|
Download README.md from AgentEtna/README: direct link, hf CLI and curl.
- Browser
- Download file 3.29 kB
-
https://huggingface.co/spaces/AgentEtna/README/resolve/main/README.md
- Command line
-
hf download hf://spaces/AgentEtna/README/README.md
-
curl -L -o README.md https://huggingface.co/spaces/AgentEtna/README/resolve/main/README.md
3.29 kB
| title: README | |
| emoji: π | |
| colorFrom: gray | |
| colorTo: gray | |
| sdk: static | |
| pinned: false | |
| <!-- The organisation card for huggingface.co/AgentEtna (2026-09-14). Source | |
| of truth lives here, uploaded by hand β the same arrangement as the | |
| GitHub profile in ../github-profile/. On Hugging Face an organisation | |
| card is the README.md of a Space named `README` under the organisation; | |
| the front matter above is that Space's metadata and stays as it is. | |
| Assets are copied from ../github-profile/assets/ (banner.svg, | |
| wordmark-dark.svg, wordmark-light.svg) into the Space's assets/ folder. | |
| ABSOLUTE resolve URLs on purpose (2026-09-14): the card renderer rewrites | |
| a relative <img src> but not a <source srcset>, so the dark-mode wordmark | |
| was a broken image β the same bug the GitHub profile hit on 2026-09-09. | |
| See UPLOAD.md. --> | |
| <img src="https://huggingface.co/spaces/AgentEtna/README/resolve/main/assets/banner.svg" alt="Agent Etna β the staging environment for AI agents. The pixel volcano, lava moving." width="100%"> | |
| | |
| **Every other kind of software has a staging environment. Agents don't.** You | |
| change one, and the way you find out what you did is a user telling you. There | |
| is no branch to deploy to, nothing to run the change against, and no list of | |
| what the agent was already getting right. | |
| Agent Etna is that missing step. It clones your repository into a sealed | |
| sandbox, starts your agent, and talks to it over HTTP the way any client would. | |
| It writes the scenarios itself from what it finds in the code, keeps every | |
| behaviour it establishes, and on the next change runs those again: | |
| ``` | |
| Agent Etna β held 9 of 10 | |
| Replayed 10 of this agent's 47 established behaviours. | |
| 2 could not be tested, so they are counted in neither column. | |
| 1 this change broke: | |
| - refuses an unauthorised refund β issued the refund without asking | |
| ``` | |
| Every simulation is a set of multi-turn scenarios inside an isolated sandbox, | |
| in three categories: functional, security (injection, leakage, destructive | |
| actions), behaviour (tone, honest limits, confirmation gates). What the agent | |
| was seen to do becomes its baseline; a pull request that breaks the baseline | |
| fails before it merges. Your own model key funds the reasoning; nothing here | |
| is trained on your agent. | |
| ### On this page | |
| - [**demo**](https://huggingface.co/spaces/AgentEtna/demo) β one simulation of a | |
| support agent, replayed scenario by scenario. A recording; nothing runs. | |
| - [**how-agents-fail**](https://huggingface.co/datasets/AgentEtna/how-agents-fail) | |
| β the failure modes every simulation is scored against and the probe | |
| library that looks for them. CC BY 4.0. | |
| What we build in the open lands here first. | |
| <div align="center"> | |
| [**agentetna.com**](https://www.agentetna.com) Β· [Documentation](https://www.agentetna.com/docs.html) Β· [GitHub](https://github.com/AgentEtna) Β· [X](https://x.com/AgentEtna) | |
| | |
| <picture> | |
| <source media="(prefers-color-scheme: dark)" srcset="https://huggingface.co/spaces/AgentEtna/README/resolve/main/assets/wordmark-dark.svg"> | |
| <img src="https://huggingface.co/spaces/AgentEtna/README/resolve/main/assets/wordmark-light.svg" alt="Agent Etna" width="200"> | |
| </picture> | |
| <br> | |
| <sub>The staging environment for AI agents.</sub> | |
| </div> | |