9 projects
revoco
Undo for AI agent actions. Plans the rollback before the action runs, proves it still works, and rolls back a compromised grant's whole blast radius in one call.
deluluscan
AI-augmented, evidence-first security auditor for authorized testing of web, API, application, container, cloud and LLM/AI-system targets.
retie
A coding agent that classifies every action by how hard it is to undo, and records it before it runs.
irredux
Route AI agent actions by how hard they are to undo, not by how hard they look. Consequence-aware model-tier and human-review scheduling.
mcp-gate-policy
Runtime policy-enforcement proxy for MCP tool calls, with NIST-aligned audit & threat scanning
mnemosyne-guard
NIST-aligned Memory Integrity & Context-Provenance Firewall for agentic AI (OWASP ASI06).
veritrail
Verifiable provenance and forensics for autonomous AI agents — a tamper-evident flight recorder and cryptographic chain-of-custody for agentic actions.
condor-scan
GCP conditional IAM & tag-based privilege-escalation scanner
netcheck-ir
Enterprise network triage, security posture, and IR/forensics in one command - environment-aware (WSL2/VM/cloud), with optional AI analysis (Claude / OpenAI / Azure / Ollama).
