AgentEnv

Uh oh!

There was an error while loading. Please reload this page.

Notifications You must be signed in to change notification settings

Fork 92

Star 1.1k

BranchesTags

Open more actions menu

Folders and files

NameName

Last commit message

Last commit date

Latest commit

History

13 Commits

13 Commits

.cargo

.cargo

.github

.github

.vscode

.vscode

adev

adev

assets

assets

benches

benches

config

config

crates

crates

deploy

deploy

docs

docs

scripts

scripts

services

services

src

src

storage

storage

tests

tests

thirdparty

thirdparty

tools-image

tools-image

.dockerignore

.dockerignore

.gitignore

.gitignore

AGENTS.md

AGENTS.md

CLAUDE.md

CLAUDE.md

Cargo.lock

Cargo.lock

Cargo.toml

Cargo.toml

LICENSE

LICENSE

Makefile

Makefile

README.md

README.md

build.rs

build.rs

cliff.toml

cliff.toml

openapitools.json

openapitools.json

rust-toolchain.toml

rust-toolchain.toml

Repository files navigation

📖 Full documentation

AgentENV (AENV) is a platform for running agent environments at scale, powering agentic RL training for Kimi K3.

🚀 Why AgentENV

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.

📋 Prerequisites

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

⚡ Quick Start (Single Node)

Warning

AgentENV currently does not support authorization. Do not expose the AgentENV API to the public network. Run it only on a trusted network or behind an authorization proxy with appropriate network controls.

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.

1. 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

1. Authenticate

aenv auth

AENV server URL [http://localhost:8000]: http://127.0.0.1:8000

API key: dummy

1. 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

🗂 Deployment

For Docker Compose / Kubernetes cluster deployment and build-from-source instructions, see 📖 Deployment.

🔌 E2B compatibility

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 for setup details.

🛠 aenv CLI reference

Templates

aenv pull docker.io/library/ubuntu:latest --name ubuntu # FROM → template aenv template list # alias: aenv template ls

Sandboxes

aenv start ubuntu # start + attach interactive shell aenv start ubuntu --detach # start, print sandbox ID, don't attach aenv cn # reattach a shell aenv exec ls -la / # one-shot command aenv ls

aenv pause aenv resume aenv timeout 600 # extend TTL to 600 s from now aenv delete # alias: aenv rm

aenv start accepts a template UUID or human-readable name/alias. aenv list outputs a table on TTY and JSON when piped; override with --output table|json.

MIT license

Activity

Custom properties

Stars

1.1k stars

Watchers

4 watching

Forks

92 forks

Report repository