Library
85,340 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
-
relay
SkillsInfrastructure for coding agents
git clone https://github.com/AgentWorkforce/relay.git -
agent-collab-skills
SkillsClaude Code marketplace for multi-agent collaboration — task splitter, output reconciler, adversarial debate, shared memory, acceptance gate. Composes with codex-delegate / gemini-delegate.
git clone https://github.com/WenyuChiou/agent-collab-skills.git -
iPolloWork
SkillsAn enterprise collaboration platform for people and multi-agent teams, built on the open-source DeepSeek Harness. Shared projects, plugins and Skills, integrated messaging, and editable code, documents, presentations, design, websites and video.
git clone https://github.com/Devin-AXIS/iPolloWork.git -
pioneer
SkillsMultiplayer harness where humans and AI agents work together and build on shared context.
git clone https://github.com/pioneerdotai/pioneer.git -
forge
SkillsGive your coding agent a delivery process you can trust. Spec → Plan → Build → Acceptance → Ship.
git clone https://github.com/brightstack/forge.git -
alook
SkillsMulti-Agent Collaboration for Team and Friends
git clone https://github.com/alookai/alook.git -
Codecks
SkillsLocal-first web console for Codex, Claude Code, OpenCode and ACP agents — remote chat, approvals, multi-provider sessions, agent collaboration and task wake-ups.
git clone https://github.com/Ovalene2333/Codecks.git -
engineering-multi-ai-skills
SkillsGeneral engineering skills and provider-neutral multi-agent collaboration workflows, templates and execution tools.
git clone https://github.com/TianMingKanae/engineering-multi-ai-skills.git -
clawrush
SkillsC(H+A)RM build diary — a CRM for Human & Agent collaboration, built in public with Claude Code. Framework: github.com/tonydzi/charm-os. English diary, longreads & reusable artifacts. RU: Telegram @ClawRus.
git clone https://github.com/tonydzi/clawrush.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.