Audience
Developers, platform teams, agent builders and businesses operating AI agents across providers.
About runx
runx is an open-source runtime and command-line tool for creating, discovering, and executing governed skills for AI agents. Developers can define bounded workflows, grant specific credentials and permissions, and run skills locally with their own provider accounts. Runs can pause for approval or missing input, then resume while retaining a signed receipt that can be inspected and verified. Skills can be installed from a public registry and used with compatible agents such as Claude Code, Cursor, and Codex. An optional hosted service adds managed OAuth connections, scoped grants, API-based run submission and inspection, approval handling, and receipt notarization. The CLI can also operate locally or in a self-hosted environment. runx is intended for developers and platform teams building and operating AI-agent workflows that need explicit authority boundaries and auditable execution.
Other Popular Alternatives & Related Software
Ausca
Ausca provides on-demand infrastructure for AI agents and developers through a public service catalog and API. Offerings include document OCR and analysis, audio and video transcription, bounded remote browser sessions, and temporary receive-only email inboxes. Each service has defined inputs, limits, pricing, and instructions. Developers can connect through HTTP with x402 payment, MCP-compatible tools, command-line utilities, or typed clients. Discovery is available without an account or API key; paid execution requires explicit payment authorization. Services charge per invocation or lease, and completed work can return a verifiable receipt. Ausca is designed for developers and agent operators adding document, media, browser, or inbox functions to automated workflows without deploying those services themselves.
Learn more
Agent Substrate
Agent Substrate is an open-source runtime for operating isolated, stateful agent and code-execution sandboxes on Kubernetes. It coordinates actor and worker lifecycles, places active workloads on a shared pool of ready capacity, and can suspend idle environments while preserving memory and filesystem state for later resumption. Sandboxes use gVisor or Cloud Hypervisor microVM isolation, with per-actor identity and network controls. Agent Substrate is designed for platform and infrastructure teams building agent-hosting services, coding environments, and other workloads that execute untrusted or intermittent tasks. The core project is Kubernetes-portable; Google Cloud also provides GKE-optimized deployment tooling. Optional Filestore agent volumes can persist workspaces across suspend and resume cycles.
Learn more
Sandbox0
Sandbox0 is an Apache-2.0 sandbox runtime for long-running AI agents and services that execute untrusted code. It provides isolated Linux environments with command execution, stateful contexts, file operations, SSH, supervised sessions, and network controls. Sandboxes retain a durable writable RootFS across successful pause-and-resume checkpoints; snapshots, restore, and forks support reusable workspaces. The Python, JavaScript/TypeScript, and Go SDKs, HTTP API, and s0 CLI let applications create and manage sandboxes. Sandbox0 Cloud provides hosted access, while teams can self-host the runtime on dedicated Nomad infrastructure. Default pause preserves filesystem state, not live process memory or external connections; experimental memory recovery requires compatible deployment support.
Learn more
HOL Guard
HOL Guard is a local-first runtime security layer for AI agents that watches what an AI assistant is about to do and stops risky actions before they happen. It sits between the agent and the computer, evaluating supported tool calls and local artifacts for threats such as secret and credential exposure, destructive commands, prompt-injection-driven actions, malicious or changed packages, risky MCP configuration, and unsafe plugins, skills, hooks, and settings. Known threats can be blocked automatically, while ambiguous actions are paused for user approval so people remain in control. Guard runs entirely on the developer’s machine, works offline, and does not upload files, prompts, or passwords. Local checks typically complete in under 50 milliseconds and require no changes to existing code or routines. It supports coding agents including Claude Code, Cursor, Codex, Gemini CLI, OpenCode, Hermes, and OpenClaw, with tailored integrations that inspect actions before execution.
Learn more
Pricing
Starting Price:
$0
Pricing Details:
The open-source CLI and local skill execution are free. Hosted connections, hosted services, and paid skill invocations may incur separate charges. Third-party services and AI providers may charge separately.
Free Version:
Free Version available.
Company Information
0state
Australia
runx.ai
Videos and Screen Captures
Other Useful Business Software
$300 Free Credits to Build on Google Cloud
Put your $300 in credit toward real workloads, then keep building with free monthly usage for 20+ products. No commitment and no charge until you upgrade.
Product Details
Platforms Supported
Cloud
Windows
Mac
Linux
On-Premises
Training
Documentation
Support
Online
