HF Space Start here / Other

REA Environments on AgentEnv

REA Environments on AgentEnv is the start-here HF Space for REA → AgentEnv replay environments: 50 replay environments REA built from app sessions. This page is a teaching mirror — we do not host the runtime or parquet/HAR.

Numbers and fields are cited from the Hugging Face note / catalog snapshot.

Open on Hugging Face

Datasets and large HAR/parquet stay on HF. This page is a teaching mirror only — no runtime here.

Open HF Space ↗

Recorded target

Product: Start here: what these 44 environments are, how REA builds them, baseline results for two models, and a filterable gallery of all of them.

Version: —

License: —

Hosting: —

Capture: Not stated in HF note

Updated: Oct 20, 2026 (Asia/Shanghai)

AgentEnv metrics

MCP tools: —

Retrieval tasks: —

Downloads (HF snapshot): —

Likes: 2

id: earakely-scale/rea-environments

What this is

REA Environments on AgentEnv is the start-here Space for the REA → AgentEnv replay-environment collection. 50 replay environments REA built from app sessions. Keywords: AgentEnv, REA, replay environment, MCP tools.

Product: Start here: what these 44 environments are, how REA builds them, baseline results for two models, and a filterable gallery of all of them.
Scenario: 50 replay environments REA built from app sessions
Category: Start here / Other

What REA captured

Capture form: Not stated in HF note.
Target product / version: Start here: what these 44 environments are, how REA builds them, baseline results for two models, and a filterable gallery of all of them..
This entry is the Space gallery entry point, not a single dataset env.

What you practice in AgentEnv

Browse tool counts, task counts, and baselines in the Space gallery, then jump to a concrete HF dataset to practice.

Relation to REA

Pipeline: REA captures an authorized browser/API session → published as a Hugging Face dataset → replayed as MCP tools on Scale AgentEnv. rea.run provides the categorized catalog and teaching copy — it is not the runtime and does not host capture files.

1
Authorize the target (own / OSS / written permission / approved lab).
2
Capture the browser session with REA (HAR or capture-browser-scenario).
3
Replay as AgentEnv MCP tools on Scale AgentEnv / the HF space — not on rea.run.

License & compliance

License is authoritative on the Hugging Face dataset card. Authorized use only: own systems, OSS, written permission, or an approved lab. Do not record or replay against unauthorized production targets. This site does not provide cracking, bypass, or unauthorized-access guidance.

Compliance · Legal boundary

Next steps

Install AgentEnv / REA

To record sessions locally with REA, install rea-agents from official sources. AgentEnv replay and eval run on Scale / HF — not on this site.

HF note (cited)

Snapshot text from the catalog note — not a verbatim dump of a long HF card.

Start here: what these 44 environments are, how REA builds them, baseline results for two models, and a filterable gallery of all of them.