DEDUPED Hot AI repos. Real use cases. What people build. Get the Monday 5
277 stars · TypeScript

How to use Dodoguard: what you can do with it

What is Dodoguard? DodoGuard is a self-hosted tool that evaluates, red-teams, and audits AI agents and agent apps before and after deployment, with reports you keep on your own infrastructure.

How do I use it? Run git clone https://github.com/dodoguardai/dodoguard.git; then run cd dodoguard && npm ci && npm run build; run cp -R examples/openai-eval-factuality ./my-eval && cd my-eval. Full steps below.

Trended earlier

View repo on GitHub

Third-party repos we don't own. AI-written use cases can be wrong. Disclaimer

Authorization notice. This tool is dual-use. Only use it on software, sites and systems you own or have explicit permission to test, and follow the relevant licenses and terms of service.

What do you want to do?

4 use cases

  • Run a factuality eval on a prompt before release

    Score an LLM prompt against test cases from the command line in about one minute of run time.

    View prompt
    In the dodoguard repo, copy examples/openai-eval-factuality to a new folder, set OPENAI_API_KEY, and run ../node_modules/.bin/dodoguard eval from that folder. Report the pass and fail count for each test case. Verify that the run finished and wrote a result for every case before you report success.

  • Red-team a local model for prompt injection

    Run adversarial probes against a model hosted with Ollama to find jailbreaks and guardrail bypasses.

    View prompt
    In the dodoguard repo, use the examples/redteam-ollama config to red-team a local Ollama model named <model-name>. Return the list of findings with severity and evidence. Verify that each finding links to the prompt that caused it.

  • Audit a Dify or Coze agent for misconfig and attack surface

    Scan an agent app built on a hosted platform and get findings with severity and a remediation path.

    View prompt
    Using the dodoguard web console at http://localhost:3000, register the agent app <agent-name> as an asset and create a platform check task for it. Return the findings with severity and evidence. Verify that the task was rerun after fixes and that no open high-severity finding remains before you recommend release.

  • Export release evidence to support a go-live decision

    Track an agent through intake, detection, and observation, then export reports you keep private.

    View prompt
    Using the dodoguard repo, register the agent <agent-name> in the web console, run its detection tasks, and export the reports. Return the exported report list and the open findings count. Verify that the acknowledged state did not move the agent to released before the remediation loop passed.

Quick start with Dodoguard

  1. Check you have what it needs: Node.js 22.12 or newer for the CLI; An OpenAI API key for the OpenAI example, or a local Ollama setup for the local red-team example; Docker with Docker Compose for the web console.
  2. Open dodoguardai/dodoguard on GitHub and read the README and license.
  3. Run git clone https://github.com/dodoguardai/dodoguard.git
  4. Run cd dodoguard && npm ci && npm run build
  5. Run cp -R examples/openai-eval-factuality ./my-eval && cd my-eval
  6. Set your key with export OPENAI_API_KEY=" ", replacing the space with your real key

These steps come from our top use case, Run a factuality eval on a prompt before release, which also has a copy-paste agent prompt.

Use this in your AI agent

Ask your agent

Using the Deduped MCP, get the setup steps for dodoguardai/dodoguard

Add Deduped to Claude Code once

claude mcp add --transport http deduped https://dedupedai.com/mcp

Cursor, ChatGPT, others

Best AI repos for Software and DevOps

About this repo

  • Who it is forDevelopers and release owners who need evidence that an LLM app or AI agent is safe and reliable before it goes live.
  • Why it is hot277 stars, launched 67 days ago
  • LanguageTypeScript
  • Sourcegithub.com/dodoguardai/dodoguard · Back to Hot repos

Requirements

  • Node.js 22.12 or newer for the CLI
  • An OpenAI API key for the OpenAI example, or a local Ollama setup for the local red-team example
  • Docker with Docker Compose for the web console
  • Access to the Dify, Coze, FastGPT, or n8n app you want to check, if you run platform checks

Add this badge to your README

Maintain Dodoguard? Show readers where to find these use cases. Use cases on Deduped

Markdown 

[![Use cases on Deduped](https://dedupedai.com/badge/dodoguardai/dodoguard.svg)](https://dedupedai.com/use-cases/dodoguardai-dodoguard/?utm_source=github&utm_medium=badge&utm_campaign=dodoguardai-dodoguard)

HTML 

<a href="https://dedupedai.com/use-cases/dodoguardai-dodoguard/?utm_source=github&amp;utm_medium=badge&amp;utm_campaign=dodoguardai-dodoguard"><img src="https://dedupedai.com/badge/dodoguardai/dodoguard.svg" alt="Use cases on Deduped" height="20"></a>

A static image, no tracking script. About the badge

Questions about Dodoguard

What is Dodoguard?

DodoGuard is a self-hosted tool that evaluates, red-teams, and audits AI agents and agent apps before and after deployment, with reports you keep on your own infrastructure. It is an open-source project on GitHub: https://github.com/dodoguardai/dodoguard.

How do I use Dodoguard?

Run git clone https://github.com/dodoguardai/dodoguard.git; then run cd dodoguard && npm ci && npm run build; run cp -R examples/openai-eval-factuality ./my-eval && cd my-eval. The use cases on this page give the full steps and a copy-paste agent prompt for each job.

Who is Dodoguard for?

Developers and release owners who need evidence that an LLM app or AI agent is safe and reliable before it goes live.

What can I do with Dodoguard?

4 use cases so far, for example: Run a factuality eval on a prompt before release; Red-team a local model for prompt injection; Audit a Dify or Coze agent for misconfig and attack surface. Each has steps and a copy-paste agent prompt.

What do I need to run Dodoguard?

Node.js 22.12 or newer for the CLI; An OpenAI API key for the OpenAI example, or a local Ollama setup for the local red-team example; Docker with Docker Compose for the web console; Access to the Dify, Coze, FastGPT, or n8n app you want to check, if you run platform checks.

What are alternatives to Dodoguard?

Other hot AI repos in Software and DevOps: ECC, Thinkrail, Superpowers, Deep Infer, Instructor.

Is Dodoguard safe to run?

Deduped does not own, audit or vouch for it. Read the README and license, run it on your own systems first and review every command before you run it.