agentsh
by canyonroad · GitHub
Execution-Layer Security (ELS) for AI agents — policy-enforced shell with audit.
⭐ Stars
359
🍴 Forks
15
📜 License
Apache-2.0
Commercial use OK📅 Created
2025
🔄 Last commit
19 days ago
🏷️ Category
agentic-ai
💻 Language
You maintain this project?
Claim its page: indexed whatever its rank, translated into six languages, and enriched with what you write yourself.
📈 Star history
2026-07-202026-07-21
📄 About
Execution-Layer Security (ELS) for AI agents — policy-enforced shell with audit.
❓ Frequently asked questions
What is agentsh?
Execution-Layer Security (ELS) for AI agents — policy-enforced shell with audit.
Is agentsh open source?
agentsh is an open-source project. It is released under the Apache-2.0 license.
Is agentsh free?
Yes. agentsh is free and open source — you can use, modify and self-host it.
🏅 Maintainer of this project?
Add this live badge to your README — your GitHub stars and directory rank, refreshed daily.
[](https://opensourceai.tech/project/canyonroad-agentsh.html)
🧬 Shares DNA with🧬 View the DNA map →
secureclaw
SecureClaw - Security Plugin and Skill for OpenClaw OWASP-Aligned
★ 348 · agentic-ai
sharesai-securityagentic-ai
h4cker
This repository is maintained by Omar Santos (@santosomar) and includes thousands of resources…
★ 28.5k · ai
sharesai-security
agent-skills-hub
Discover and compare open-source Agent Skills, tools & MCP servers — with quality scoring, tren…
★ 313 · agent-skills
sharesai-security
Measured from GitHub topics shared by both projects, weighted by how rare each topic is.