# Giskard-AI/giskard-oss

🐢 Open-Source Evaluation & Testing library for LLM Agents

Repository: https://github.com/Giskard-AI/giskard-oss
Canonical: https://ross.abutalabs.com/products/giskard-oss
Homepage: https://docs.giskard.ai
Language: Python
License: Apache-2.0
License Family: permissive
Topics: mlops, ml-validation, ml-testing, ai-testing, llmops, responsible-ai, fairness-ai, trustworthy-ai, llm-eval, llm-evaluation, rag-evaluation, ai-security, llm-security, ai-red-team, red-team-tools, llm, agent-evaluation
Last push: 2026-08-26T12:31:32+00:00

## Health v2 (maintenance only)
Score: 95/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 99, release rhythm 87, longevity 100
- inputs: {"age_days": 1641, "days_push": 7, "days_rel": 7, "gap_med": 0, "n_releases_24m": 62}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 5773, forks 523 (observed 2026-08-28T04:09:29.463134+00:00)

## What it is
Giskard is an open-source Python library for testing, evaluating, and red-teaming LLM-based agents and RAG systems. Its v3 rewrite provides modular packages for checks, vulnerability scanning, and dynamic multi-turn agent testing.

## Use cases
- evaluate llm agents automatically
- red team my chatbot for vulnerabilities
- test rag pipeline quality
- scan llm app for security issues
- generate test cases for ai agents
- benchmark llm outputs for hallucinations

## When to choose
- you need programmatic, Python-based evaluation of LLM agents or RAG systems
- you want automated AI vulnerability scanning and red teaming in CI
- you prefer a lightweight, modular, async-first testing library

## When to avoid
- you need a GUI-based enterprise testing platform with team collaboration (consider Giskard Hub)
- you need to test tabular/ML models - that legacy scan is v2-only and unmaintained
- your environment is below Python 3.12

## Facets
- artifact type: library
- maturity: active
- function: testing, llm-inference, rag, agent-framework, security, benchmarking
- domain: artificial-intelligence, large-language-models, machine-learning, testing, security
- platform: python, cli
- tags: llm-evaluation, red-teaming, ai-safety, llmops, vulnerability-scanning, rag-evaluation, agent-testing, responsible-ai, ai-agents, retrieval-augmented-generation

## Member repositories
- Giskard-AI/giskard-oss (main) score 95

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:29.463134+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:52:52.361253+00:00, confidence not recorded.
  - readme: https://github.com/Giskard-AI/giskard-oss (fetched 2026-08-28T04:09:29.463134+00:00, sha be4f3d603172)
  - homepage: https://docs.giskard.ai (fetched 2026-08-29T08:48:11.830156+00:00, sha 94ffe2321b83)
- Data as of 2026-08-30T08:39:29.467469+00:00.