ssh.bot – Controlled SSH Access for AI Agents
SSH proxy with command allowlists stops AI agents from running rm -rf.
Live audit log of every command, file, and network connection a Claude Code (or any matched) session makes, from the kernel.
Kernel-level eBPF filtering tracks AI agent process trees without strace noise.
Developers using Claude Code, security teams auditing AI agents
Tracee · Falco · strace
SSH proxy with command allowlists stops AI agents from running rm -rf.
Agent approval gates and audit logs beat open-source alternatives, but multi-agent governance isn't novel.
AI trading harness with approval boundaries and audit logs for Claude agents.
uvx one-liners for 10 log formats with Poisson-paced anomaly scenarios.
eBPF runtime visibility for AI agents—first tool solving the trust problem with Claude Code and similar.
Cryptographic proof audit logs can't be rewritten, even by DB admins.