AA

Arthur Agent Development Toolkit

Developer tool

by Arthur AI

Toolkit for building, debugging and shipping AI agents: version prompts, A/B test prompts, models and RAG configs on production data, trace every agent step, run continuous evals and guardrail checks for hallucination, PII, prompt injection and toxicity on live traffic, and alert on quality drift.

Find alternatives to Arthur Agent Development Toolkit

What it does

• Evaluation and observability
• Guardrails and safety

Sources

Pricing

Official documentation · 18 Oct 2026

The page states no price for the Toolkit.

Description

Official documentation · 18 Oct 2026

"A/B test prompts, models, and RAG configs against real production data"; "Inspect every step — inputs, tool calls, reasoning paths, and outputs across every run"; "Run evals on live traffic — hallucination, PII, prompt injection, toxicity, and correctness, continuously"

What it does

Official documentation · 18 Oct 2026

"Set alerts the moment quality drifts — not after a user escalation"; "Arthur scores every prompt and response against your policies and returns a pass or fail with the reasoning behind it."

Sold within

Not found · 18 Oct 2026

The page says the Toolkit is part of the Arthur Engine and "builds on top of that", but does not say whether it is included in the free Engine or sold separately.

Name

Official documentation · 18 Oct 2026

"The Agent Toolkit is part of the Arthur Engine — Arthur's free, open-source AI evaluation and monitoring platform."

URL

Official documentation · 18 Oct 2026

Own page titled "Agent Development Toolkit | Arthur", linked from the Arthur site as the Agent Toolkit.

Deployment

Official documentation · 18 Oct 2026

"Deploy your way — Docker, CloudFormation, or Helm. Your environment, your data."

Also from Arthur AI

• Arthur Platform

  AI observability platform monitoring model performance, bias, drift and behavior for ML and generative AI/agentic applications in production, built on an open-source evals engine.

• Arthur Engine Developer tool

  Open-source, real-time evaluation engine for generative AI and traditional ML models: instant analysis of outputs, active guardrails, and built-in plus customizable metrics, run inside a user's own infrastructure independently of the hosted Arthur platform.

• Arthur Agent Security & Governance Application

  Module within the Arthur AI Platform providing security scanning, policy enforcement and governance controls specifically for autonomous agent deployments (tool-use permissions, action auditing, risk scoring).

• Arthur Observability Platform

  Monitors model performance, model metrics, and data drift.

Open Arthur AI in the directory

Something wrong here? Send a correction — quote this product id: arthur-agent-development-toolkit.