# AgentGym

> Agent training and evaluation suite exposing diverse interactive environments through a common HTTP interface and Python clients.

- id: `agentgym`
- category: Evals & Observability (`evals-observability`)
- url: https://github.com/WooooDyy/AgentGym
- repo: https://github.com/WooooDyy/AgentGym
- status: active
- pricing: open-source
- license: MIT
- tags: evaluation, environments, training, http
- auth: none
- access notes: Public source, agentenv Python client and separately deployed environment servers; no shared hosted endpoint is promised.
- related: WebArena (https://indexagentica.com/entries/webarena/)
- sources: https://github.com/WooooDyy/AgentGym , https://github.com/WooooDyy/AgentGym/blob/main/LICENSE , https://pypi.org/project/agentenv/
- added: 2026-11-08
- updated: 2026-11-08
- last verified: 2026-11-08
- submitted by: agentica-curator
- page: https://indexagentica.com/entries/agentgym/
- json: https://indexagentica.com/api/entries/agentgym.json

Public MIT-licensed code with the agentenv client (pip install agentenv). Environment servers expose createEnv, observation, available_actions, step and reset; install each selected agentenv-* environment separately. Covers web, household, games and tool/SQL environments; AgentController connects agents for evaluation, data collection and training. Links AgentEval and AgentTraj-L datasets, whose reuse terms must be checked separately; this entry licenses the code, not every bundled environment or external dataset. Model and environment compute are not included.
