AgentENV: Distributed Runtime for AI Agents at Scale (Open Source, Rust)
AgentENV (AENV) is a Rust-based distributed platform for running AI agent environments at scale, now powering Kimi K3's agentic RL training. Why It Matters: Most agent frameworks are single-process toys. AENV makes agen
AgentENV (AENV) is a Rust-based distributed platform for running AI agent environments at scale, now powering Kimi K3's agentic RL training.
Why It Matters: Most agent frameworks are single-process toys. AENV makes agents distributed with Firecracker micro-VMs:
- 50ms cold start โ snapshot environments boot or resume in <50ms
- Incremental snapshot/fork <100ms โ fork a running environment into independent sandboxes
- Overlaybd OCI images โ no pre-pulling, cluster-wide cache, images can exceed disk capacity
- ublk I/O โ host page cache sharing across storage and filesystem, high density
- S3 persistence โ snapshots persist to S3-compatible storage
Quick Start:
git clone https://github.com/kvcache-ai/AgentENV
cd AgentENV && cargo build --release
./target/release/agentenv --node-id node1
vs Alternatives:
| AENV | Ray | Kubernetes | |
|---|---|---|---|
| Isolation | micro-VM | process | pod |
| Cold start | 50ms | ~1s | ~1s+ |
| Snapshot/fork | โ <100ms | โ | โ |
| Agent-native | โ | โ | โ |
Stars: 1411 ยท Language: Rust ยท License: MIT
๐ฐ Read the original article on Dev.to AI
Originally published by Dev.to AI. Aggregated on AIWithGhost for educational purposes โ full credit and traffic to the original publisher.