guardrails

Stop That Shit（别再造史了）｜面向 Codex/GPT 场景的多平台 Hook + Skill Guard：拦截 AI coding agent 无需求的哈希、校验和与任务范围膨胀。 A multi-platform Hook + Skill Guard for AI coding agents in Codex/GPT workflows: stop unrequested hashes, checksums, and task-scope creep.

Real-time guardrail that shows token spend & kills runaway LLM/agent loops.

Composable data security plane for Model Context Protocol. Pluggable layers — collect, analyze, guard — across 50+ enterprise providers. Open architecture.

Architecture guardrails for AI coding agents building backend services with DDD and Hexagonal Architecture.

The open-source agent firewall. Prevent AI agents from leaking data, using dangerous tools, and importing poisoned dependencies.

ThumbGate Pre-Action Checks self-improve from ranked lessons and repeated failures, hard-block detected secret leaks, and block matches in strict mode.

DSH 小说锻炉：把 AI 长篇写作通病变成代码强制的硬约束（事实账本/上下文包/阶段门禁/零费用去AI味扫描/确定性审计/提案制修订）。Novel-writing guardrails plugin for DeepSeek Harness (DSH).

A governance layer for Claude Code sessions: hooks that check an agent's commands before they run, a spec-first workflow, and project memory the next session reads.

spec-builder + harness-bootstrap. Specs both you and the AI understand. An agent team tailored to your repo, derived from your contract and your code, not a kit that installs everything. Guardrails that block, not advise.

Leave your coding agent alone with your repo. Come back to a reviewed pull request, not a mess.

🧠 Essential guardrails to prevent AI from going sideways in development projects

How a non-coder builds real software with Claude Code: governance, guardrails, and session rituals - not code reading.

AI writes. SPARDA proves. A deterministic, offline gate that catches when an AI edit removes a guard, exposes a route, or breaks an invariant — no API key, right in the agent edit loop.

Give an AI agent a real Solana wallet without giving it your money. The agent gets a spending allowance the SPL Token program enforces on-chain, plus guardrails (per-tx cap, daily cap, recipient and host allowlists, expiry, kill switch), x402 payments, and a one-call on-chain deploy. Custody never leaves your wallet: you can revoke or withdraw at a

CI guard tests for multi-tenant isolation: zero-dependency static guards + a runtime RLS proof that proves one tenant can't read OR write another's rows — SELECT, UPDATE/DELETE, tenant-hop, and INSERT.

Behavior discipline for coding agents: read-before-write enforcement, failure convergence, write verification with auto-rollback, and a high-risk command gate. Ships FULL plugin/hook adapters for DSH, Claude Code, Codex, and Pi, plus a host-agnostic SOFT skill with ADAPTIVE adapter guidance.

Automated LLM red-teaming system with 4 AI agents

Forge rough ideas into drift-proof execution contracts for AI coding agents. 6-step pipeline, 16 agents, 8 skills, lifecycle hooks, 5 tech presets.

A one-file door-guard for coding agents — first-class on Claude Code (permissionDecision deny); portable to any agent with a blocking pre-exec hook.

CORD — Constitutional AI safety engine for autonomous agents. Hard blocks, risk scoring, real-time audit. 482 tests.