排序 相关度 时间
共 12 条 · 0.096 秒
82搜索为您找到约 12 条结果
www.agentsh.org 网页 综合
Features - agentsh
Execution-layer capabilities of agentsh — traffic control, data protection, deterministic enforcement, and operational tools. Most systems can deny an action. agentsh can also steer it to an…
2026-11-14 自动蜘蛛 相关度 63.9
www.agentsh.org 网页 综合
Getting Started - agentsh
agentsh ("agent shell") provides execution-layer security for AI agents. Intercept file, network, process, and Postgres-family database activity at runtime—enforce policy, emit audit events,…
2026-11-14 自动蜘蛛 相关度 60.1
www.agentsh.org 网页 综合
Database Proxy - agentsh
agentsh provides database-aware enforcement for Postgres-family traffic. Declare protected upstreams with db_services, route governed processes through the per-session proxy, and apply conne…
2026-11-14 自动蜘蛛 相关度 60.1
www.agentsh.org 网页 综合
Setup & Integration - agentsh
Platform support, container setup, and integrating agentsh execution-layer security with your development environment. agentsh supports Linux, macOS, and Windows with varying levels of enfor…
2026-11-14 自动蜘蛛 相关度 58.2
www.agentsh.org 网页 综合
Agent Shell for AI Agents | agentsh
agentsh, pronounced agent shell, is an execution-layer security gateway for AI agents. It wraps an agent process, intercepts file, network, and process activity at runtime, and enforces dete…
2026-11-14 自动蜘蛛 相关度 56.0
www.agentsh.org 网页 综合
Glossary - agentsh
…t governs Postgres-family database traffic for declared services. agentsh routes governed processes through a per-session Unix socket, authenticates the connecting process with Linux peer cr…
2026-11-14 自动蜘蛛 相关度 54.2
www.agentsh.org 网页 综合
Examples & Integrations — agentsh
Working examples of agentsh securing AI agent sandboxes. Each repo is a complete, runnable project — clone it and go. Each integration shows the same execution-layer pattern in a different r…
2026-11-14 自动蜘蛛 相关度 53.4
www.agentsh.org 网页 综合
agentsh | Agent Shell Security for AI Agents
agentsh ("agent shell") is a policy-enforced execution gateway that intercepts file, network, and process activity at runtime—no matter what the prompt, tool output, or user says. Models are…
2026-11-14 自动蜘蛛 相关度 53.0
www.canyonroad.ai 网页 综合
Canyon Road — Execution-Layer Security for AI Workloads
…. One control plane. Local enforcement. Developer? Go straight to agentsh.org → How it works · What is Execution-Layer Security? Copilots and desktop tools run with employee credentials.Beac…
2026-11-14 自动蜘蛛 相关度 16.5
www.canyonroad.ai 网页 综合
How It Works — Canyon Road
…s, one architecture: local enforcement powered by central policy. agentsh wraps AI agents for runtime enforcement. Beacon monitors AI desktop apps at the OS level. Watchtower manages both fr…
2026-11-14 自动蜘蛛 相关度 15.9
第 1 / 2 页