DeepTeam

license

Apache-2.0(OSI)

source

public

self-host

yes

service

none

core features withheld

no

DeepTeam's full source is published under Apache-2.0 and runs locally. Confident AI sells a hosted platform for viewing red-teaming results, but it is a separate product and nothing is withheld from the framework.

• https://github.com/confident-ai/deepteam recorded 2026-08-13

  Repo metadata records license spdxId - Apache-2.0. README states DeepTeam 'runs locally on your machine and is built on DeepEval, the open-source LLM evaluation framework'; the hosted Confident AI offering is pitched as somewhere for results to live, not as a tier that unlocks the framework. No enterprise directory, commercial edition or license key on the page.

• https://pypi.org/pypi/deepteam/json recorded 2026-09-29

  PyPI metadata for deepteam 1.0.9 carries the classifier "License :: OSI Approved :: Apache Software License", lists the sdist "deepteam-1.0.9.tar.gz", and the long description calls it an "open-source red teaming framework for LLM systems" that "is licensed under Apache 2.0".

• https://trydeepteam.com recorded 2026-09-29

  The DeepTeam homepage FAQ answers "DeepTeam is the open-source red teaming framework, while Confident AI is the enterprise platform" that adds managed assessments and dashboards, and the footer reads "Open-source LLM red teaming framework. Apache 2.0 licensed."

• https://trydeepteam.com/docs/getting-started recorded 2026-09-29

  The getting-started page describes Confident AI as "the cloud solution for DeepTeam and DeepEval" for viewing results centrally, while red teaming results can be converted to a dataframe or "saving it locally for any downstream tasks you may have".

Deepteam's adoption reading comes from its GitHub star count, and a star is not a use, so the reading cannot climb from that signal alone. No other usage figure -- downloads, installs, or customer count -- appears in the sources checked here.

• https://github.com/confident-ai/deepteam recorded 2026-08-13

  stargazerCount 2442 for confident-ai/deepteam; no download, install or customer figure appears on the page.

DeepTeam maps its checks and attacks to the main published AI security taxonomies, including the OWASP lists for LLM and agent applications, NIST AI RMF and MITRE ATLAS, and its attacks cover both single-turn and multi-turn jailbreaks. Runtime guardrails for model inputs and outputs ship in the same package.

• https://github.com/confident-ai/deepteam recorded 2026-08-13

  README lists '50+ ready-to-use vulnerabilities', '20+ research-backed adversarial attack methods for both single-turn and multi-turn', mappings to OWASP Top 10 for LLMs 2025, OWASP Top 10 for Agents 2026, NIST AI RMF and MITRE ATLAS, and '7 production-ready guardrails'.

• https://pypi.org/pypi/deepteam/json recorded 2026-09-29

  The README on PyPI lists "50+ ready-to-use" vulnerabilities and "20+ research-backed" attack "methods for both single-turn and multi-turn" red teaming, maps to "OWASP Top 10 for LLMs 2025", "OWASP Top 10 for Agents 2026", NIST AI RMF, MITRE ATLAS, BeaverTails and Aegis, and offers "7 production-ready" guardrails.

• https://trydeepteam.com recorded 2026-09-29

  The homepage lists "OWASP Top 10 for LLMs, MITRE ATLAS, NIST AI RMF, EU AI Act" plus "safety benchmark datasets like BeaverTails and Aegis" among the frameworks DeepTeam maps to.