agentcage is an open-source CLI tool that provides a defense-in-depth proxy sandbox for AI agents. Below are 32 other ai apps with similar functionality to agentcage, matched by what each product actually does — not ranked or scored. Explore each to find the closest fit for your use case.
Security harness for AI coding agents (Claude Code, Codex CLI, etc.) — mitmproxy payload inspection + TOML policy control.
agentu is an open-source AI agent runtime designed for developers to run autonomous agents with tool isolation, self-correction, and permission scoping. It provides a CLI interface and is suitable for building secure, extensible AI workflows.
ai-agentguard is an open-source CLI tool that monitors AI coding agents for security threats such as remote code execution, MCP poisoning, and API key theft. It is designed for developers working with AI agent frameworks to enhance security.
agentguardCI is an open-source command-line tool that provides contract testing for tool-using AI agents. It integrates with CI pipelines to automatically evaluate and validate agent behaviors, helping developers ensure reliability and correctness of their AI systems.
CLI tool for deploying and managing AI coding agent configurations (MCP servers, skills, instructions) across multiple providers.
agentcouncil-hub is an open-source universal hub for connecting multiple AI coding agents using a single link and the A2A protocol. It enables seamless integration and coordination of autonomous agents for collaborative coding tasks, supporting MCP and various agent frameworks.
agent-security-harness is an open-source CLI tool that automates security and compliance testing for AI agent systems. It supports MCP and other protocols, providing a comprehensive suite of tests aligned with industry standards for developers and security teams.
agentcloak is an open-source CLI toolkit designed for AI agents, providing capabilities for stealth browsing, web reverse engineering, and automation. It supports both CLI and MCP interfaces, making it ideal for developers building autonomous web agents.
agentcikit is an open-source CLI toolkit that provides CI-grade evidence and safety tools for AI agents, MCP servers, and open-source contribution workflows. It helps developers automate validation and ensure safety in continuous integration environments.
air-agent is an open-source Python framework for building lightweight AI agents with support for OpenAI tool calling, Model Context Protocol (MCP), and parallel subagents. It is designed for developers who want to orchestrate and extend AI agent capabilities efficiently.
aiagenthub-cli is an open-source command-line tool for running and managing AI agents. It supports agent registry, Docker integration, and automation, targeting developers building or orchestrating AI agent workflows.
agentsec-eval is an open-source CLI framework for evaluating the security of AI agents. It provides adversarial test runners, server-side audits, and scoring mechanisms to help researchers and developers identify vulnerabilities such as prompt injection and improve agent robustness.
agentsecure is an open-source CLI tool that provides a local-first security runtime for AI coding agents. It enables developers to securely execute AI agents in sandboxed environments, ensuring safe and controlled code execution.
agent-id-cli is an open-source command-line interface for managing identities of AI agents. It allows developers to create, update, and organize agent identities efficiently. Suitable for AI developers and teams working with multiple agents.
agentpk is an open-source CLI tool that allows developers to package AI agents into portable .agent files, making it easier to distribute and deploy agents across different environments. It is designed for AI developers and researchers who need a standardized way to share agent implementations.
A CLI-driven virtual filesystem for AI agents
agentbench-cli is an open-source command-line tool that allows AI developers and researchers to evaluate, test, and scan the behavior and safety of AI agents. It provides automated checks and reporting for agent performance and compliance.
agentao is an open-source governed agent runtime designed for running AI agents locally with a focus on privacy and embeddability. It supports multimodal agents, integrates with MCP, and is suitable for developers building private, local-first AI solutions.
agentops-cockpit is an open-source, production-grade platform for managing AI agent operations via the command line. It is designed for AI engineers and developers who need robust tools for deploying and monitoring AI agents.
agent-probe-ai is an open-source CLI tool for adversarial resilience testing of AI agents. It evaluates agent robustness against attacks like memory poisoning and tool misuse, helping AI researchers and security engineers identify vulnerabilities.
csage is an open-source CLI tool that leverages AI to assist security professionals in conducting intent-driven security testing and vulnerability scanning. It automates pentesting workflows, making security assessments more efficient and comprehensive for testers and auditors.
agentlint is an open-source CLI tool that provides real-time quality guardrails and linting for AI coding agents. It helps developers maintain code quality and safety by integrating with agentic coding workflows and enforcing best practices.
Multi-agent orchestrator for AI coding tools
agent-audit-kit is an open-source CLI tool that scans MCP-connected AI agent pipelines for security vulnerabilities. It helps AI security engineers ensure the safety and compliance of agent-based workflows.
agent-colosseum is an open-source Python framework for orchestrating and benchmarking multi-agent AI systems. It supports agent debates, red-teaming, and peer review, helping researchers evaluate and improve collaborative AI reasoning.
agent-coordinator is an open-source CLI tool that orchestrates workflows among multiple AI coding agents using a structured handoff protocol. It is tool-agnostic and designed for developers building complex, multi-agent AI systems.
code-sandboxes is an open-source Python package that allows developers to manage and execute AI agent code in isolated sandboxes via the command line. It is designed for AI researchers and developers who need secure and flexible code execution environments.
Deterministic MCP-first browser automation runtime for coding agents
box-agent is an open-source AI agent framework featuring a Jupyter sandbox, data analysis tools, MCP protocol support, and multi-provider LLM integration. It enables developers to build, test, and deploy autonomous agents with advanced capabilities.
A microkernel-style agent framework
agent-container is an open-source tool that enables developers to create always-on, containerized development environments for AI coding agents. It leverages SSH and tmux for remote access and persistent sessions, supporting Docker and Podman. Ideal for developers needing robust, automated agent workspaces.
Agentjail is an open-source security tool designed to enforce policy guardrails for coding agents, with a focus on blocking dangerous tool calls before they are executed. The platform addresses risks associated with AI agents issuing destructive or unauthorized commands, such as deleting sensitive files or force-pushing to production repositories. It is intended for development teams and individuals who utilize coding agents and require deterministic, auditable controls over agent actions. The tool operates by intercepting every tool call from an agent and evaluating it against user-defined policies written in Rego, using a local OPA (Open Policy Agent) daemon. This evaluation happens in under five milliseconds, and if a command matches a blocked pattern or violates a policy, agentjail denies execution before the command reaches the shell. env files, and blocking commands such as rm -rf, curl|bash, sudo, force-push, and others. Additional opt-in library rules are available to further restrict actions like writing to shell initialization files, modifying application binaries, or reading shell history and browser cookies. Agentjail supports granular, tool-level policies for MCP (multi-cloud provider) servers, maintains a full inventory of server configurations, and enforces a default-deny posture. Every decision made by the tool is logged for auditability, and policy enforcement can be customized at global, project, or session levels. The platform also features a live dashboard, full-screen session replay, and automatic daemon updates. Defense-in-depth is provided through a kernel sandbox and network proxy, which can block file and network access if hooks are bypassed. Self-protection measures prevent agents from disabling their own hooks or policy files. Installation is performed via a shell script, and the tool operates offline on the user’s machine. 0 license, with its source code openly available. The service is positioned within the class of policy enforcement and security tools for coding agents, emphasizing deterministic, policy-as-code controls and rapid, local enforcement.
