# ClawHub

> **TL;DR.** [ClawHub](https://clawhub.

- **Category:** AI / Developer Tools / Agent Frameworks
- **Stage:** rising
- **Age:** 151 days
- **Origin date:** 2026-01-03
- **First detected:** 2026-04-17
- **Canonical URL:** https://earlyterms.com/term/clawhub
- **Sources:** 7 primary URLs

## Definition

[ClawHub](https://clawhub.ai/) is the public skill registry and marketplace for [OpenClaw](https://github.com/openclaw/openclaw), the self-hosted personal AI agent. Developers publish text-based `SKILL.md` bundles, browse by category and vector search, and install them into any OpenClaw instance with a single `clawhub install <slug>` command.

The [openclaw/clawhub repo](https://github.com/openclaw/clawhub) was created January 3, 2026 and clearFrame shipped publicly shortly after — skills grew from a few hundred to 52k+ tools and 180k users by mid-April 2026. Anyone with a week-old GitHub account can publish; Hermes Agent can also install skills from the registry, making it the de-facto agent-skill npm across competing runtimes.

## Analogy

npm for AI agent skills — a registry with versioning, vector search, and a one-line CLI install, feeding every major self-hosted agent runtime.

## Why it's emerging now

ClawHub crossed 52k skills and 180k users in under 16 weeks while surviving a February supply-chain attack that infected 341 skills (Koi Security / 1Password disclosure). An April 15 independent audit of 2,354 skills reset the security narrative — 4.4% malicious, 86% vulnerable — turning the registry from a feature into a category-defining piece of agent infrastructure.

## Related terms

- *parent:* OpenClaw
- *related:* Hermes Agent
- *related:* Claude Code
- *related:* Agent Harness
- *related:* Managed Agents
- *related:* MCP Server
- *related:* ClawHavoc
- *related:* agentskills.io
- *competitor:* HermesHub
- *competitor:* VS Code Marketplace

## Sources

1. [ClawHub — official marketplace](https://clawhub.ai/)
2. [openclaw/clawhub on GitHub](https://github.com/openclaw/clawhub)
3. [OpenClaw docs — ClawHub reference](https://docs.openclaw.ai/tools/clawhub)
4. [1Password — From Magic to Malware](https://1password.com/blog/from-magic-to-malware-how-openclaws-agent-skills-become-an-attack-surface)
5. [Trent AI — 2,354 ClawHub Skills Analysed](https://trent.ai/blog/clawhub-ai-agent-security-analysis/)
6. [The New Stack — Persistent AI Agents Compared](https://thenewstack.io/persistent-ai-agents-compared/)
7. [eSecurity Planet — Malicious Skills Found in ClawHub](https://www.esecurityplanet.com/threats/hundreds-of-malicious-skills-found-in-openclaws-clawhub/)

---
_Generated by EarlyTerms · https://earlyterms.com/term/clawhub_