About this tool
AXIS is open source tooling and a scoring framework designed to measure how well services work for AI agents. It runs real scenarios to generate a composite 0–100 score, helping developers identify and fix bottlenecks that slow agents down.
Core Features
- Scenario Execution: Run real agent scenarios to evaluate service performance in actual interactions.
- Four-Dimension Scoring: Scores across Goal Achievement, Environment, Service, and Agent, with detailed breakdowns for each dimension.
- Project Initialization: Quickly initialize a project with the
axis initcommand, interactively configuring the scenarios directory and agents. - Skill Installation: Automatically runs
npx skills add netlify/axis --allto install the configure-axis skill into detected agent config directories. - API Key Support: Requires an API key for at least one supported agent (e.g., ANTHROPIC_API_KEY for Claude Code).
Workflow
- From your project root, run
axis initand follow prompts to configure the scenarios directory and agents. 2. Two files are created:axis.jsonsample scenario and agent configuration file. 3. Run scenarios to obtain a composite AXIS score from 0–100. 4. Use the four-dimension breakdown to locate and fix issues affecting agent experience.
Scoring Dimensions
- Goal Achievement: Did the agent complete the task? Scored against your rubric checks.
- Environment: How the agent interacts with the system environment.
- Service: Quality of service responses to agent requests.
- Agent: The agent's own execution performance. AXIS is free to use and is suitable for AI agent developers, service providers, and platform engineers.
Features & use cases
{json|js|ts} -minimal config with your chosen scenarios path and agentsAfter the files are written, init also runs npx skills add netlify/axis --all to install the configure-axis skill into your detected agent config directoriesAn API key for at least one supported agent (for example, ANTHROPIC_API_KEY for Claude Code)Breakdowns for each of the four scoring dimensions: Goal Achievement, Environment, Service, and AgentDimension What It Tells You Goal Achievement Did the agent complete the task? Scored against your rubric checksExecution & Agents -how AXIS runs scenarios, supported and custom agents, and workspace isolationExecution & Agents -how AXIS runs scenarios, supported and custom agents, and workspace isolation.Initialize Your Project From your project root, run: axis init In an interactive terminal, this prompts you for the scenarios directory, which agents to include (comma-separated, eInterpret Your Results The AXIS Result is a composite of four dimensions, each measuring a different aspect of the agent's interaction with your systemIt then creates two files: axisjson -a sample scenario that asks the agent to create a file with specific contentNext Steps Scoring Framework -how the four dimensions are calculated, what signals drive each score, and why the scoring works the way it does
At a glance
Sources
Every profile keeps its sources and latest verification date.Similar tools
Spettro
spettro.app
90
Spettro is a terminal-first multi-agent coding assistant written in Go, with configurable agents, goal mode, agent skills, approval-aware execution, persistent sessions, and OpenAI-compatible model routing.
Freemium · 5+/mo
