AgentENV is a distributed platform for running large numbers of isolated AI-agent environments across one or more machines. It uses Firecracker microVMs to provide strong sandboxing while loading diverse OCI-compatible images on demand. Overlay-based storage and bounded local caching keep frequently used data close without requiring every image to fit on each host. Snapshot-backed sandboxes can pause, resume, fork, and persist memory and filesystem changes for parallel or recoverable workflows. The platform includes an aenv command-line interface for creating templates, starting shells, executing commands, and managing sandbox lifecycles. Its E2B-compatible HTTP API lets existing Python and TypeScript integrations target a self-hosted deployment with minimal changes. AgentENV is designed for high-density agentic reinforcement learning and currently requires trusted-network deployment because built-in authorization is not yet available.

Features

  • Firecracker microVM isolation
  • Distributed multi-host environment orchestration
  • On-demand OCI image loading
  • Fast pause, resume, snapshot, and fork operations
  • E2B-compatible HTTP API
  • Command-line sandbox lifecycle management

Project Samples

Project Activity

See All Activity >

Categories

AI Agents

License

MIT License

Follow AgentENV

AgentENV Web Site

Other Useful Business Software
Save Up to 91% on Cloud Compute With Spot VMs Icon
Save Up to 91% on Cloud Compute With Spot VMs

Automatic sustained-use discounts. One free VM per month. No negotiation needed.

Run batch jobs at 60-91% off with Spot VMs. Long-running workloads get automatic discounts with sustained use.
Start Free
Rate This Project
Login To Rate This Project

User Reviews

Be the first to post a review of AgentENV!

Additional Project Details

Operating Systems

Linux

Programming Language

Rust

Related Categories

Rust AI Agents

Registered

2026-07-29