AgentENV: A platform for running agent env at scale (Kimi K3 RL) AgentENV (AENV), a platform for running agent environments at scale powering agentic RL training for Kimi K3, launches with support for snapshot-backed environments that boot or resume in under 50 ms and pause in under 100 ms, incremental snapshots completing in under 100 ms, and an E2B-compatible HTTP API. The platform runs on Linux kernel 6.8+ and Ubuntu 24.04, using Firecracker microVMs with overlaybd for on-demand image loading and memory ballooning for high overcommit. Running agent environments at scale AgentENV AENV is a platform for running agent environments at scale, powering agentic RL training for Kimi K3 . Scale across diverse environments : AENV runs massive numbers of Firecracker environments across machines and diverse OCI-compatible images, loaded on demand via overlaybd. Local disk acts as a bounded cache, retaining hot data and evicting cold, so images can exceed disk capacity while startup stays fast cluster-wide, without pre-warming every host. Make idle environments inexpensive : Snapshot-backed environments boot or resume in under 50 ms and pause in under 100 ms. Idle environments can quickly release CPU and memory, then return when new work arrives. Native snapshot and fork support : AENV snapshots memory and filesystem changes incrementally, completing in under 100 ms even under heavy disk modification. A running environment can fork into multiple independent sandboxes for parallel agent workflows. Snapshots persist to S3-compatible object storage or a shared distributed filesystem to prevent data loss. Preserve performance and density over time : AENV delivers high-performance I/O via ublk while sharing the host page cache across storage and memory-snapshot data. Memory ballooning returns reclaimable guest memory to the host, sustaining high overcommit as environments run longer and diverge. Linux kernel 6.8+ ; the install script additionally requires Ubuntu 24.04 see Quick Start below for installation options /dev/kvm access for Firecracker microVM execution 1. Install and start the server Option A — install script Ubuntu 24.04 Install both the server and the aenv CLI, then start the server as a systemd service: curl -fsSL https://raw.githubusercontent.com/kvcache-ai/AgentENV/main/scripts/install.sh | sudo bash sudo systemctl start aenv Option B — Docker Set up the server: curl -fsSL https://raw.githubusercontent.com/kvcache-ai/AgentENV/main/scripts/docker-setup.sh | sudo bash docker pull ghcr.io/kvcache-ai/aenv-server:latest docker run -d --privileged -v /dev:/dev -p 8000:8000 ghcr.io/kvcache-ai/aenv-server:latest The server is accessible at http://127.0.0.1:8000 by default. 2. Install the aenv CLI skip if you used Option A in step 1 Install separately if you used the Docker method above, or if you are running the CLI on a different machine from the server. Supports Linux and macOS on x86 64 and arm64: curl -fsSL https://raw.githubusercontent.com/kvcache-ai/AgentENV/main/scripts/install-cli.sh | bash 3. Authenticate aenv auth AENV server URL http://localhost:8000 : http://127.0.0.1:8000 API key: dummy 4. Pull a template and run a sandbox aenv pull ubuntu:22.04 --name ubuntu aenv start ubuntu starts a sandbox and attaches an interactive shell For Docker Compose / Kubernetes cluster deployment and build-from-source instructions, see 📖 Deployment https://kvcache-ai.github.io/AgentENV/deployment/manual-compile.html . AgentENV exposes an E2B-compatible HTTP API. Point E2B API URL at your server and use the standard E2B Python / TypeScript SDK without any code changes. See 📖 E2B integration https://kvcache-ai.github.io/AgentENV/integration/e2b.html for setup details. Templates aenv pull docker.io/library/ubuntu:latest --name ubuntu FROM