AI product Open source
AgentENV (AENV) is an open-source distributed platform developed by kvcache-ai for running agent environments at scale, including environments used for agentic reinforcement-learning training such as Kimi K3. It runs Firecracker microVM sandboxes across machines, loads OCI-compatible images on demand through overlaybd, and uses local disks as bounded caches for image and snapshot data. The aggregate image and snapshot footprint can exceed local disk capacity because cold data is evicted from the cache.
Snapshot-backed environments can boot or resume in under 50 ms and pause in under 100 ms. AENV incrementally snapshots memory and filesystem changes, stores snapshots in S3-compatible object storage or a shared distributed filesystem, and can fork a running environment into independent sandboxes for parallel workflows. It uses ublk for I/O and memory ballooning to return reclaimable guest memory to hosts; the documentation reports a 9.6× memory overcommit ratio in production.
The distribution includes an AENV server and the `aenv` command-line client for pulling OCI images as templates, starting, attaching to, executing commands in, pausing, resuming, and deleting sandboxes. It exposes an E2B-compatible HTTP API that works with the standard E2B Python and TypeScript SDKs. It requires Linux kernel 6.8 or later and `/dev/kvm` access for Firecracker execution. API requests are authenticated, but traffic is not encrypted; the documentation recommends a trusted network or HTTPS termination at a reverse proxy or load balancer.
3 uses taken from transcripts — each links to the moment in the video.
A sandbox platform for agentic reinforcement-learning training built on Firecracker microVMs. It rapidly boots, resumes, snapshots, and forks running environments into parallel sandboxes.
Runs large fleets of agent sandboxes as lightweight Firecracker microVMs. It supports on-demand OCI images, incremental snapshots, and branching of running environments for parallel work.
An open-source distributed platform for running agent sandboxes at scale. It runs Firecracker microVMs across machines from OCI images, supports snapshots and forks for parallel agents, and provides an E2B-compatible API and CLI.
3 in the library.