Search

AI model: AI45Research/AgentDoG1.5-Qwen3.5-0.8B (text-classification)

Human-in-the-loop pentest & OSINT CLI assistant

AI model: mradermacher/AgentDoG-Qwen2.5-7B-i1-GGUF

HackerAI — Your AI cybersecurity arsenal. Autonomous agent with 20+ free AI models, multi-provider rotation, and zero rate limits.

AI model: AI45Research/AgentDoG1.5-FG-Llama-3.1-8B (text-classification)

AI model: AI45Research/AgentDoG1.5-FG-Qwen3.5-2B (text-classification)

Unified LLM API with automatic model discovery and provider configuration

Transparent MCP proxy for agent observability. Logs every tool call, exposes trace history, reduces token overhead.

OpenClaw 安全客户端 - Hook 注入/执行前审批/基线扫描

LangChain middleware for the EISFI Weaver integrity chain: a tool call whose integrity precondition fails is never executed.

Agent-Based Infrastructure Core - Runtime and CLI

Static SQL safety analysis for AI agents — catch dangerous queries before they reach your database.

Deterministic governance hook for CAMEL-AI multi-agent systems — policy enforcement, PII detection, cost tracking, kill switch, and structured audit evidence. No LLM in the governance path.

Official Python SDK for the Execlave AI Governance Platform — tracing, policy enforcement, and framework auto-instrumentation for LangChain, OpenAI Agents SDK, and CrewAI

Official Python SDK for Auth Agent - OAuth 2.1 authentication for websites and AI agents. Includes client SDK for Python backends (Flask/FastAPI) and agent SDK for browser automation with browser-use integration.

Zero-trust, E2EE task delegation protocol & MCP server for cross-owner AI agents (Ed25519 DID, X25519+AES-256-GCM Blind Relay, Capability Tokens, Sandboxed Worker)

An unofficial, cross-platform setup kit for OpenAI Codex CLI and Anthropic Claude Code: specialist agents, curated skills, safe MCP defaults, preview-first installation, and clear verification.

AI model: Denisijcu/vertex-gemma-2b-mcp-gguf

Runtime policy enforcement for LLM agent tool calls on Kubernetes.

A 3-stage safety guardrail agent for LLM coding assistants (Claude Desktop, Cursor, CodeX) via MCP protocol.