Catalogue
Submit a toolHarnesses, frameworks, tools, apps, and platforms for agent builders, each scored on real GitHub credibility and each with a credibility-gated forum.
90 tools · showing 49–72
ToolPentestCode
Security
s0ld13rr
PentestCode - Multi-agent AI penetration testing system with persistent engagement state, strategic coordination, and parallel autonomous op
penetration-testingmulti-agentgptclaude
ToolAgent Vault
Security
Infisical
HTTP credential proxy that injects secrets into agents' outbound requests so agents never hold real credentials
credential-proxysecrets-managementhttp-proxyinfisical
ToolDoberman
Security
DobermanCore
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..
guardrailsprompt-injectionhuman-in-the-loopproxy
ToolOpen Kritt
Security
Kritt-ai
Orchestrate AI agents to find real vulnerabilities in code.
vulnerability-scannersource-code-analysislocal-first
HarnessParlant
MemorySecurity
emcie-co
Interaction control harness optimized for controlled, consistent, and predictable LLM interactions.
customer-serviceguardrailschatbotgemini
HarnessSandBase Harness
SecurityMonitoring
sandbaseai
Open-source CMA-compatible agent runtime for any model, with MCP tools, sandboxed sessions, audit, replay, and a local console. Includes a n
sandboxlocal-firstgovernancesession-replay
ToolSandbox
SecurityInterface
agent-infra
All-in-One Sandbox for AI Agents that combines Browser, Shell, File, MCP and VSCode Server in a single Docker container.
sandboxcode-executionbrowser-automationdocker
ToolDeepAudit
Security
lintsinghua
DeepAudit：人人拥有的 AI 黑客战队，让漏洞挖掘触手可及。国内首个开源的代码漏洞挖掘多智能体系统。小白一键部署运行，自主协作审计 + 自动化沙箱 PoC 验证。支持 Ollama 私有部署 ，一键生成报告。支持中转站。让安全不再昂贵，让审计不再复杂。
code-auditvulnerability-scannergeminiollama
ToolForge
DeploymentSecurity
initializ
Forge is the open-source runtime for Anthropic's Agent Skills standard — built for the agent that runs next to a service, in your environmen
skilla2akubernetesegress-control
HarnessSWE-agent
CodingSecurity
SWE-agent
Lets a language model autonomously use tools to fix GitHub issues and CTF challenges; superseded by mini-swe-agent
evaluationgithubctf
ToolVigolium
MonitoringSecurity
vigolium
Vigolium - High-fidelity vulnerability scanner fusing agentic AI with native speed, modularity, and precision
vulnerability-scanneroast
ToolCloudflare OS
InterfaceSecurityCoding
cloudflare
Agent workspace built on Cloudflare Workers for creating documents, building apps, and running agents with your company’s context and system
productivitysandboxguardrailsapp-generationhuman-in-the-loop
ToolMnemory
MemorySecurity
fpytloun
Mnemory is a self-hosted MCP server that turns agent memory into shared infrastructure. One command (uvx mnemory) runs i
local-firstvector-dbfact-extractionsemantic-search
ToolOpenOSINT
SecurityResearch
OpenOSINT
AI-powered OSINT agent with interactive REPL, MCP server, and CLI. 16 tools. Works with Claude, GPT-4, or local models. For authorized secur
osintreconnaissancemcp-servercli
ToolAgentic Security
Security
msoedov
Open-source vulnerability scanner that red-teams LLMs and agent workflows with jailbreak, fuzzing, and multimodal probes
red-teamfuzzingvulnerability-scanner
ToolAutoCVE
Security
larlarua
Agent-driven automated CVE discovery platform for source code auditing, vulnerability verification, and report generation.
vulnerability-scannercvecode-auditpenetration-testing
ToolAos Ce
DeploymentSecurity
unicity-aos
AOS Community Edition: the open agent operating system.
clisandboxdaemon
ToolNumbat
SecurityMonitoring
perplexityai
Visibility into AI agent activity on endpoints, with on-device detection, optional pre-action blocking, and forensic reconstruction.
endpoint-detectionforensicsgovernancetelemetry
ToolTreg
ConnectorsSecurity
superdesigndev
OpenRouter for agent tools. Join community here: https://discord.gg/6mQYYfFMAn
gatewayproxysecrets-managementapi
ToolAdrian
SecurityMonitoring
secureagentics
Say your agent starts resetting passwords it shouldn't. Logging it after the fact is too late, and no prompt-injection c
prompt-injectionruntime-securitythreat-detectionpolicy-drift
ToolDeepTeam
Security
confident-ai
DeepTeam is a framework to red team LLMs and AI agents.
red-teamprompt-injectionguardrails
ToolRikugan
SecurityCoding
buzzer-re
A reverse-engineering agent for IDA Pro and Binary Ninja
reverse-engineeringida-probinary-ninjamalware-analysis
PlatformContainer use
CodingSecurity
dagger
MCP server giving each coding agent an isolated container and git branch so multiple agents work in parallel without clobbering each other.
daggersandboxdockergit-branching
ToolVisa Vulnerability Agentic Harness
Security
visa
Visa Vulnerability Agentic Harness
vulnerability-remediationsarifautomated-remediation