Projects

Rampart intercepts agent actions at the OS layer before they execute. Network requests, file writes, subprocess spawns — all evaluated against your policy profile. If an action violates policy, it's blocked. The agent sees a failure; you see a log entry.

• — OS-layer interception via eBPF and syscall hooks
• — Policy-as-code: YAML rules, version-controlled
• — Works with Claude Code, Cursor, Cline, and similar tools
• — Ships with default profiles tuned for common agents

Snare lets you plant detection tripwires in credentials, files, and API responses. When an AI agent — or a human attacker — triggers one, you get an immediate alert with request metadata that often fingerprints the caller. Detection that works even when prevention fails.

• — Works in .env files, credentials dirs, git history
• — Alerts include user agent, IP, and timing data
• — Detects both human attackers and misbehaving agents
• — No infrastructure required — tokens resolve via DNS