awesome-openclaw-agents
196 production-ready AI agent templates for OpenClaw. SOUL.md configs across 24 categories. Submit yours!
No outside reports on file
Using unvetted community templates can expose your system to malware, data leaks, and misbehaving agents unless you carefully audit each template before deployment.
Based on public adoption and transparency signals as of Oct 21, 2026. Our opinion, not a code audit or security guarantee.
What it can access
- Local filesNo local folder access notedLOW
- Command executionNo shell command runner notedLOW
- Network reachConnects to outside service APINOTED
- CredentialsNo API token requiredLOW
- Package sourceGitHub (mergisi/awesome-openclaw-agents)PUBLIC
Inferred from this listing’s public package details and description. Check the project’s source before installing.
Install
No npm or PyPI package is listed. Install from source: github.com/mergisi/awesome-openclaw-agents ↗
About Awesome Openclaw Agents
This is a collection of 162 pre-made AI agent templates designed for OpenClaw, an AI agent framework. Each template includes configuration files that define how agents should behave. You can use these templates as starting points to build your own AI agents.
Who it’s for
Developers building AI agents with OpenClaw who want ready-to-use examples and patterns. Teams looking to speed up agent development by reusing tested templates.
Alternatives
- Anthropic's model context protocol (MCP) — Official agent framework with built-in safety features.
- LangChain templates — Community agent templates with more established vetting.
- Hugging Face Agents — Pre-built agents focused on machine learning tasks.
- Creating custom templates — Build your own agents with known, audited code.
Setup
Check these steps against the project’s own instructions before running anything.
Follow the project's README for detailed setup instructions. The repository is at https://github.com/mergisi/awesome-openclaw-agents (opens external site) and can be cloned or explored on GitHub.
Why this grade
Signal-based grade (3/7 points): well starred on GitHub, public source code. This reflects adoption and transparency, not a code review.
Popularity and upkeep
- GitHub stars
- 4k
- Listing last refreshed
- 2026-10-28
These are public popularity signals, not a maintenance check. Look at the repository’s commit history and open issues.
Security reports
No reports found for this package in our research (last checked 2026-10-29).
Risks to watch for
- Untested code execution: Templates from open-source collections may contain bugs or outdated code that could crash your application or behave unexpectedly.
- Dependency vulnerabilities: Each template might use libraries with known security flaws if not regularly updated.
- Malicious templates: Community-submitted templates could include hidden code designed to leak data, steal API keys, or access unauthorized systems.
- Over-permissioned agents: Templates might request more system access (file system, network, APIs) than actually needed, increasing risk if an agent malfunctions.
- Prompt injection via templates: Configuration files could contain crafted text that tricks your AI into ignoring safety guidelines or executing unintended actions.
How to lower the risk
Least-privilege permissions
- Run agents with minimal file system and network access needed for their actual job.
- Never give agent templates admin or root-level permissions.
Network isolation
- Restrict which external APIs and endpoints agents can contact.
- Use firewalls or network policies to block unexpected outbound connections.
Monitoring
- Log all template execution and monitor for unusual API calls or file access.
- Set alerts if agents try to access unauthorized resources.
Red flags to watch for
- Templates requesting permissions unrelated to their stated purpose.
- Unsigned or unverified contributors; check GitHub commit history.
- Recently added templates with few reviews or stars; prioritize widely-used ones.
Questions
How do I install Awesome Openclaw Agents?
Awesome Openclaw Agents does not publish a standalone npm or PyPI package. Clone or follow the setup instructions in its source repository at github.com/mergisi/awesome-openclaw-agents.
Are there security reports about Awesome Openclaw Agents?
No reports found for this package in our research (last checked 2026-10-29). Awesome Openclaw Agents currently holds Grade C (Moderate risk signals) based on public adoption and transparency signals. Key risk areas to watch include untested code execution, dependency vulnerabilities, malicious templates.
Is Awesome Openclaw Agents actively maintained?
Awesome Openclaw Agents has 4k GitHub stars. Our directory data was last refreshed on 2026-10-28. Check recent commit activity, release tags, and open issues at github.com/mergisi/awesome-openclaw-agents before pinning it in production.
What are alternatives to Awesome Openclaw Agents?
Notable alternatives to Awesome Openclaw Agents include Anthropic's model context protocol (MCP) (Official agent framework with built-in review features), LangChain templates (Community agent templates with more established vetting), Hugging Face Agents (Pre-built agents focused on machine learning tasks), Creating custom templates (Build your own agents with known, review code). You can also compare Awesome Openclaw Agents side by side with other MCP servers in the Related tools section on this page.
README badge and team notes
Maintain or use Awesome Openclaw Agents? Show its live grade in your GitHub README, docs site, or run a check from the terminal before you install.
GitHub README Markdown:
[](https://agentarmorhq.com/skills/mergisi-awesome-openclaw-agents)HTML embed:
<a href="https://agentarmorhq.com/skills/mergisi-awesome-openclaw-agents"><img src="https://agentarmorhq.com/api/badge/mergisi-awesome-openclaw-agents" alt="AgentArmorHQ Risk Grade for Awesome Openclaw Agents" height="20" /></a>Terminal check:
curl -fsSL https://agentarmorhq.com/api/cli | node --input-type=module - check "mergisi-awesome-openclaw-agents"- Compare Awesome Openclaw Agents →
- Add to a team allowlist
- Claude and terminal guide →
- Download the PDF guide
Share with your security lead
Need sign-off to use awesome-openclaw-agents? Copy this note for Slack, a ticket or a pull request.
### AgentArmorHQ Security Review Memo: awesome-openclaw-agents
- **Listing URL:** https://agentarmorhq.com/skills/mergisi-awesome-openclaw-agents
- **Type:** App connector
- **Risk Grade:** Grade C (Moderate risk signals)
- **Outside Security Advisories on File:** 0
- **Public Adoption:** 4k GitHub stars
#### Permission & Blast-Radius Signals
- **Local files:** No local folder access noted
- **Command execution:** No shell command runner noted
- **Network reach:** Connects to outside service API
- **Credentials:** No API token required
- **Package source:** GitHub (mergisi/awesome-openclaw-agents)
#### Recommended Hardened Setup
- **Source Repo:** https://github.com/mergisi/awesome-openclaw-agents
- **Controls:** Pin an exact version in `.mcp.json`, scope access to a single workspace folder, and use a least-privilege read-only token where supported.
_Based on public adoption and transparency signals as of Oct 21, 2026. Our opinion, not a code audit or security guarantee._Key facts
- Type
- App connector
- Publisher
- mergisi
- Source code
- github.com/mergisi/awesome-openclaw-agents
- Est. context load
- ~850 tokens / turn (~5 tool schemas, 0.43% of 200k context)
- Popularity
- 4k GitHub stars
- Last updated
- 2026-10-28
- Last graded
- 2026-10-21
Community
Discussions for Awesome Openclaw Agents
Ask questions or share configuration tips. Governed by our Community Rules & Terms.
No posts match this filter yet.
Be the first to ask a question or share a working tip.
Check before you install, in Claude
Your assistant answers Block, Review or No known issues for any package before it installs it.
Get this check inside Claude