Back to Topics Directory
Topic Hub

#agent-security (21 Repositories)

Ranked open-source repositories tagged with #agent-security, scored by pull request acceptance likelihood and maintainer engagement velocity.

Topic Avg Merge Rate

52.9%

Avg Review Latency

57.4h

Filter by language

21 repositories tagged #agent-security

S TierPython 198 30 GFIs

DobermanCore/Doberman-Core

Your AI's guard dog. Doberman sits at runtime, gating every input, output and tool call to stop unsafe or unintended actions before they execute.

94.2%
Merge Rate
1d
First Review
82%
1st-Timers
13
Maintainers
S TierTypeScript 676

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.

86.6%
Merge Rate
4h
First Review
80%
1st-Timers
8
Maintainers
S TierPython 207

fu351/Doberman-Core

Your AI's guard dog. Doberman sits at runtime, gating every input, output and tool call to stop unsafe or unintended actions before they execute.

93.8%
Merge Rate
1d
First Review
83%
1st-Timers
11
Maintainers
A TierGo 319

Asymptote-Labs/agent-beacon

Agent Beacon is the world's first open-source telemetry layer for AI agents wherever they run: locally, in CI, in the browser, or in the cloud.

90.3%
Merge Rate
7d
First Review
100%
1st-Timers
4
Maintainers
A TierRust 400 4 GFIs

alibaba/anolisa

ANOLISA (Agentic Nexus Operating Layer & Interface System Architecture) | Agentic OS with runtime, security, observability, and Tokenless response compression for lower token usage and cost.

79.5%
Merge Rate
2d
First Review
65%
1st-Timers
33
Maintainers
A TierPython 326

PrismorSec/prismor

Self-hosted runtime control plane for AI agents. Observe or HITL approve or Block rogue tool calls before it executes: secret leaks, prompt injection, supply chain etc in a local dashboard. Agent agnostic (Claude,codex etc.)

86.2%
Merge Rate
2d
First Review
67%
1st-Timers
10
Maintainers
A TierTypeScript 176

Garudex-Labs/caracal

🐾 Authority, not credentials, for AI agents: policy-approved actions, delegation that can only narrow, instant revocation, tamper-evident audit.

80.0%
Merge Rate
2d
First Review
100%
1st-Timers
7
Maintainers
B TierTypeScript 812 1 GFIs

emiliaprotocol/emilia-protocol

Consequence firewall for machine actions. EMILIA Gate verifies exact authority before money, code, permissions, infrastructure, or regulated state changes; the open protocol makes the evidence independently verifiable.

84.3%
Merge Rate
6d
First Review
100%
1st-Timers
1
Maintainers
A TierPython 181

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.

53.6%
Merge Rate
2h
First Review
43%
1st-Timers
13
Maintainers
A TierPython 481

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.

79.8%
Merge Rate
9d
First Review
100%
1st-Timers
2
Maintainers
B TierRust 115

GenseeAI/gensee-crate

Run AI harnesses like Claude Code, Codex, Copilot, Antigravity, and Omnigent in disposable workspace forks. Review, merge, or roll back changes with policy enforcement and provenance.

15.4%
Merge Rate
8h
First Review
100%
1st-Timers
2
Maintainers
B TierPython 15.2k

NVIDIA/SkillSpector

Security scanner for AI agent skills. Detect vulnerabilities, malicious patterns, security risks, prompt injection, data exfiltration, and supply-chain risks in Claude Code, Codex, and MCP skills before you install them.

64.3%
Merge Rate
7h
First Review
52%
1st-Timers
64
Maintainers
B TierRust 5.3k

Nasiko-Labs/nasiko

Developer Control Plane for your AI Agents

61.1%
Merge Rate
7d
First Review
75%
1st-Timers
4
Maintainers
B TierPython 5.7k

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.

70.3%
Merge Rate
7d
First Review
80%
1st-Timers
10
Maintainers
B TierTypeScript 371 2 GFIs

Agent-Threat-Rule/agent-threat-rules

Open detection-rule standard for AI agent security threats — like Sigma, but for AI agents. Executable rules across 10 categories; merged into Microsoft AGT, Cisco AI Defense, MISP, OWASP, FINOS & SigmaHQ. MIT-licensed.

71.5%
Merge Rate
6d
First Review
100%
1st-Timers
1
Maintainers
D TierRust 286

eqtylab/cupcake

A native policy enforcement layer for AI coding agents. Built on OPA/Rego.

0.0%
Merge Rate
-
First Review
0%
1st-Timers
0
Maintainers
D TierPython 345

getagentseal/agentseal

Security toolkit for AI agents. Scan your machine for dangerous skills and MCP configs, monitor for supply chain attacks, test prompt injection resistance, and audit live MCP servers for tool poisoning.

0.0%
Merge Rate
-
First Review
0%
1st-Timers
0
Maintainers
D TierJavaScript 206

0xNyk/awesome-agent-cortex

Curated map of AI agent frameworks, protocols, runtimes, skills, memory, identity, security, evaluation, and commerce.

0.0%
Merge Rate
-
First Review
0%
1st-Timers
0
Maintainers
D TierPython 153

apisec-inc/mcp-audit

See what your AI agents can access. Scan MCP configs for exposed secrets, shadow APIs, and AI models. Generate AI-BOMs for compliance.

0.0%
Merge Rate
-
First Review
0%
1st-Timers
0
Maintainers
D TierTypeScript 287

backbay-labs/clawdstrike

AI EDR for developer workstations and autonomous agent fleets. Build Swarm Detection & Response platforms with Clawdstrike.

0.0%
Merge Rate
-
First Review
0%
1st-Timers
0
Maintainers
D TierRust 302

duncatzat/vigils

A local control plane for AI agents — see what they do, approve what matters, keep secrets out. Rust + Tauri + Chrome MV3.

0.0%
Merge Rate
-
First Review
0%
1st-Timers
0
Maintainers
Best Agent-security Open Source Repositories & C-Rank™ | GetMerged