Guardian

AgentGuard is a web-based scanner for AI-agent Skills, including SKILL.md instructions. It combines deterministic pattern checks with AI-assisted analysis to identify capabilities and risks such as shell-command execution, file-system access, environment-variable and credential access, network requests, external downloads, suspicious URLs, obfuscated instructions, prompt-injection patterns, and destructive operations. It produces a trust report with security and quality scores, a risk rating, detected capabilities, findings, explanations, and recommendations. The scanner is free to use, requires no account, accepts up to 80,000 characters of Skill text, and is designed for analysis before installation.

Agent S is an open-source computer-use agent framework from Simular. It accepts natural-language tasks, observes a real desktop through screen and accessibility signals, and operates ordinary applications by clicking, typing, scrolling, and executing optional local code rather than relying on per-application APIs or scripts. The project has progressed through three generations: accessibility-tree grounding with an LLM, a vision-based manager-worker architecture using multiple foundation models, and Agent S3, which scales computer-use attempts through parallel rollouts and selection. Its workflow can combine model-driven exploration with reusable automation code, replay saved skills, and recover when the interface changes. The framework supports macOS, Windows, and Linux, works with models from OpenAI, Anthropic, Gemini, OpenRouter, vLLM, and open-weight providers, and is distributed through the `gui-agents` Python package. An optional local coding environment can execute Python and Bash with the current user's permissions, so the repository warns that this capability should be used only in trusted environments.

OpenBot is an open-source AI agent platform from CopilotKit that gives each agent its own computer with a browser, logins, files, tools, and a dedicated interaction channel. It runs in the user's infrastructure and accepts agents that speak the AG-UI protocol, including agents built with LangGraph, Mastra, CrewAI, Pydantic AI, Google ADK, or custom code. A single gateway mediates actions involving the computer, files, MCP servers, and UI components: it decides whether an action is permitted before execution and records it afterward. Agents can operate their own browser screen, hand control to a human for restricted actions, and return component-based responses. Docker Compose runs the application components and PostgreSQL, while the administrator supplies the model credentials; the repository describes the project as alpha software under active development.

An open-weight AI safety guardrail for security operations centers (SOCs), designed to be independently deployed rather than used solely through a hosted service. Its specific detection inputs and supported deployment integrations are not established here.

The Agent Accountability Framework is an open governance framework for making AI agents accountable when they hold authority in production. Published and funded by Gravitee, it defines six principles organized around three stages: Assignment establishes an agent's identity, team, and named human sponsor; Alignment defines its role, mission, measurable boundaries, and least-privilege authority; and Administration provides oversight scorecards, guardian agents, and step-by-step recourse when an agent goes off course. The framework is published free for anyone to use, with a concept paper and an invitation for contributors.