Fast, Multi-Cloud Sandbox Engine for AI Agents
Agent Sandbox is an open-source sandbox engine for AI agents. It is purpose-built for three classes of workload:
- Lightning Fast — pre-warmed pools keep isolated environments on standby, eliminating cold-start latency for high-frequency agent loops, evaluations, and RL rollouts
- Enterprise Grade — deploy on any cloud using native Kubernetes CRDs, RBAC, and multi-cluster routing, without vendor lock-in
- Agentic RL — stateful environments with deterministic resets and any-image runtimes, built for complex multi-turn agent training
| Feature | Description | |
|---|---|---|
| ⚡ | Speed — Sub-60ms allocation | Pre-warmed pools deliver idle sandboxes instantly, unblocking high-volume agent loops and multi-turn RL rollouts |
| ☸️ | Infrastructure — Containers or microVMs | Run on your existing estate using CRDs, namespaces, RBAC, and autoscaling to manage warm capacity efficiently |
| 🌐 | Routing — Cross-region and cross-cloud | Dispatch requests across clouds, clusters, and regions without forcing application teams to manage routing logic |
| 🧪 | Runtime — Zero-rebuild runtimes | Run any Docker image for SWE tasks, RL environments, and internal tools without building custom VM images |
| 🔌 | Ecosystem — Drop-in agent SDKs | Seamless compatibility with E2B clients, SWE-ReX workflows, and popular reinforcement learning frameworks |
| 📊 | Observability — Console-grade visibility | Complete view of pools, active sessions, logs, and metrics through a unified product console |
RL training requires thousands of environment resets per hour. Agent Sandbox pre-warms a pool of sandboxes so each rollout worker gets a fresh, isolated environment in milliseconds — removing the environment-reset bottleneck from your training loop. Supports SWE-bench Verified, SWE-Gym, Terminal-bench, and custom task distributions.
Give every agent turn or eval call its own isolated execution environment. The E2B-compatible API means existing SWE-agent, SWE-ReX, and similar frameworks work without modification.
Deploy sandbox pools across multiple clouds or regions. The built-in ExtProc routing layer dispatches requests to the most available cluster transparently — no routing logic required in application code. Supported cloud providers: AWS, Google Cloud, Azure, Alibaba Cloud, Volcengine, Cloudflare.
Coming soon: microVM-backed sandboxes for stronger isolation guarantees.
| Resource | Link |
|---|---|
| Documentation site | scitix.github.io/Agent-Sandbox |
| API Reference (OpenAPI) | /docs/api/sandboxes/CreateSandbox |
| Installation guide | /docs/installation |
| Integrations | /docs/integrations |
| Changelog | /docs/changelog |
Contributions are welcome — bug reports, feature requests, documentation, and code. Please read CONTRIBUTING.md before submitting a pull request.
All commits must include a Signed-off-by line (DCO). Use git commit -s.
Apache License 2.0 — see LICENSE for details.
Copyright © 2026 ScitiX.