Search: ai-guardrails
Search MCP servers and agent skills by name, description, category or topic — 4 results.
get-tmonier/argot
Guardrail that checks agent-written code against a repo's own git-history-learned patterns — flags foreign dependencies, reinvented functions, misplaced code, broken layering, and gamed tests. Exposes `voice_context` (the repo's familiar imports/idioms for a file, so agents write in-voice before generating), `check` (score a generated hunk against the repo's patterns), and `explain`. 100% local, n
taniwhaai/arai
Policy enforcement for AI coding agents derived from existing instruction files (CLAUDE.md, .cursorrules, .windsurfrules, .github/copilot-instructions.md) — no separate YAML to maintain. Rules with prohibitive predicates (`never`, `forbids`, `must_not`) emit `permissionDecision: deny` to block tool calls in Claude Code; advisory rules inject context. PostToolUse is correlated with PreToolUse to pr
AperionAI/shield
Local guardrail proxy for AI coding agents. Wraps any MCP server (stdio or Streamable HTTP) and blocks destructive tool calls — DROP TABLE, rm -rf, force-push — before they execute. MCP supply-chain protection: TOFU tool-catalog pinning against rug pulls, plus tool-description and tool-result scanning for tool poisoning and prompt injection. 51 starter rules, approval gates, audit logging. Single
kiro0x/five-mcp
LLM character consistency engine — generates structured JSON constraints from 4 multiple-choice questions about an AI's psychology. Drop the JSON into any LLM's system prompt to prevent persona drift; reduces inference cost from retries. 160,000 personality patterns; works with any LLM.