Install & Configure

Caution

Giskard v3.0.0rc1 is a release candidate. APIs can still change before the stable 3.0.0 release.

Install with a coding agent

Ask your coding agent to follow this page.

Paste this into your coding agent:

Follow the instructions from https://docs.giskard.ai/oss/checks/installation.md and install Giskard in my project.

How it works

1. Paste the URL into any coding agent (Claude Code, Cursor, Windsurf, Copilot, etc.)
2. The agent reads the installation instructions from this page
3. The agent installs giskard and configures your LLM provider
4. You review the changes and start writing checks

Want a permanent Giskard expert in your agent?

Install the Giskard Agent Skills. They give your coding agent a workflow for generating adversarial test scenarios, red-team suites, and RAG evaluation suites, triggered by prompts like “test my agent”, “red-team my chatbot”, or “evaluate my RAG”.

Install the Python package

Giskard requires Python 3.12 or higher. Install it together with the SDK for the LLM provider you will use as a judge: an LLM the library calls to grade your agent’s replies.

pip install "giskard[openai]==3.0.0rc1"

No provider SDK ships with giskard itself, so installing it without a provider extra leaves LLM-based checks unable to reach a model.

Pick the extra that matches your provider:

Provider prefix	Install	SDK
openai/	pip install --pre "giskard[openai]"	openai
google/ or gemini/	pip install --pre "giskard[google]"	google-genai
anthropic/	pip install --pre "giskard[anthropic]"	anthropic
azure/	pip install --pre "giskard[azure]"	openai
azure_ai/	pip install --pre "giskard[azure]"	openai

Use pip install --pre "giskard[all-llms]" for all the native SDKs at once.

Using LiteLLM instead

For unsupported providers, install pip install --pre "giskard[litellm]" and pass LiteLLMGenerator explicitly:

from giskard.agents.generators import LiteLLMGenerator

llm_judge = LiteLLMGenerator(model="bedrock/anthropic.claude-3-sonnet")

The default Generator does not use LiteLLM.

Configure the default LLM judge model

A judge is an LLM that reads your agent’s reply and decides whether it satisfies a rule you wrote in plain language. Some checks need one (LLMJudge, Groundedness, Conformity). To use them, configure a provider SDK. The default Generator uses Giskard’s native provider SDK integrations; install the matching giskard extra, such as openai above. LiteLLM is optional through giskard[litellm].

When a judge runs, its prompt includes the test inputs and agent outputs. Those values are sent to the configured LLM provider, so use a provider and model that meet your data-handling requirements. A weak judge model can produce unreliable verdicts.

For OpenAI, set the OPENAI_API_KEY environment variable:

export OPENAI_API_KEY="your-api-key"

Keep these in a .env file rather than your shell profile. To load them in Python, install python-dotenv:

pip install python-dotenv

from dotenv import load_dotenv

load_dotenv()  # loads .env from the current directory

Then you can set your preferred LLM judge model like this:

from giskard.agents.generators import Generator
from giskard.checks import set_default_generator

# Create a generator with giskard.agents
# The provider prefix picks the SDK: openai/, google/, anthropic/, azure/, azure_ai/
llm_judge = Generator(model="openai/gpt-5-mini")

# Configure the checks to use this judge model by default
set_default_generator(llm_judge)

Generator is GiskardLLMGenerator, which routes the provider/model string to that provider’s native SDK through giskard-llm. Use a capable judge model and review failures before acting on them.

Next Steps

For a step-by-step lesson with no API key, try Your First Test first. Or head to the Quickstart for a single example.