Search

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

Cryptographic identity, trust chains, and E2E encrypted messaging for AI agents

The Two-Layer Agent Contract: guidance influences candidate behaviour, runtime policy enforces executable authority. Reference implementation for 'Intent Is Not Policy' talk.

Self-hostable TOTP MCP server for AI agents. Generate 2FA codes without exposing seeds.

A firewall that blocks dangerous AI requests before they execute

CLI/MCP agent surface for Enji Guard

Reeflex — deterministic governance gate for AI-agent actions, the /v1/decide decision engine. Name reservation; code at github.com/Reeflex-io/reeflex

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

🛡️ Local-first AI gateway in Go — zero-dependency single binary, WAF on by default. 13 clients × 35 providers, OpenAI-compatible HTTP/stdio. MIT.

本地 AI Agent 工具治理网关：不防提示词注入发生，防注入得逞后的高危工具调用后果（policy / approval / audit / MCP 双向治理）

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

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

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

KYA — Know Your Agents. Trust + governance + risk scoring for any autonomous system (LLM agent, lakehouse job, AutoML pipeline, RPA bot).

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.

Aios — Artificially Intelligent Operating System. An AI-native operating environment where no component both decides and executes.

AgentPlugged: a method of AI agents for solo developers and small startups

No-code AI agent builder — turn one sentence into a single agent or a multi-agent team. The engine inside Agentlas. A no-code CrewAI / LangGraph / AutoGen alternative that runs on Claude Code, Codex, and Cursor.

Agentic Control Plane for fx (vercel-labs/fx) — a governed protocol middleware for fx's Agent Client Protocol mode, checking every tool call against your policies before fx's own permission prompt reaches the client.

MCP_HACK//26 — Industrial Zero-Trust AI: T-IA Connect + AgentGateway for Siemens TIA Portal