An embeddable, portable, branchable virtual machine to safely run Agents locally.
Sub-millisecond VM sandboxes for AI agents via copy-on-write forking
Rootless container runtime with no daemon. Runs agent tool calls and LLM-generated code in kernel-enforced containers.
Secure runtime to sandbox AI agent tasks. Run untrusted code in isolated WebAssembly environments.
TypeScript interpreter for AI agents. Written in Rust. 2µs cold start. Sandboxed. Alternative to MCP tool calling.
Lightweight, secure Linux sandboxes for untrusted processes. Runs in the browser and on the server.
Manage secure microVMs — one command from zero to secure sessions, locally and remotely.
Secure sandboxing system for untrusted code execution
Execute agent-generated TypeScript in isolated WebAssembly, with runtime-enforced semantic permissions.
Bare-metal microVM execution engine in Rust. Sub-5ms snapshot restores, Zero-NIC network isolation, and 30 built-in language toolchains for AI code sandboxes & online judges.
Sandboxed code execution for LLMs, powered by Nix
Arbor — The Agentic RL Sandbox. Checkpoint-native. Branch-safe. Self-hosted.
Rootless sandbox that judges untrusted code by counting CPU instructions instead of seconds — same verdict on a busy machine as on an idle one.
Run short-lived Python, Node, and Bash with hard limits, live output, and verifiable receipts.
Lightweight embeddable sandbox for running untrusted code, built on OS-native isolation (namespaces, cgroups, seccomp, Landlock, Seatbelt). No containers, no VMs.
Yet another code execution engine written in Rust.
Arbitrary code execution server using Docker.
A high-performance, code execution engine written in Rust. Useful for on-demand, safe code evaluation for Judge platforms like leetcode, CTF sites.
A telegram bot to execute code, written in Rust. Leverages
To associate your repository with the code-execution topic, visit your repo's landing page and select "manage topics."