Library
85,766 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
-
watch-n-learn
SkillsTurn a how-to video into a reusable skill for your AI coding agent — watched locally, no API keys.
git clone https://github.com/axel-pm/watch-n-learn.git -
msg
SkillsEnd-to-end engineering harness for Claude Code — go from planning to building to reviewing in one workflow. 8 agents with multiple modes. In-built GUI to visualise your PRDs and todos. Ship with AI confidently. MIT.
git clone https://github.com/ndisisnd/msg.git -
qwen38-strix-halo-harness
Datasets & benchmarksAI coding agent harness for any hardware, local or cloud (OpenAI-compatible engines). Tuned for AMD Strix Halo: Qwen3.8 125B on the iGPU, NPU side-jobs, crash recovery, logged benchmarks.
git clone https://github.com/aic0d3r/qwen38-strix-halo-harness.git -
skills
SkillsClaude Code plugin marketplace — 77 installable reference skills across vLLM/SGLang inference, Kubernetes & Harvester, GPU host bring-up, observability, security, and agent workflows.
git clone https://github.com/air-gapped/skills.git -
C2C
Agents & frameworks[ICLR'26] The official code implementation for "Cache-to-Cache: Direct Semantic Communication Between Large Language Models"
git clone https://github.com/thu-nics/C2C.git -
repo-forensics
SkillsOffline security scanner for AI-agent repos, skills, plugins, and MCP servers.
git clone https://github.com/alexgreensh/repo-forensics.git -
ante
Agents & frameworksGhost in your shell. Ante is a self-contained agent harness with a highly optimized core. It works like Claude Code or Codex, with none of their dependencies or model constraints.
git clone https://github.com/AntigmaLabs/ante.git -
builder
Agents & frameworks📦✨ AI Builder For Creating Sites and Apps! An open-source alternative to Lovable, Replit, v0, and similar platforms.
git clone https://github.com/HeyPuter/builder.git -
dispatchseo
MCP serversFree SEO autopilot: researched articles published to your site. Hosted at dispatchseo.com (2 free articles per month), or self-host this repo and drive it with Claude Code, Codex or Cursor over MCP. Open source (AGPL).
git clone https://github.com/NeoZi12/dispatchseo.git -
Procedura
Agents & frameworksAgentic 3D Modeling with Procedural Control — turns a text prompt into an editable parametric program, with optional per-part materials and articulation.
git clone https://github.com/SpatiaOS/Procedura.git -
postext
SkillsA programmable typesetter for the web
git clone https://github.com/drnachio/postext.git -
agent-plugins-skills
SkillsAgentic OS Control Plane: deterministic state-machine governance for AI coding agents with cryptographically enforced SSH/CIBA human-in-the-loop gates and zero-trust verification.
git clone https://github.com/richfrem/agent-plugins-skills.git -
forge-skills
SkillsThe Forge Skills Plugin bundles several Forge-focused skills plus MCP-backed tooling so your agent can scaffold apps, review them before deploy, debug production issues, and stay current on Forge APIs and the Atlassian Design System.
git clone https://github.com/atlassian/forge-skills.git -
mlx-serve
AI repositoriesNative LLM inference server for Apple Silicon. OpenAI + Anthropic API compatible. No Python. Zig backend, Swift frontend macOS app with chat, music, voice, video generation.
git clone https://github.com/ddalcu/mlx-serve.git -
hewn-forge
PromptsHEWN 2.0 2026: AI Output Router for Precision Summaries & Polished Code
git clone https://github.com/kaderkck/hewn-forge.git -
Vibe_Assistant
MCP serversCross-platform desktop workspace for AI agent memory, Skills and MCP. 跨平台桌面应用:统一管理 AI 智能体的记忆、Skill 与 MCP。
git clone https://github.com/Zafer-Liu/Vibe_Assistant.git -
researchforge
SkillsA lab protocol for coding agents. Freeze baselines, run hypotheses in isolated worktrees, reject failures and validate improvements from Claude Code, Cursor or a direct API key (Gemini/Anthropic/openAI).
git clone https://github.com/forger-labs-hq/researchforge.git -
bsl-ai-toolkit
MCP serversAI agent toolkit for 1C:Enterprise 8.3 (BSL): rules, skills and MCP servers so the agent works from your real code, plus byte-perfect metadata editing verified in a test base. Docs in Russian.
git clone https://github.com/vgtitov/bsl-ai-toolkit.git -
MeowKit
SkillsProduction ready. AI Agent Workflow System for Claude Code
git clone https://github.com/ngocsangyem/MeowKit.git -
qa-skills
SkillsTesting skills for AI coding agents: evidence-backed strategy, executable cases, Playwright/API testing, regression and QA memory. 面向 AI Agent 的测试工程技能。
git clone https://github.com/fishzjp/qa-skills.git -
review-squad
SkillsDispatch panels of specialized subagents to review projects — expert audits, first-impression personas, task-completion flows, and pedantic nitpicks
git clone https://github.com/2389-research/review-squad.git -
opencues
Tools & appsThe open standard for omnipresent AI. Claude Code, OpenCode, Gemini CLI, Shell, Chrome, DeepSeek Harness. Model-agnostic
git clone https://github.com/opencues/opencues.git -
cat
Agents & frameworksAn agentic workflow with a focus on reliability and developer experience
git clone https://github.com/holdmyspot-com/cat.git -
contexere
Agents & frameworksThe one place for the skills, keys and memory of every agent you use. Formerly OMNI.
git clone https://github.com/fajarhide/contexere.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.