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
-
Skills
SkillsA opinionated collection of agent skills organized by domain: dev, writing, productivity, and knowledge management
git clone https://github.com/kriscard/Skills.git -
Microverse
Agents & frameworksA god-simulation sandbox game built on Godot 4 as a multi-agent AI social simulation system. In this virtual world, AI characters possess independent thinking and memory, capable of autonomous social interactions, task completion, and developing complex social relationships through continuous communication.
git clone https://github.com/KsanaDock/Microverse.git -
swarmclaw
MCP serversOpen-source self-hosted AI agent runtime and multi-agent framework for autonomous agent swarms. Agent memory, MCP tools, schedules, delegation, and 23+ LLM providers (Claude, GPT, Gemini, OpenRouter, Ollama). A practical Claude Code and LangChain alternative.
git clone https://github.com/swarmclawai/swarmclaw.git -
claude-code-pro-course
SkillsClaude Code PRO — полный курс и гайд на русском: CLAUDE.md, settings, skills, subagents, hooks, MCP, плагины, CI. 8 лабораторных, библиотека промптов и готовый starter-kit. Здесь бесплатные курсы по chatgpt -
git clone https://github.com/justxor/claude-code-pro-course.git -
vibe-coder-kit
Skillsgit clone https://github.com/omergocmen/vibe-coder-kit.git -
Cohort
Agents & frameworksLocal-first Agent Runtime connecting LLMs to controlled tools, Chrome, desktop automation, MCP, context governance, and verifiable memory.
git clone https://github.com/congchuanling-dot/Cohort.git -
agent-qa
MCP serversOpen-source self-improving QA agent for software teams. A test harness with memory. Write tests in natural language for web and mobile. agent-qa learns from every run, adapts to UI changes, and catches regressions before you ship.
git clone https://github.com/vostride/agent-qa.git -
assay
Agents & frameworksAn agent-native QA CLI for web pages. Deterministic, no tests to write, no LLM.
git clone https://github.com/awss1i/assay.git -
mulmoterminal
Agents & frameworksRun multiple Claude Code and Codex sessions in parallel — a browser terminal grid that shows which agent needs you. Local, tmux-backed, MIT.
git clone https://github.com/receptron/mulmoterminal.git -
whetstone
SkillsSmall, sharp, agent-agnostic skills that keep an AI agent's work honest.
git clone https://github.com/jovesun-lab/whetstone.git -
pmb
AI repositoriesLocal-first persistent memory for AI coding agents (Claude Code, Cursor, Codex) over MCP. Decisions, lessons and facts live in one SQLite file on your disk. Offline, multilingual.
git clone https://github.com/oleksiijko/pmb.git -
tia-portal-mcp
MCP serversSpecialized bridge designed to connect LLMs and AI agents directly to Siemens SIMATIC TIA Portal V21.
git clone https://github.com/Czarnak/tia-portal-mcp.git -
Orkas-VideoStudio
AI repositoriesTurn your coding agent into a video studio: describe a video in plain language, and your agent writes the timeline and produces the file.
git clone https://github.com/Orkas-AI/Orkas-VideoStudio.git -
ai-engineering
SkillsDeveloper-centered AI engineering: build software with security, quality and governance. One local binary under the agent you already run
git clone https://github.com/arcasilesgroup/ai-engineering.git -
DuDuClaw
Agents & frameworksTurn AI coding CLIs (Claude Code, Codex, Antigravity) into AI employees on LINE, Telegram, Discord, Slack and 7 more chat apps. A judge reviews each result, every cost is logged, memory stays on your machine. Also runs as a standalone MCP memory server. Self-hosted, Apache 2.0.
git clone https://github.com/zhixuli0406/DuDuClaw.git -
dsh-research-report
Tools & appsVerifiable research-report engine for DeepSeek Harness: content-addressed evidence ledger (claim-snapshot binding, tamper-evident) plus versioned sealed reports with per-claim verification verdicts and a manifest-sealed directory.
git clone https://github.com/PerryLink/dsh-research-report.git -
anywhere-agents
SkillsOne config to rule all your AI agents: portable (every project, every session), effective (curated writing, routing, skills), and safer (destructive-command guard).
git clone https://github.com/yzhao062/anywhere-agents.git -
TaskWeaver
Agents & frameworksThe first "code-first" agent framework for seamlessly planning and executing data analytics tasks.
git clone https://github.com/microsoft/TaskWeaver.git -
Claude-Skills
Skills403 AI skills, 76 expert agents, and 973 stdlib Python tools for every team: engineering, UI/UX design, PM, marketing, C-level, compliance, business ops, research, founders, and a LinkedIn toolkit. Installs on Claude Code, Cursor, Codex, Gemini, Copilot, and 6 other AI assistants.
git clone https://github.com/borghei/Claude-Skills.git -
wenflow
Agents & frameworks先说清你想解决的事,再开始学习。问流 WenFlow:从真实问题出发的开源 AI 学习路径原型——对话澄清目标、生成可执行路径、回合式教学、遗忘曲线复习、学习负荷追踪(LSS/KTL/LF/LSB);自带 18 页管理后台与虚拟学习者仿真。Vue3 + Node.js + SQLite,MIT,可自托管。早期实验原型。
git clone https://github.com/wenflow-org/wenflow.git -
chessmata
MCP serversChessmata: chess game for humans and AI agents
git clone https://github.com/metavert-io/chessmata.git -
maestro-orchestrate
Agents & frameworksMulti-agent orchestration platform for Gemini CLI, Claude Code, Codex, and Qwen Code — 39 specialists, parallel subagents, persistent sessions, and built-in code review, debugging, security, SEO, accessibility, and compliance tools
git clone https://github.com/josstei/maestro-orchestrate.git -
beyondseo
SkillsYour AI SEO house. Audit your website, write useful content, compare competitors and plan backlinks inside your AI assistant. Free and open source.
git clone https://github.com/beyondtahir/beyondseo.git -
walrus-memory
Agents & frameworksA portable memory layer that makes AI agents reliable across apps and sessions. Persistent, verifiable, and fully under your control.
git clone https://github.com/MystenLabs/walrus-memory.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.