Sprites are full Linux computers designed for agents instead of people. As persistent or disposable as you want, with full environment checkpointing and restore.
Sprites - Stateful sandboxes
Persistent, hardware-isolated execution environments for arbitrary code. Run AI agents, untrusted code, and more in secure sandbox environments with checkpoint & restore.
agentOS — A faster, lighter, cheaper alternative to sandboxes
A portable open-source operating system for agents. Stateful runtime, universal agent interface, and secure code execution. One SDK, deploy anywhere.
agentOS - Everything Agents Need to Run and Operate - Rivet
The complete platform for production AI agents. Stateful runtime, universal agent interface, and secure code execution. One SDK, one platform, deploy anywhere.
Where Should the Agent(s) Live? – OpenComputer
Isolation models, agent placement tradeoffs, credential design, and sandbox lifecycle patterns for agentic systems.
Composable, fast, and secure dev environments | Workshop | Ubuntu
Launch agent-ready, sandboxed development environments with a single command. Define them via simple YAML configs, share them to recreate on different machines.
Computers for agents
Sandboxes aren't enough. Give your agent a real computer and get back to building.
OpenFang — The Agent Operating System
Open-source Agent OS built in Rust. 7 autonomous Hands. 16 security layers. 40 channels. 27 providers. Single binary. Battle-tested.
Cua: Scale computer fleets for computer-use agents
Scale Linux, Windows, macOS, and Android computer fleets for computer-use agents with one open-source MCP/CLI driver.
AgentBox · Free In-Browser AI Agent OS | Strukto
A free, privacy-first in-browser AI agent OS that connects to Google Drive, Dropbox, Slack, GitHub, etc. No server-side data storage.
The Heart of Spritely: Distributed Objects and Capability Security
This paper is the second in a three-part series outlining Spritely's thinking and design. The first paper, Spritely: New Foundations for Networked Communities, explains the problems which face contemporary social network design. This paper details the core technical toolbox provided by Spritely Goblins and how it supplies the necessary features to feasibly build out Spritely's broader vision. The third paper in the series, Spritely for Secure Applications and Communities, ties the first two papers together by showing how the architecture for user-facing software fulfills the vision of the first paper and can be built on top of ideas from this paper.
Agent Plugins
A portable package format for reusable components that extend AI agents.
New capabilities for building agents on the Anthropic API | Claude
Claude now offers code execution, MCP server connections, file storage, and extended prompt caching through the API—giving developers powerful tools to build agents that analyze data, connect to external systems, and maintain context for longer periods of time.
I can haz smoller NixOS ISOs? | natkr's ramblings
In which I painstakingly remove functionality from a Linux live image. Like a normal person.
Your agent needs a computer, not a container — introducing @cloudflare/computer
Agents need more than just a container to scale. We're introducing @cloudflare/computer, an agent runtime that dynamically orchestrates between fast, efficient isolates and full Linux containers to give every agent a computer of its own.
shepherd-agents/shepherd
A runtime substrate that turns an agent's execution into a reversible, Git-like trace, so meta-agents can observe, fork, replay, and revert any run. Couples agent and environments in a copy-on-write fork ~5x faster than docker commit, with ~95% KV-cache reuse on replay. Framework built for meta-agents to supervise, optimize, and train other agents