Search

Control Android devices through ADB with this Python automation framework for task execution and phone farm scaling.

Runtime approval gates for AI agent tool calls. Intercept payments and emails before execution

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.

Production-ready AI dev workflow scaffold with 59 skills, 33 agents, hooks, and rules for Claude Code, Codex, Gemini CLI, Copilot CLI, Qwen Code, and OpenCode.

Python SDK for Torrix, self-hosted observability for AI agents: record OpenAI and Anthropic calls with no dependencies.

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.

Scaffold a MetaMynd/AgentSafe-governed AI agent in one command — logs in, provisions the agent (identity + mandate + SOP + Standards) in a single call, writes agent.metamynd.json plus a runnable agent + separate tool-gateway process (the real enforcement

Agentic agriculture platform for farm operations, advisory workflows, and authenticated application services.

AI model: alirezaaminzadeh/soc-analyst-tool-use

Thin AutoGen adapter for the OxDeAI universal execution guard

Claude Code plugin: universal radial-tree exploration engine. One tree skill + swappable presets (brainstorm / attack / design / code-audit) for divergent ideation, adversarial critique, and design-space exploration. 12 framings × hard-ban-on-incomplete-leaves × stable convergence.

D1337 CIPHER-OSC V3 — Elite AI Agent Framework. 106+ components. Hooks, subagents, custom commands. Underground mindset, brutal execution, sovereign protocol.

Claude Code session capture and analysis. Trace tool calls, detect backtracks, analyze decisions, track edit chains, and measure plan drift. Local-first, zero-dependency observability.

OpenAI gym reinforcement learning environment wrapper for CybORG

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

The agentic code editor with its own AI inside. Built on Pi and Gentle AI, with Engram memory, MCP servers and any provider you bring. Free and open source.

CLI/MCP agent surface for Enji Guard

Nominee adapter for the Vercel AI SDK — fresh tokens and human-in-the-loop approval for AI SDK tools

This repository represents the transition from behavioral safety to Neural Forensics. It provides the infrastructure to detect, audit, and mitigate high-order AI risks—such as Latent Deception, Sycophancy-Masking, and Synthetic Intimacy—directly at the mechanistic activation layer.

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