AI red teaming & LLM evaluation
DeepTeam is an open-source LLM red teaming framework from Confident AI. It is released under the Apache-2.0 license and is offered as: Library, CLI, Self-hosted.
Best for
Python teams that want a free framework to run single-turn and multi-turn attacks against an LLM app or agent from code or a YAML config
Consider instead if
DeepTeam is an open-source Python framework for red teaming LLM applications and agents, made by Confident AI and built on the DeepEval project. You install it with pip, then run it from Python or from a YAML config with the deepteam run command. Its README lists more than 50 vulnerabilities, such as PII leakage and bias, and more than 20 attacks, including single-turn prompt injection and multi-turn jailbreaks such as Crescendo. The README says it can red team against frameworks including OWASP Top 10 for LLMs 2025, NIST AI RMF and MITRE ATLAS. The code is Apache-2.0 licensed and free to run. DeepTeam is a testing framework, not an inline filter for live traffic.
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 |
|---|---|---|
| LLM01 Prompt Injection | Runs prompt injection and jailbreak attacks, single-turn and multi-turn, against a target. | Runs single-turn prompt injection attacks; Runs jailbreaking attacks, including linear, tree and Crescendo jailbreaking; Runs multi-turn attacks such as Sequential Jailbreak and Bad Likert Judge |
| LLM02 Sensitive Information Disclosure | Tests a target for PII leakage. | Tests for PII leakage among its data privacy vulnerabilities |
| LLM09 Misinformation | Tests a target for misinformation. | Tests for misinformation among its vulnerability types |
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
Yes. DeepTeam is released under the Apache-2.0 license, and the code is on GitHub at confident-ai/deepteam.
The README says to install it with pip install -U deepteam, then run red teaming from Python or from the CLI with a YAML config.
The framework is free under Apache-2.0. Confident AI's pricing page lists an AI red teaming module only under its Enterprise plan, which has custom pricing.
DeepTeam is released under the Apache-2.0 license.
Source Source, checked October 21, 2026: github.com (opens in a new tab) Checked
DeepTeam is offered as: Library, CLI, Self-hosted.
Source Source, checked October 21, 2026: github.com (opens in a new tab) Checked
Pricing model for DeepTeam: Free: The framework is free. On the vendor's pricing page, the Enterprise plan.
Source Source, checked October 21, 2026: confident-ai.com (opens in a new tab) Checked
Latest release of DeepTeam: November 12, 2025.
Source Source, checked October 21, 2026: api.github.com (opens in a new tab) Checked
We have no commercial relationship with Confident AI.