
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
Encrypted vault for .env files with scoped, audited MCP access for coding agents
Read-only MCP view of Odile Gate runs, held actions, audit log and metrics
Daily AI white-hat review of your site, with findings reported as they appear
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

Ask why Korzen Bot Protection blocked a request and which AIs read your site
Run a free security, email, speed, DNS, cookie and SEO check on any public site
Remote MCP server for Curve Compliance's healthcare marketing and consent reports
Not checked yet
Free link and site safety checks that warn agents about prompt-injection traps
Read-only Solana token risk checks: honeypot, liquidity lock, authorities, holders
Let an AI agent register and pay for its own verifiable DID-LLM identity
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 locallyHosted MCP server for CVE, CISA KEV and exploit data, SBOM scans and IOC checks
Free remote MCP server for SEO, AI-crawler visibility and security-header checks
A safer MCP for Dokploy: agents deploy and fix apps without seeing keys or secrets
Not checked yetLook up who stands behind a website or AI agent and what the agent may do
Ask Claude about on-site incidents, monthly counts and trends in SISA
Bulk domain lookup: tech stack, email provider, DNS, WHOIS age, SSL expiry, AI bot rules
Encrypted secrets for agents plus a phone approval step for sensitive actions
Runs locallyGive AI agents WhatsApp, Telegram and PostgreSQL access limited by explicit scopes
Not checked yet
Record signed events, AI outputs and document fingerprints, then verify them later
Scan a URL for AI Act issues, classify risk and issue Article 50 notices and receipts
Screen banks, wires, sanctions, wallets and transfers before an agent moves money
Versioned store for specs, plans and tasks that AI agents read and write
Not checked yet
Check children's screen time and manage device rules from an AI assistant
Not checked yetCheck user prompts for injection and jailbreaks with a guard that learns from your labels
Scan PDFs and Office files for malware and hidden prompt injection before an AI reads them