Search

Universal TIBET provenance for ANY Python code. @tibet_guard decorator, ASGI middleware, agent safety. OWASP LLM06 compliant.

Let Claude Code and other MCP agents work on your own computers and servers with your approval: the agent asks your Host, you approve with a passkey, and a bastion on each machine checks every request. Free and self-hosted; runs on Windows, macOS and Linux.

TypeScript client for plimsolld, with Trigger.dev and Mastra executeCode add-ons

CrewAI adapter for Sentinel AI agent governance — wrap any CrewAI tool so every call is authorized (and audited) by the Sentinel gateway before it runs. Private beta: [email protected]

A dashcam for your AI agents: local, tamper-evident recorder for process/file/network activity, with a LangChain/LangGraph drop-in prompt-injection circuit breaker.

A guardrail system that intercepts and validates AI agent tool calls

Runtime governance for AI agents — deterministic fail-closed enforcement. Wraps any agent tool and blocks dangerous calls before execution. Zero LLM calls, zero cloud dependencies, works offline.

just-bash provider for ComputeSDK - local sandboxed bash execution with virtual filesystem

Deterministic MCP toolkit for autonomous AI agents auditing and optimizing EVM smart contracts

Read-only static scanner for AI-agent codebases: finds dangerous action sinks, proves reachability, attributes guard coverage, and rates findings honestly (reachable-verified vs install-liability).

Run the OpenAI Agents SDK's sandbox commands in local Hyperlight micro-VMs

Local verifier for agentic data handoffs: envelope, provenance, trust, authority, identity, capability, and audit checks.

AegisAuth CLI - Trust Layer for AI Agents with Auth0 Token Vault and Multi-Agent Orchestration

AI model: mradermacher/AgentDoG-Qwen3-4B-GGUF

Encrypt .env files with keys stored outside the project, and run commands with automatic secret redaction — so LLM agents and logs never see your keys.

Agent Policy Layer - Portable, composable policies for AI agents

Local-first AI agent framework with 5-layer container hardening. Runs Ollama models offline behind iptables, DNS sinkhole, seccomp, and read-only rootfs. No cloud, no telemetry, no API keys.

GenDD Agentic Governance — multi-agent SDLC governance engine (LangGraph)

Ask your AI coding agent, in natural language, to search production logs or inspect a database — safely. Two drop-in MCP servers (MySQL, SSH logs) keep safety red lines in code: read-only by default, dangerous SQL/shell blocked, production disabled, no stored credentials. A recommended Skill layer teaches the model when and how to use them.

探驪 Tanli - 自主紅隊測試 Agent(LLM + Web 雙軌安全評估)