DeepTeam
v0.1.9 open-sourceThe section your link pointed to isn't on DeepTeam's page any more, so we've brought you to the top.
DeepTeam tests and red-teams LLMLLMA large language model, a neural network trained on large amounts of text to recognize patterns and generate language. Applications use it for tasks such as answering, summarizing and writing code. applications by simulating attacks and evaluating security vulnerabilities.
deepteam run config.yaml
from deepteam import red_team
risk_assessment = red_team(
model_callback=your_agent_callback,
vulnerabilities=[DirectControlHijacking()],
attacks=[AuthoritySpoofing()]
)
Summary
DeepTeam is an open-source red teaming framework for LLM systems, distributed free under its published licence, and used as a library imported into your own code rather than run as a hosted service. It simulates attacks — jailbreaking, prompt injectionprompt injectionAn attack where text the model reads, such as a web page, file or tool result, carries instructions that override the user's. It is the main security risk for agents with tools., multi-turn exploitation — against agents, RAGRAGRetrieval-augmented generation: looking up relevant documents and adding them to the prompt before the model answers. It grounds responses in private or current data without retraining. pipelines, and chatbots to surface issues like bias, PIIPIIPersonally Identifiable Information — data that can identify a specific individual, such as names, email addresses, or SSNs. Cyber tools flag or redact it to limit exposure and meet privacy regulations. leakage, and SQL injectionSQL injectionAn attack that makes an application treat untrusted input as part of a database command. It can expose or modify data by changing what the query does., and it also offers guardrails to catch these in production. It runs locally on your machine and is built on DeepEval, the project's own open-source LLM evaluation framework, which places it in the same lineage rather than alongside a named external competitor. It's aimed at teams building or securing LLM applications who need to test them the way penetration testers approach conventional software. With 32 contributors and 701 commits in the past year across four tracked releases, it is under active development.
DeepTeam tests and red-teams LLM applications by simulating attacks and evaluating security vulnerabilities.
How DeepTeam helps
Which vulnerabilities in my chatbot or agent would an attacker actually find first?
runs simulated jailbreaking, prompt injection, and multi-turn exploitation attacks against the system and reports which ones surfaced bias, PII leakage, SQL injection, and similar issues, with the attack that triggered each
Would a determined user be able to talk my model out of its safety rules over several turns?
drives multi-turn exploitation conversations against the target and shows which sequences eventually broke through, not just single-prompt attempts
Is my retrieval pipeline leaking data it shouldn't through crafted queries?
points the same attack simulations at a RAG pipeline and flags responses containing PII or injected content that leaked from the retrieved context
Can I catch these attacks before they reach production instead of just after a test run?
applies the same checks as guardrails at inference time so a request or response matching a known attack pattern is caught while the system is live
Which of my own prompts or agent configurations are most exposed?
runs the vulnerability and attack simulations against a given agent or chatbot configuration and reports results per target, so different configurations can be compared for exposure
How do I test my LLM system for security holes without standing up a separate red-teaming service?
runs as a library imported directly into your own code and executes entirely on your machine, so the attack simulation happens inside your existing test or CI setup
Languages
Command line
No command matches.
| option | found in | since | description |
|---|
Values are placeholders taken from each option’s declared default. Nothing is executed here — the output shown is a recording of a run that already happened.
Score card
-
Shipping velocity releases a month, last 12 months
-
Documentation quality release-notes rubric, 0–100
-
Breaking-change discipline how rarely a release breaks users, and notice given
-
Maintenance risk quiet time against its own cadence, maintainers
-
Innovation & surface new capabilities, API and MCP surface
- Community health
-
Contributor trend distinct committers, this year against last
-
Maintainer concentration bus factor now against a year ago
-
Issue backlog trend issues closed per issue opened, 12 months
-
Responsiveness median time to a maintainer’s first reply
Nine scores for DeepTeam, each built from the releases, notes and API history this site tracks — and, on Researcher and Business, where it stands among every measured tool in its category and how that has moved.
Score cards are part of every paid plan.
See plans → Already subscribed? Sign in →Trajectory
Blank means never measured; nothing here is a filled-in zero.
Peer standings are included with Researcher and Business. See how this tool ranks against its competitors, using data we don't publish anywhere else.
See plans →Each score is 0–100 on a published rubric, derived from data this site already shows. A dimension we cannot measure says so — it is never scored 0 and never enters a rank.
How this is scored
- Shipping velocity — releases a month over the last 12 months, on a log scale where 16 a month scores 100. Needs 3 releases in the window.
- Documentation quality — the release-notes rubric published on the analytics page, unchanged.
- Breaking-change discipline — the share of releases carrying a breaking change (none scores 100, half or more scores 0). Only projects that label breaking changes are measured: a clean record cannot be told from an unlabelled one.
- Maintenance risk — quiet time measured against the tool's own release cadence (quiet longer than 90 days and three typical gaps scores 0), plus the number of active maintainers and whether contributors are growing, where known. Higher is lower risk.
- Innovation & surface — new capabilities in the feature ledger this year, API and MCP operations added, and the share of commits that are features: the mean of whichever we hold.
- Community health (open-source tools only) — each is a direction, not a size: contributors this year against last, the bus factor now against a year ago, and issues closed per issue opened, where steady scores 50, doubled 100 and halved 0; plus the median time to a maintainer's first reply (an hour scores about 100, a month or more 0). A commercial card has no repository and carries none of the four.
- Documented delivery (commercial tools) — when a vendor's documented new capabilities have slowed against its own baseline, that counts against the overall standing as heavily as two low dimensions. Steady delivery, or too little history to judge, leaves the standing alone; it is never a sixth score.
- Open-source tools are scored on repository signals; commercial tools on their published changelog. Ranks compare tools within one category and one profile and need at least five measured peers; the overall standing needs three ranked dimensions. Best-in-breed or consolidator is a shape, not a quality, and is never scored.
Release-note detail over time
See how much detail DeepTeam puts in its release notes, quarter by quarter, and compare it with tracked tools in the same category. This history uses up to ten retained, reviewed notes per tool; sparse or blank older quarters may reflect that limit.
Checking release-note history…
Releases
2 entries
No entries match these filters.
- July 20251
- May 20251
Project health
Issue, contributor and maintainer activity in confident-ai/deepteam, 2023-10 – 2026-09, as of 2026-09-25. Twelve-month figures first; the trend lines run the whole window.
- Contributors 15 −5 vs prior 12 months
- Maintainers 2 +0 joined · −1 left, last 12 months
- Bus factor 1 committers behind half the commits
- Community-filed 100% of issues opened, last 12 months
- Median time to close 1.8 days first maintainer reply 2.8 days
- Open backlog 34 of 55 issues ever filed
- Issues opened / month 2 · 0 communitymaintainers
- Open backlog 34
- Contributors / month 1
- Commits / month 1
- Stars 2,821
- other 100%
Counts from the project's public repository and git history; no individuals are identified. Maintainers are the committers covering 80% of the last year's commits. how we measure this
Libraries its release ships
What its latest release locks, checked against known advisories.None of its release's images build from a lockfile we can read.
Add the badge to your README
Maintain this project? The badge links readers straight to this page, so they can follow every release here.
Choose a badge style and copy the code →