Search

DeepKeep AI Firewall tools for CrewAI agents — check inputs, create conversations, and call the DeepKeep API.

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

Nexus-LLM is a ai model which can run locally on your device.

🚀 An Model Context Protocol (MCP) server for Fleet. Query OSQuery data, check compliance, and investigate CVEs natively from Claude, Cursor, and any MCP-compatible AI agent.

Runtime governance for AI agents. Conduct Guard as a NeMo Guardrails plugin — enforce runtime policy on every Colang flow and LLM call.

Open-source AI verification infrastructure for deterministic verification of LLM outputs, tool calls, code, schemas, and agent state before production execution.

A service dependency injection, configuration and logging library.

AI Space: Agents-MCP-Hackathon/ExposureGPT

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

Portfolio técnico de Eugenio Santiago — arquitetura de agentes AI: multi-agent systems, MCP servers, n8n workflows. Berlin.

AI behavior governance for Claude Code — 55+ guards, input rewriting, LLM-as-Judge, A2A safety agent, zero-dep core

Permits and signed receipts for agent tool calls. One dispatch, one charge, verifiable offline.

Deception at the Registry Layer: detecting autonomous AI agents in MCP environments (working paper)

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

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.

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

A highly efficient, collaborative agentic coding framework using Model Context Protocol (MCP) to divide work between planning, code graph analysis, and execution.

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

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

Process-local budget authorization and replay-aware execution disposition for Python AI-agent tools.