Library
85,861 resources from 11 public sources. 47 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
-
TeamAgentMemory
MCP serversSelf-hosted memory service for AI agents that work in teams, written in Rust: layered L0→L3 memory, async LLM distillation, hybrid BM25 + vector recall, and department/team/member isolation. SQLite or Postgres, any OpenAI-compatible LLM.
git clone https://github.com/hsuanshao/TeamAgentMemory.git -
SwiftAutoGUI
SkillsA Swift library for macOS automation — mouse, keyboard, screenshots, image recognition, and AI-powered agents.
git clone https://github.com/NakaokaRei/SwiftAutoGUI.git -
deepdive
SkillsDeepdive skill for Claude Code — 12-phase research pipeline: plan-review gate, parallel sub-agent search, claims-ledger triangulation with dissent protection, relevance × authority evidence filter, multi-angle red team, four-layer citation verification. 105 blocks, 29 channels, 460+ stat sources, 47 APIs, 1072 verified endpoints.
git clone https://github.com/Socialpranker/deepdive.git -
dynobox
SkillsCross-harness testing framework for agent skills and workflows
git clone https://github.com/dynobox/dynobox.git -
android-mainline-port
Skills把主线 Linux 移植到安卓手机、平板的 Agent Skill:流程、决策规则与踩坑经验 · Agent skill for porting mainline Linux to Android phones and tablets
git clone https://github.com/yzddmr6/android-mainline-port.git -
spotter
Skills先问清,再动手,改完有证据 | Clarify first. Prove after. Remember everything. Risk-aware workflows for Codex / Claude Code / Antigravity
git clone https://github.com/hopkinson/spotter.git -
claude-code-config
SkillsMy Claude Code config, versioned in place at ~/.claude: skills for code review, issue triage, and releases, plus subagents, hooks, rules, settings, and a statusline. A reference to borrow from, not a starter template.
git clone https://github.com/philoserf/claude-code-config.git -
Unified enterprise & software architecture Claude Code skill: C4+Structurizr, ArchiMate, TOGAF ADM, arc42+ADR. Diagram, document, review, and model the enterprise.
git clone https://github.com/gauravs19/enterprise-architecture-skill.git -
GABBE
SkillsGenerative Architectural Brain Base Engine - Agentic Software R&D Engineering Kit - development, all languages, agents, platforms, with Engineering Team & Experimental Cognitive Brain, Software Engineering & Architecture Best Practices and Governance
git clone https://github.com/andreibesleaga/GABBE.git -
Carbon-Monitor
SkillsAgentic PR reviews for the IBM Carbon Design System, run by IBM Bob or Claude from a codified review prompt and grounded by Carbon MCP. Built on a reusable agent harness for IBM Cloud Code Engine: scheduled, parallel runs, a per-run spend cap, a web console, Elasticsearch telemetry and a Slack digest. A skill adapts it to your repo, job or agent.
git clone https://github.com/carbon-design-system/Carbon-Monitor.git -
superior-skills
PromptsBuild smarter. Work superior. An opinionated rule set for AI coding agents to create original interfaces, compelling content, and production-ready code.
git clone https://github.com/KodekaTeam/superior-skills.git -
claude-code-docs
SkillsAlways-current official Claude docs inside Claude Code. A 3 MB metadata plugin: live on-demand fetching from Anthropic's servers, zero content redistributed. Auto-discovery skill, instant search, interactive HTML courses, and doc changelog reports.
git clone https://github.com/costiash/claude-code-docs.git -
builder-skills
SkillsWorkflow, security, and writing skills for builders shipping Convex apps. npx builder-skills
git clone https://github.com/waynesutton/builder-skills.git -
ai
SkillsAI-native architecture kit for modern React — disciplined agent rules in one command.
git clone https://github.com/virastack/ai.git -
Tentra — Memory for AI Coding Agents
MCP serversMemory for AI coding agents. Call graphs + refactor safety + persistent code context. 35 MCP tools.
tentra-mcp@1.3.2 -
archlang
MCP servers【Every star you give feeds a hungry developer's motivation! ⭐️】Floor plans as code. Your AI writes ArchLang; the compiler draws a precise, dimensioned plan (SVG, DXF, PDF) and tells it what's wrong. Open source, MIT.
git clone https://github.com/ChanMeng666/archlang.git -
wiredkits-free
SkillsFree Claude Code skills and agents: CLAUDE.md writer, commit messages, release notes, code explainer, and smart model/effort picking for subagents. MIT.
git clone https://github.com/electronx/wiredkits-free.git -
agentsilex
Agents & frameworksA transparent, minimal, and hackable agent framework. ~300 lines of readable code. Full control, no magic.
git clone https://github.com/howl-anderson/agentsilex.git -
ai-powershell-standards
SkillsEnterprise-grade PowerShell development standards, shipped as GitHub Copilot instructions and Claude Code rules, for consistent, secure, and high-quality PowerShell code across teams and projects.
git clone https://github.com/fadwen/ai-powershell-standards.git -
seo-skill-bench
Datasets & benchmarksOpen benchmark for Claude Code SEO skills — real headless execution against fixture sites with planted-defect answer keys. Deterministic scoring, pre-registered rubric.
git clone https://github.com/aleclindz/seo-skill-bench.git -
Compartment
MCP serversEncrypted, fully offline agentic memory. One click install, GUI w/ memory map, all OS and agents. Superior memory creation, storage and retrieval.
git clone https://github.com/MaxFreedomPollard/Compartment.git -
oya-browser
MCP serversHIPAA-compliant browser for AI agents: an AI browser on desktop, agentic browsers in the cloud, every action audited.
git clone https://github.com/OyadotAI/oya-browser.git -
hyperclaude
SkillsClaude Code plugin: Claude builds, Codex critiques — a gated research → plan → review → ship pipeline, with autonomous multi-agent revise loops that self-converge.
git clone https://github.com/zeikar/hyperclaude.git -
brandmd
Tools & appsStop Claude Code/Cursor from guessing UI. Extract any website's design system into a spec-valid DESIGN.md that passes the official @google/design.md linter.
git clone https://github.com/yuvrajangadsingh/brandmd.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.