Mindburn-Labs/helm-ai-kernel
Fail-closed execution firewall for AI agents: quarantine MCP tools, proxy OpenAI-compatible requests, emit signed receipts, and verify EvidencePacks offline.
Fail-closed execution firewall for AI agents: quarantine MCP tools, proxy OpenAI-compatible requests, emit signed receipts, and verify EvidencePacks offline.
npx skills add Mindburn-Labs/helm-ai-kernelFail-closed execution firewall for AI agents: quarantine MCP tools, proxy OpenAI-compatible requests, emit signed receipts, and verify EvidencePacks offline.
Verify AI-generated output with an adversarial quality gate that forces revisions and prevents factual errors before code or content ships.
Personal AI config layer — skills for Claude Code and Codex, agent rules, and CLAUDE.md
Local-evidence production readiness audit for shipped apps, pre-launch reviews, post-merge checks, and "what breaks in prod?" questions without sending repo data to an external audit service.
DSPy/GEPA-powered self-improvement plugin for Hermes Agent skills, memory, and evaluator prompts.
Open-source shared memory for teams using AI agents. Captures every decision and the alternatives your team ruled out, and flags when a new decision contradicts an old one — so your team revisits past decisions intentionally, instead of re-litigating from zero.
Portable Claude Code skill ecosystem — 85+ skills, 26 commands, 21 agents