Open source ai-agent-security projects
Every project in the registry tagged ai-agent-security, ranked by real GitHub adoption.
secure multiplexed execution paths for agents - zero trust, zero setup, zero latency.
Open-source AI agent firewall for MCP security and agent egress. Scans mediated HTTP, MCP, A2A, and WebSocket traffic for exfiltration, SSRF, and prompt injecti
Open-source antivirus for AI agents: block risky tools, secret access, prompt injection, malicious packages, MCP servers, plugins, and skills at runtime.
Related tags
Frequently asked questions
How many open source ai-agent-security projects are there?
This registry tracks 3 projects tagged ai-agent-security, with 5,631 GitHub stars between them. The most-adopted is nono at 4,124 stars.
Are these ai-agent-security projects free to use?
Yes — 3 of the 3 carry an explicit open-source licence across 1 distinct licence, so there is no licence fee. Where a project also sells a hosted or enterprise version, the self-hosted path remains free.
Which ai-agent-security project should I choose?
The list above is ranked by GitHub stars, but stars measure attention rather than fit. Check three things on each card: the licence (permissive versus copyleft), the language it is written in, and the last-push date — a high-star project that has not been pushed in a year is a liability.
Are these ai-agent-security projects still maintained?
3 of the 3 were pushed in the last 90 days, and every card shows its exact last-push date so you can see the rest. Sort your shortlist by that date before committing to a migration.