Strict Goal Mode agents, commands, and guard plugin for OpenCode.
Full Court Defense CLI — security scanning for AI agents from your terminal
AI agent security & MCP security middleware — prompt injection detection, AI firewall, runtime guardrails & data-loss prevention for LLM tool calls. 8-layer defense against data exfiltration & dangerous commands. Zero dependencies. SDK + OpenClaw plugin.
Catch risky code before your AI coding agent ships it. Reviews every edit and shell command with full context.
Production utilities for the OpenAI Agents SDK — conversation persistence, tool caching, handoff tracking, tracing export, and guardrail presets
AgentOS: open-source TypeScript framework for autonomous AI agents. Unified graph orchestration, cognitive memory, runtime tool forging, multi-tier guardrails, voice pipeline, and 11 LLM providers.
ThumbGate self-improving agent governance: thumbs-up/down turns every mistake into a prevention rule and blocks repeat patterns. 36 pre-action checks, budget enforcement, and self-protection for Claude Code, Cursor, Codex, Gemini CLI, and Amp.
A deterministic stop condition and code-graph context layer for AI coding agents: gives agents a code graph to make changes, then blocks only net-new detector-backed regressions at the stop boundary, with no model in the gate.
Development guardrails for SignalTree reactive JSON. Performance monitoring and anti-pattern detection.
Inline PII, credential, and regulated-data classifier for AI agent I/O. Dual-layer: deterministic regex + optional semantic Guard. Library + CLI.
OpenBox AI governance SDK for TypeScript. Generated from a TypeSpec source of truth in this monorepo; the same spec drives sibling per-language SDKs.
Give your AI agents reflexes — write the logic once, enforce it on every coding agent.
A repo-level harness for coding agents — file-level constraints that keep every agent true to your repo's structure. Node-friendly launcher for the Python engine.
Official DriftGard Node.js SDK — evaluate LLM interactions against your compliance policy
Input and output guardrails middleware for Vercel AI SDK.
Composable AI safety pipeline framework with industry compliance packs (HIPAA, SOX, GDPR, FedRAMP)
Official ClearedBy SDK — gate agent actions, wait for human review, guard a function.
Docs-based guardrails for AI coding workflows: coverage scoring, doc-drift checks, and diff safety review.
Wardrail MCP server — let your coding agent consult your project's contract while it writes code.
Wardrail Claude Code plugin — consult your project's contract while coding (MCP) plus a checkpoint->clear->resume workflow with machine-verified checkpoints.
VHK — AI 코딩 세션을 목표·증거·기억·규칙으로 묶는 한국어 CLI. 규칙 동기화, MCP 30 tools, verify/review/preflight 게이트.
VAIBot governance plugin for Claude Code — intercepts tool calls, classifies risk, enforces policy, and creates tamper-evident audit receipts with on-chain provenance anchoring.
Governance layer for multi-agent AI systems. 7 mechanically enforced rules, 30 tools including kill switch, audit chain, dispatch, drift audit, security audit, page health, pre-publish audit, and session close. Works with Ruflo, Hivemind, Agent Teams, and