# AgentEnv Framework

> Scale AI's open-source Python SDK and CLI for building, deploying and scoring containerized agent environments and tasks for RL and evals.

- id: `agentenv-framework`
- category: Evals & Observability (`evals-observability`)
- url: https://www.agentenvframework.com
- repo: https://github.com/scaleapi/agentenv-framework
- docs: https://www.agentenvframework.com/docs
- status: active
- pricing: open-source
- license: Apache-2.0
- tags: evals, rl-environments, sandbox, benchmarks, python
- related: Harbor (https://indexagentica.com/entries/harbor/); Modal (https://indexagentica.com/entries/modal/); E2B (https://indexagentica.com/entries/e2b/); Agent2Agent Protocol (A2A) (https://indexagentica.com/entries/a2a-protocol/)
- sources: https://github.com/scaleapi/agentenv-framework , https://labs.scale.com/blog/introducing-agentenv , https://pypi.org/project/agentenv-framework/
- added: 2026-10-27
- updated: 2026-10-27
- last verified: 2026-10-27
- featured in: Agent environment frameworks compared: Harbor vs AgentEnv Framework vs Seahaven (https://indexagentica.com/compare/agent-environment-frameworks/)
- maintainer: Scale AI
- submitted by: agentica-curator
- page: https://indexagentica.com/entries/agentenv-framework/
- json: https://indexagentica.com/api/entries/agentenv-framework.json

Environments are containerized servers speaking the open `agentenv-framework-protocol`; the framework builds them into versioned images, deploys them behind a gateway, points an agent at them over MCP, REST or a generated CLI, and grades what the agent did. Agents are described by A2A Agent Cards, so the same task runs against Claude Code, OpenAI agents or custom agents. Sandboxes: local Docker, Modal containers, and Modal and E2B VMs, plus custom providers via plugins; optional AWS/GCP store backends and an OpenEnv extra. Try it with `uvx --from agentenv-framework agent-env run hello`. Requires Python 3.11.4+; PyPI `agentenv-framework` 0.9.1364. Scale says every RL environment it builds runs on AgentEnv.