ai-agent-security repositories
Trending repositories tagged ai-agent-security, ranked by trending score. Updated daily.
-
1
nolabs-ai/nono
agent runtime security - zero trust, zero setup, zero latency agent sandboxing
GitHub · Rust · 5,055 stars · 338 forks · +17 stars in 24 hours · Trending score 2.64
-
2
hashgraph-online/hol-guard
Open-source antivirus and firewall for AI agents: block risky tools, secret access, prompt injection, malicious packages, MCP servers, plugins, and skills at runtime.
GitHub · Rust · 1,116 stars · 285 forks · +4 stars in 24 hours · Trending score 1.86
-
3
pipelab-org/pipelock
Open-source AI agent firewall for MCP security and agent egress. Scans mediated HTTP, MCP, A2A, and WebSocket traffic for exfiltration, SSRF, and prompt injection, and emits mediator-signed action receipts: verifiable audit evidence from outside the agent.
GitHub · Go · 1,011 stars · 113 forks · +7 stars in 24 hours · Trending score 1.63
-
4
solongate/agent-security
Local-first, open-source security gateway for AI coding agents. Enforce tool-call policies, detect secrets, and audit actions on-device.
GitHub · Go · 674 stars · 104 forks · −31 stars in 24 hours · Trending score 1.21
-
5
tinylabscom/mvm
Manage secure microVMs — one command from zero to secure sessions, locally and remotely.
GitHub · Rust · 49 stars · 6 forks · +2 stars in 24 hours · Trending score 0.82
-
6
blitzcrieg1/agentmetry
Open-source security for AI coding agents: record, detect and block at the tool boundary, with a verifiable audit trail in the SIEM you already run.
GitHub · Python · 47 stars · 5 forks · +1 stars in 24 hours · Trending score 0.77
-
7
devadeiltonlima/ClawFast-
O ghostcyber do seu terminal: agente de pentest com IA que faz recon, explora e prova vulnerabilidades de verdade. Tor por padrão, 25 provedores de IA, binário único.
GitHub · 9 stars · 0 forks · +1 stars in 24 hours · Trending score 0.56
-
8
Attention-Span-AI/Tego
Tego limits what any AI agent can touch on Linux, and records every run. Rules for MCP servers, CI jobs, Python workers, 24/7 assistants and coding agents, enforced by the kernel.
GitHub · Go · 26 stars · 2 forks · 0 stars in 24 hours · Trending score 0.53
-
9
alexgreensh/repo-forensics
Offline security scanner for AI-agent repos, skills, plugins, and MCP servers.
GitHub · Python · 208 stars · 30 forks · 0 stars in 24 hours · Trending score 0.44
-
10
ThreeMoonsLab/agents-shipgate
The deterministic merge gate for AI-generated agent capability changes — a local-first, static Tool-Use Readiness review for MCP, OpenAPI, and SDK tool surfaces. Open-source CLI + GitHub Action.
GitHub · Python · 87 stars · 9 forks · 0 stars in 24 hours · Trending score 0.24
-
11
saivedant169/AegisFlow
Local-first policy gateway for coding agents. Allow, review, or block MCP, shell, SQL, GitHub, and HTTP actions with scoped credentials and signed evidence.
GitHub · Go · 40 stars · 13 forks · 0 stars in 24 hours · Trending score 0.22
-
12
awarexone/AXguard
Open-source AI security tool to scan and fix vulnerabilities in your vibe-coded projects before you ship. AXguard by AwareXone.
GitHub · Python · 27 stars · 7 forks · 0 stars in 24 hours · Trending score 0.22
-
13
eltociear/skill-audit-mcp
Static security scanner for MCP servers, agent skills & plugins: 17 attack patterns / 60 regex signatures, calibrated to a 1% false-positive rate over 196 public MCP servers. In the official MCP Registry: io.github.eltociear/skill-audit-mcp. Also a pay-per-call x402 API.
GitHub · Python · 5 stars · 2 forks · 0 stars in 24 hours · Trending score 0.19
-
14
Memnox/memnox-runtime
Let AI agents work autonomously. Memnox rules on every tool call Claude Code, Codex, Cursor, Gemini CLI and Windsurf make, before it runs: allow, ask or deny. Runs on your machine, needs no account, and no model decides anything. npm install -g memnox
GitHub · TypeScript · 11 stars · 5 forks · 0 stars in 24 hours · Trending score 0.09
-
15
open-coder-ai/chock
Governance-as-code for AI coding agents: author a policy once, enforce it on every agent (Claude, Copilot, Cursor, Codex) via git hooks, CI, and native controls.
GitHub · Python · 10 stars · 1 forks · 0 stars in 24 hours · Trending score 0.09
-
16
IronTrex-CyberTechnology/steelmatter-systems
Action safety for AI agents. Authorise the exact change, enforce shared limits and verify what happened at the destination, even after a lost reply. Apache-2.0 core by IronTrex.
GitHub · Go · 7 stars · 0 forks · 0 stars in 24 hours · Trending score 0.09
-
17
adamsjack711-ux/pkgxray
Pre-install security for AI agents, npm packages, and MCP servers. Zero-dep local static analysis; normal scans never execute package code.
GitHub · JavaScript · 12 stars · 4 forks · 0 stars in 24 hours · Trending score 0.09
-
18
mlcyclops/lucidagentide
Security-First Agentic IDE Coding Harness
GitHub · TypeScript · 27 stars · 4 forks · 0 stars in 24 hours · Trending score 0.08
-
19
Psionic-labs/Agent-Causality
Causal Debugging for Branching Multi-Agent Systems
GitHub · Python · 7 stars · 2 forks · 0 stars in 24 hours · Trending score 0.08
-
20
mas-bandwidth/nova-tools
One toolkit for a team of AIs on different models.
GitHub · Go · 22 stars · 0 forks · 0 stars in 24 hours · Trending score 0.08
-
21
lensapp/lens-sandbox-core
Core Rust library for Lens sandbox policy enforcement, networking, DNS, proxying, and boundary credential exchange.
GitHub · Rust · 8 stars · 1 forks · 0 stars in 24 hours · Trending score 0.02
-
22
openlegion-ai/openlegion
Secure autonomous AI agent framework and platform. Build AI teams by describing what you want. Orchestrate agents that can do everything a human can do.
GitHub · Python · 127 stars · 28 forks · 0 stars in 24 hours · Trending score 0.00
-
23
Top-Celestial-Company-Ltd/DROS-VajraClaw-Hacker
⚡ DROS™ VajraClaw (Hacker Edition): Free Multi-Agent Runtime Security & Docker Governance Gateway with W3C DID & <1μs Enforcement
GitHub · Python · 16 stars · 0 forks · 0 stars in 24 hours · Trending score 0.00
-
24
mcpware/IntentProbe
CPU activation probes for AI-agent guardrails and classification. One frozen local model pass, many independent heads. Open models, code and reproducible benchmarks.
GitHub · Python · 9 stars · 0 forks · 0 stars in 24 hours · Trending score 0.00