GitHub topic

agent-security GitHub repositories

Explore 6 tracked GitHub repositories tagged agent-security. Compare their recorded star activity and implementation languages, then follow related topics to find other projects.

Snapshot: 2026-10-28. The collection gained 44 stars since the previous daily snapshot.

Tracked repositories: 6
Total stars: 10,693
Stars gained · 7 days: +302
Stars gained · 30 days: +989

Compare star activity

Up to five projects on this page, ordered by total stars. Open a project for its description and recorded star history.

Swipe to compare all star periods →

Star activity for agent-security repositories on this page
Repository	Total stars	Today	7 days	30 days
Tencent/AI-Infra-Guard	7.1K	+33	+225	+543
hashgraph-online/hol-guard	1.0K	+2	+46	+332
arcjet/arcjet-js	694	+0	+1	+10
samvallad33/vestige	657	+1	+4	+9
NVIDIA/SkillEvaluator	607	+8	+22	+85

Explore repositories

Showing 1–6 of 6 tracked repositories.

Tencent/AI-Infra-Guard

A full-stack AI Red Teaming platform securing AI ecosystems via Agent Scan, Skills Scan, MCP scan, AI Infra scan and LLM jailbreak evaluation.

hashgraph-online/hol-guard

Open-source antivirus for AI agents: block risky tools, secret access, prompt injection, malicious packages, MCP servers, plugins, and skills at runtime.

arcjet/arcjet-js

Runtime security for AI apps and agents: prompt injection detection, tool-call authorization, sensitive-data redaction, bot protection, and rate limiting. Drop it into your JS/TS code.

★ 694+0 todayTypeScript

ai-agents mcp

View ↗

Think before doing, prove before saving. Vestige is a local, deterministic safety kernel for AI agents. Every memory write and agent action is recorded in Strata, an append-only log, so you can see exactly what your agent did and why.

NVIDIA/SkillEvaluator

Multi-tier framework for evaluating AI agent skills with quality gates, semantic overlap detection, synthetic evaluation dataset generation, and live agent evaluation that measures how skills affect agent behavior.

★ 607+8 todayPython

claude-code codex

View ↗

secureagentics/Adrian

Open-source runtime AI agent security tool - monitors and controls AI agents, catching malicious tool use, prompt injection, and policy drift in real time, before the agent acts.

agent-security GitHub repositories

Compare star activity

Explore repositories

Tencent/AI-Infra-Guard

hashgraph-online/hol-guard

arcjet/arcjet-js

samvallad33/vestige

NVIDIA/SkillEvaluator

secureagentics/Adrian

Sign in to continue

Loading

Account settings

Delete listing?