AI red teaming & LLM evaluation
Repello AI is an autonomous AI red teaming platform from Repello AI. It is a commercial product offered as: SaaS. Pricing model: not published.
Best for
Repello AI sells ARTEMIS, a red teaming product aimed at AI agents and the apps around them more than at bare models. Two things separate it from the other hosted red teaming listings here: a Browser Mode that attacks the application through its own web interface (chats, clicks, uploads) next to API testing, and tests that chain exploits across an agent's steps. The product page cites an attack library of over 1,000 entries and coverage of more than 100 languages. What the public pages leave out matters to a buyer: no prices, no ARTEMIS documentation, no named model providers and no hosting model beyond a free web scan. Treat the OWASP, NIST and EU AI Act mapping as a reporting feature to check in a demo.
This summary is our own wording of the sourced facts on this page.
Each value links to the page that states it, with the date we checked it.
As documented by the vendor or project. The tag is our label from a controlled vocabulary.
Our editorial model, not a standard. The primary layer follows the category, except for tools whose main documented job is detection and response; other layers rest on a capability the sources document. How the model works.
| Layer | Role | How it applies | Based on |
|---|---|---|---|
| L4 Testing Testing and red teaming | Primary | Attack and evaluate models, apps and agents on purpose, before release and after every change, to find what the other layers miss. | Follows its category, AI red teaming & LLM evaluation |
The risk list is OWASP's (Top 10 for LLM Applications, 2025). The mapping is our analysis, and each row rests on a capability the sources document.
| Risk | How it applies | Based on |
|---|---|---|
| LLM06 Excessive Agency | The product page says it discovers and validates multi-stage exploit chains in AI agents. | Discovers and validates multi-stage exploit chains in AI agents |
More in AI red teaming & LLM evaluation, ranked within the category by Coverage Score.
NVIDIA
Probes language models and LLM apps for prompt injection, jailbreaks, data leakage and more.
Best for: Teams that want a free command-line scanner they can point at any model or LLM endpoint before release
Reviewed
Giskard AI
Generates adversarial test suites for LLM agents and RAG apps, runs them and reports failures by threat type.
Best for: Python teams that want a free library to scan an LLM agent or RAG app for prompt injection and harmful output, and to write pass or fail checks for it
Reviewed
OpenAI (Promptfoo)
Runs evals and red team scans against LLM apps from a CLI or CI pipeline and writes a vulnerability report.
Best for: Developer teams that want one open-source CLI for both prompt evals and red teaming, run locally and in CI
Reviewed
It is Repello AI's red teaming product. The product page describes autonomous testing of AI applications and agents using multi-turn, multi-stage attacks.
Not on the pages we read. The home page offers a demo request and a free scan of an AI agent.
The product page says findings can be mapped to MITRE, OWASP, NIST, ISO 42001 and the EU AI Act.
No. ARTEMIS is the testing product this page covers. ARGUS is Repello's separate runtime product that screens live traffic, and Inventory is its AI asset discovery product. A team that wants findings turned into blocking rules would need ARGUS or another guardrail on top of ARTEMIS.
Repello AI is closed source (proprietary).
Source Source, checked October 21, 2026: repello.ai (opens in a new tab) Checked
Repello AI is offered as: SaaS.
Source Source, checked October 21, 2026: repello.ai (opens in a new tab) Checked
Pricing model for Repello AI: Not published in the sources we checked.
Source Source, checked October 21, 2026: repello.ai (opens in a new tab) Checked
Status of Repello AI: Active.
Source Source, checked October 21, 2026: repello.ai (opens in a new tab) Checked
We have no commercial relationship with Repello AI.