
pentagi
AgentSelf-hosted multi-agent system that plans and runs penetration tests in a sandbox
- Open source
- Open-source agent
- 34.3K GitHub stars
- Security

Self-hosted multi-agent system that plans and runs penetration tests in a sandbox

SentinelOne and IT security catalog, prices, quotes and checkout links for Israel
A reverse CAPTCHA that proves a language model, not a person, is answering
Sign agent actions into a tamper-evident log and verify any agent's log from an MCP client
Run a free security, email, speed, DNS, cookie and SEO check on any public site

Free link and site safety checks that warn agents about prompt-injection traps
Check any domain's SPF, DKIM, DMARC and blacklist status from your AI assistant, free
Hold risky agent actions for passkey approval and keep signed receipts you can verify
Runs locallyA safer MCP for Dokploy: agents deploy and fix apps without seeing keys or secrets
Not checked yetFree, keyless email checks for fake signups: disposable domains, typos, Gmail aliases
Local, reversible masking of client names and numbers before text goes to an AI
Runs locally
Open-source control plane that firewalls MCP tool calls and caps agent model spend
Verified email for AI agents: checked inbound mail, held sends and disposable inboxes
Not checked yetFlags fake engagement and prompt injection in AI-agent job board listings
Runs locallySearch open cybersecurity jobs with posted pay, refreshed hourly from employer sites
Not checked yet24 free DNS, email-auth, certificate, WHOIS and network check tools, no key
Not checked yetCheck DKIM and DMARC alignment, analyse headers and screen payment-change emails
Not checked yetSafety grades for MCP servers and APIs, with wrap and lockfile modes to catch tool changes
Runs locallyCheck a company's data breach history and open settlements, with sources
Not checked yetFree CVE lookups, lockfile checks and patch-priority ranking for AI agents
Not checked yetRead-only MCP server to search ERC-8004 agents on Ethereum and Base
Not checked yetScan text or files for hidden Unicode, decoded ASCII smuggling and look-alike letters
Not checked yetStatic security scanner for MCP servers, agent skills and npm or PyPI packages
Runs locallyChecks npm and PyPI package names against live registries before you install
Not checked yetCheck Supabase SQL for who can read and write each table, with fix SQL
Not checked yetCheck which AI bots a website's robots.txt lets in, grouped by purpose
Not checked yetOffline security checks for code, dependencies and AI agent setup with six read-only tools
Runs locallyPaste a suspicious message and get a plain finding and the smallest safe next step
Not checked yetDaily spending caps and phone approval for AI agents that pay for things
Not checked yetGrade an AI-built app from A to F for leaked keys and open data, with fix prompts
Runs locally