser-use Browser Use is an open-source Python library and cloud service that lets AI agents control a web browser to finish tasks for you. | Framework or SDK | Setup level 5 of 5: Requires programming | +869 | 120k |
| 34 | ↑10 | SkillOpt SkillOpt is a training tool that improves reusable instruction files for AI agents without changing model weights, for developers and researchers. | Framework or SDK | Setup level 5 of 5: Requires programming | +325 | 18.8k |
| 35 | ↓8 | cangjie-skill Cangjie Skill is a skill generator that turns books, long videos, and podcasts into reusable AI skills for applying their methods. | Skill or plugin | Setup level 4 of 5: Guided command-line setup | +276 | 12k |
| 36 | ↓20 | Cognee Cognee is an open-source memory platform that gives AI agents persistent long-term memory across sessions for developers and teams. | Framework or SDK | Setup level 5 of 5: Requires programming | +485 | 33k |
| 37 | ↓7 | VoiceMem VoiceMem is a memory library that gives voice agents long-term recall of facts and emotions about the user. | Framework or SDK | Setup level 5 of 5: Requires programming | +129 | 2,825 |
| 38 | ↓10 | gsd-core GSD Core is a set of instructions that adds a phased planning and verification workflow to AI coding agents for developers building software projects. | Skill or plugin | Setup level 2 of 5: Adds to an AI app you already use | +245 | 11.1k |
| 39 | ↓21 | Tiny Engineer Tiny Engineer is a desk robot that shows what your AI coding agent is doing by moving, changing its face, and ringing a bell. | Other | Setup level 5 of 5: Requires programming | +80 | 1,026 |
| 40 | ↓9 | crawl4ai Crawl4AI is an open-source web crawler that turns any website into clean Markdown for AI agents and data pipelines. | Framework or SDK | Setup level 5 of 5: Requires programming | +538 | 86.8k |
| 41 | ↓5 | LangGraph LangGraph is a framework that helps developers build long-running agents that keep their state and resume after failures. | Framework or SDK | Setup level 5 of 5: Requires programming | +412 | 44.3k |
| 42 | ↑4 | TrueForge TrueForge is a runtime that runs the execution loop for AI agents, with a chat UI and API, for developers and teams who want agents running reliably. | Framework or SDK | Setup level 4 of 5: Guided command-line setup | +146 | 6,417 |
| 43 | ↓3 | EnterpriseAgentFramework ReachAI is an enterprise agent platform that lets AI query data, fill forms, and run tasks inside existing business systems like OA, ERP, and CRM. | Framework or SDK | Setup level 5 of 5: Requires programming | +65 | 1,018 |
| 44 | New | ag-ui AG-UI is an open protocol that connects AI agents to user-facing apps and interfaces for developers building agent-powered software. | Framework or SDK | Setup level 5 of 5: Requires programming | +217 | 17k |
| 45 | ↓13 | RPent RPent is an open framework for building physical robot agents that learn from interaction with the real world for robotics developers and researchers. | Framework or SDK | Setup level 5 of 5: Requires programming | +80 | 1,681 |
| 46 | ↓1 | FrontierAgent FrontierAgent is an agent app that runs research and file-based work in a terminal, with one agent or a team of parallel sub-agents, for people comfortable with the command line. | Agent app | Setup level 4 of 5: Guided command-line setup | +128 | 5,438 |
| 47 | New | camofox-browser camofox-browser is a stealth browser server that lets AI agents load and use websites that block automated browsers. | Framework or SDK | Setup level 4 of 5: Guided command-line setup | +172 | 12.1k |
| 48 | ↓11 | Mem0 Mem0 is a memory layer that lets AI agents and apps remember user details and past context across sessions for developers building assistants. | Framework or SDK | Setup level 5 of 5: Requires programming | +434 | 68.3k |
| 49 | New | Reef Reef is an open-source infrastructure for agents that keep improving from user feedback, for developers and researchers running model training or agent refinement. | Framework or SDK | Setup level 5 of 5: Requires programming | +131 | 7,788 |
| 50 | New | Midscene Midscene is a testing framework that lets developers write end-to-end tests for web, mobile, and desktop apps in plain language. | Framework or SDK | Setup level 5 of 5: Requires programming | +176 | 15.5k |
No entries match these filters this week. Try a wider setup level or another task.