Library
87,608 resources from 11 public sources. 54 checked by hand. The rest are indexed automatically and not reviewed.
Results
-
Varin
SkillsThe open-source agent harness, ready out of the box and customizable in depth. Tools, context, durable execution, permissions and recovery for code, research and office work, with a long-running super-agent Bot that leads a team of agents.
Source for Varin (opens github.com) git clone https://github.com/Astrmira/Varin.git -
paper-reading-skill
SkillsAgent skill for visual, source-grounded paper reading: one standalone HTML atlas of methods, equations, and experiments.
Source for paper-reading-skill (opens github.com) git clone https://github.com/xiaofengShi/paper-reading-skill.git -
ontology-atlas
MCP serversUnderstand what your codebase builds, why it is structured that way, and what a change could affect. One shared Markdown ontology for humans and coding agents—visualized for people, accessible to agents through MCP, and reviewed with Git. Local-first. Open source.
Source for ontology-atlas (opens github.com) git clone https://github.com/wlsdks/ontology-atlas.git -
YouTube-AI-Motion-Graphics
SkillsAI motion graphics for YouTube explainer videos: 74 animated HTML explainer boards (charts, diagrams, Venn, timeline, heatmap) synced to your voice with Whisper, exported frame by frame with Chrome + FFmpeg. Every prompt + Claude skills. By TEIN AI.
Source for YouTube-AI-Motion-Graphics (opens github.com) git clone https://github.com/sirioberati/YouTube-AI-Motion-Graphics.git -
Agents-Prompts
Prompts# Agents-PromptsEste repositório contém os prompts usados nas principais ferramentas de IA do mundo, incluindo FULL v0, Cursor, Manus, Lovable e mais. Estude mais de 7000 linhas de prompts para entender como criar seus próprios agentes. 🛠️🤖Se você deseja aprender a criar seus próprios agentes, confira nosso curso gratuito que ensina a combinar
Source for Agents-Prompts (opens github.com) git clone https://github.com/BigBoySlave/Agents-Prompts.git -
mcp-server
MCP serversThe context platform for AI agents. Code search, team decisions, and shared project context with traceable sources and scoped access, carried across sessions and tools.
Source for mcp-server (opens github.com) git clone https://github.com/contextstream/mcp-server.git -
agent-duel
Datasets & benchmarksBlinded battles between coding agents: two agents, one prompt, you pick the winner. Desktop app, runs locally.
Source for agent-duel (opens github.com) git clone https://github.com/bottomless/agent-duel.git -
awesome-claude-seo-skills
SkillsOpen-source Claude SEO skills, SEO MCP servers and GEO tools for coding agents. Each read and security-graded. EN + 中文.
Source for awesome-claude-seo-skills (opens github.com) git clone https://github.com/zhuyansen/awesome-claude-seo-skills.git -
ar-plugins
SkillsMarketplace de 15 plugins para Claude Code y Codex sobre Argentina: dólar e inflación en vivo, trámites, sueldos, derechos, salud y facturación del monotributo.
Source for ar-plugins (opens github.com) git clone https://github.com/kvothesson/ar-plugins.git -
Argus
Agents & frameworksOpen-source red-team testing for AI agents. 295 bundled probes with OWASP LLM Top 10, MITRE ATLAS, and NIST AI RMF mappings. Selected probes use recorded browser requests, MCP tool calls, or mock payments. CLI, SARIF, GitHub Action.
Source for Argus (opens github.com) git clone https://github.com/gy15901580825/Argus.git -
covel
Agents & frameworksOpen-source agentic AI role-playing framework for interactive stories, worlds and plugins. Supports multiple AI providers. Early access; public trial: https://demo.covel.cc/ (bring your own API key).
Source for covel (opens github.com) git clone https://github.com/ackness/covel.git -
TwinFix
Datasets & benchmarksTwinFix — AI agent that diagnoses, reproduces and fixes bugs in a disposable twin environment. 在一次性孪生环境中自动诊断、复现并修复故障的 AI Agent。
Source for TwinFix (opens github.com) git clone https://github.com/spacesky-cell/TwinFix.git -
NORMOT — Israeli building norms
MCP serversIsraeli building and planning norms: permits, fire, accessibility; Hebrew text, source, citation.
-
silvertongue
MCP serversWrite like anyone famous. 65+ famous voices and styles for your agent over MCP, and a funny AI code review GitHub Action: your PRs reviewed by Gordon Ramsay. Every source linked.
Source for silvertongue (opens github.com) git clone https://github.com/auscaster/silvertongue.git -
Traccar
Public APIsOpen Source GPS Tracking Platform
-
GNews
Public APIsSearch for news from various sources
-
arcsecond.io
Public APIsMultiple astronomy data sources
-
OpenLigaDB
Public APIsCrowd sourced sports league results
-
mac-ml-speed-test
Datasets & benchmarksA few quick scripts focused on testing TensorFlow/PyTorch/Llama 2 on macOS.
Source for mac-ml-speed-test (opens github.com) git clone https://github.com/mrdbourke/mac-ml-speed-test.git -
github-bounty-scanner
Skills🛡️ Autonomous GitHub Bounty Scanner & On-Chain Escrow Verifier — Find Real Crypto/USDC/wDOOM Bounties & Filter Fake Scraper Traps
Source for github-bounty-scanner (opens github.com) git clone https://github.com/doomsday-network/github-bounty-scanner.git -
pie-ai-agent
Agents & frameworksPie – free, open-source AI browser agent for Chrome. Reads pages & PDFs, fills forms, extracts data, automates tabs, hands off to Claude Code. BYOK or subscribe.
Source for pie-ai-agent (opens github.com) git clone https://github.com/wiseria-ai-labs/pie-ai-agent.git -
novel-engine
Agents & frameworksNovel Engine is a desktop app that lets you construct novels. Seven AI agents handle the editorial pipeline — from pitch to published manuscript — while you focus on the story. Powered by Claude, Codex, and Ollama. Open source. Free. No gatekeeping.
Source for novel-engine (opens github.com) git clone https://github.com/john-paul-ruf/novel-engine.git -
brand-skills
SkillsOpen-source brand skills that turn an idea into a real brand — name, identity, voice & brand book — without leaving your AI agent. Works in Claude Code, Cursor & 70+ agents.
Source for brand-skills (opens github.com) git clone https://github.com/cofoundy/brand-skills.git -
debate
Datasets & benchmarksAdversarial multi-turn benchmark for LLM debate quality, using side-swapped matchups and multi-model judging to rank models by judged debate performance.
Source for debate (opens github.com) git clone https://github.com/lechmazur/debate.git
Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.