Search

Scoped, time-bound, cryptographically-signed capabilities for AI agents. Zero dependencies. Sovereign by design.

Ethics-aware OSINT investigation planning, collection, and risk evaluation, delivered as an MCP server. Classification, risk tiers, hard stops, and defensible documentation — driven by local YAML doctrine.

Kali 原生的 LLM 渗透测试 harness:大模型自主驱动 Kali 完整工具链,scope 护栏 + 持久 PTY + 哈希链审计。Python,GPL-3.0。

Deterministic execution authorization engine for AI agents. Enforces economic and operational constraints before tool execution.

Bug bounty agent framework for Claude Code, Codex, Gemini, Cursor, Windsurf, Copilot, and OpenClaw — 48 agents, 26 commands, 19 CLI tools, 2 MCP servers, autonomous hunt loops, exploit chain builder.

A TypeScript framework for agents, typed tools and durable workflows.

AI-assisted phishing investigation tool built with Python, Playwright, OpenRouter, and SQLite.

Core of the AgiMate agent platform: per-agent access to connectors and tools, credentials that never reach the model, every call checked before it leaves and logged after

BINNY: an open source agent harness for reverse engineering. Plug in any model, or a local one.

Standards coverage for any agent on any stack. Python twin of @connexum/agent-standards; one catalogue JSON, one conformance suite.

Processing raw multilingual drafts into structured, readable versions for diverse audiences using defined editorial principles.

Zero-dependency runtime governance for any Node AI agent — gate tool calls through MetaMynd/AgentSafe (allow / block / escalate) against the agent's mandate, enforced Standards, and SOPs. Ed25519-signed, deterministic, fail-closed.

EvalGuard SDK — canonical alias for evalguardai. The independent AI platform for teams shipping LLM agents.

Mercado Pago Subscriptions as drop-in tools for the Vercel AI SDK. Argentine-focused, agent-ready.

Open-source Python framework to build, orchestrate and deploy AI agents: multi-provider, tool calling, RAG memory and desktop distribution.

Runtime governance for tool-using AI agents in Java — budget enforcement, tool authorization, human approval, and loop brakes.

AI 助手的模組化能力框架：記憶、防禦、診斷、品質穩定 | Modular capability framework for AI assistants | Claude Code / Cursor / Any LLM

Runtime defense against temporal backdoors in tool-using agentic LLMs

Agentic platform for physics lecture workflows with backend services and supporting client application.

Safety-gated multi-agent framework for authorized cyber operations and penetration testing