Library
86,235 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
Looks like a goal we have a starting path for: I want to build an AI agent
-
SAME - Stateless Agent Memory Engine
MCP serversPersistent memory for AI coding agents. Local-first SQLite + vector search. 17 MCP tools.
@sgx-labs/same@0.12.1 -
agent-toolkit
MCP serversPay-per-call developer utilities and npm supply-chain security tools for coding agents, over x402.
agent-toolkit-mcp@0.4.0 -
Agent Billboard
MCP serversRead and post to The Agent Billboard on Solana, with spend limits in code and a reasoning log.
agent-billboard-mcp@0.5.0 -
Agent Verify
MCP serversSecurity checks for AI agents and MCP configs: 124 tested checks, from your AI coding assistant.
agentverify@2.0.0 -
storyboard-scavenger
SkillsAI 视频分镜与提示词 Skill(AI video storyboard / video prompts):把创意、参考图或音乐想法拆为七要素分镜,提供可灵 Kling、即梦 Seedance、Veo、Sora 工作流。
git clone https://github.com/ouxxyy/storyboard-scavenger.git -
fantastic-ui
SkillsAgent skill for Claude: build instrument-grade UI — landing pages that read like the product, plus app pages, dashboards, panels, and subpanels held to the same discipline. Single-accent color system, serif+mono type, live data as proof, a11y/perf ship gates.
git clone https://github.com/succtorlin/fantastic-ui.git -
Athenode
MCP serversSpec-driven development for AI coding agents: specs, skills, agents, rules and MCP servers.
@athenode/cli@0.10.7 -
Cursor Delegate
MCP serversBridge AI coding hosts to cursor-agent over the Agent Client Protocol.
cursor-delegate-mcp@2.8.0 -
verirun
MCP serversExecution-grounded verification for AI coding agents on Windows: evidence, not agent claims.
verirun@0.2.1-dev -
dead-letter
SkillsConvert .eml and .mbox email, including Gmail Takeout, to Markdown with YAML front matter
git clone https://github.com/BigCactusLabs/dead-letter.git -
hyperframes-motion
SkillsAfter Effects-style motion graphics in plain HTML + GSAP: 3D camera moves, kinetic typography and ready-to-edit 1080x1920 video templates
git clone https://github.com/2boysfromtown/hyperframes-motion.git -
CONTINUUM
MCP serversCONTINUUM: Verifiable semantic recovery for long-running AI agents. Semantic checkpoints (not conversation dumps), an idempotent action ledger that refuses duplicate side effects, and a hash-chained tamper-evident event log, all exposed as a deny-by-default MCP server. Framework-agnostic, Python 3.11+
git clone https://github.com/Cyrax321/CONTINUUM.git -
wavespeed-cli
SkillsWaveSpeed CLI — run any image, video, audio or 3D model from your terminal or coding agent: live catalog search, per-model schema introspection, local-file upload, price quotes
git clone https://github.com/WaveSpeedAI/wavespeed-cli.git -
ui-ticket-mcp
MCP serversHuman-to-AI code review bridge. Review UI in the browser, AI agents fix code via MCP.
ui-ticket-mcp@1.6.2 -
ai-image-generator-skill
SkillsAI image generator agent skill for Claude Code, Cursor, Codex, Windsurf, Cline & OpenClaw: generate, compose, and edit product images, brand visuals, posters, social graphics, illustrations, and photo variations. AI图片生成 · 文生图 · AI修图
git clone https://github.com/beatra-ai/ai-image-generator-skill.git -
VMware-Monitor
SkillsMCP server and CLI for read-only VMware vCenter/ESXi health triage, inventory, alarms and evidence-based VM, host and datastore investigation.
git clone https://github.com/vmware-skills/VMware-Monitor.git -
claude-systems-prompts
PromptsAll official Claude system prompts in one open-source repo from Claude Fable 5.2 to Claude Haiku 3 23 models from Anthropic's release notes, plus original analysis, tool schemas, and AI-safety research.
git clone https://github.com/KalarisLabs/claude-systems-prompts.git -
<!-- LLM System Prompt Start --> # LLM Skill: Go Industrial Autonomous Business Module Coding Spec (shanjunmei/dig Compile-Time DI) Type: System Prompt / Agent Skill Model Compatible: Doubao / GPT / Claude / Qwen…
-
AgentSearch (agentsearchhq.com)
MCP serversFree web search + extract/render trial (no key), then pay per call via x402 on Base.
@agentsearchhq/agentsearch-mcp@1.8.4 -
sci-paper
SkillsClaude Code plugin for scientific paper writing, source-traced review, and de-AI rewriting. 12 skills + 35 tools under one typed standard: non-waivable integrity blockers, zero-target L0 lexicon, ranked advisories, and explicit measurement states so missing calibration never reads as clean. Corpus-calibrated for ApJ/MNRAS/PRD/JCAP manuscripts.
git clone https://github.com/skymanbp/sci-paper.git -
elecxzy
MCP serversA Lisp-free, Emacs-keybinding text editor for Windows built with Electron + React + TypeScript, with a built-in MCP server that lets AI agents (Claude Desktop, etc.) drive the editor. Batteries-included defaults, JSON-only config.
git clone https://github.com/kurouna/elecxzy.git -
little-canary
SkillsDetects prompt injection by its effect on a sacrificial canary model, not just pattern matching: untrusted input hits a powerless model first, a behavioral check reads the residue, and it returns block, flag, or pass before your primary model acts. Inbound preflight sensor, not a guarantee.
git clone https://github.com/hermes-labs-ai/little-canary.git -
plombir-git
MCP serversLightweight, open-source, self-hosted Git server and forge written in Rust. Gitea/Forgejo/GitHub alternative with pull requests, CI/CD and built-in MCP for AI agents.
git clone https://github.com/Nettechnologys/plombir-git.git -
arcgram
SkillsArcgram — an interactive diagram engine for human–AI collaboration: an AI agent draws its reasoning as an auditable node-and-edge flow and self-audits it, delivered as one standalone HTML file. (Arcgram the AI diagram tool — not Archigram.)
git clone https://github.com/jovesun-lab/arcgram.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.