---
title: README
emoji: 📊
colorFrom: blue
colorTo: indigo
sdk: static
pinned: false
---

# Quantiles

**Open-source, local-first evaluation infrastructure for applied AI systems, designed for developer and coding-agent workflows.**

Quantiles gives developers a CLI and Python SDK for creating, running, analyzing, and comparing AI evaluations from their existing development environment. It records metrics, sample-level outputs, execution traces, and run history locally, making it easier to measure system behavior, detect regressions, validate changes, and ship higher-quality, more reliable AI systems.

With Quantiles, developers can:

- Run built-in benchmarks or create custom evaluations from configuration or Python.
- Debug individual samples with step-level inputs, outputs, metrics, and errors.
- Resume interrupted runs and reuse completed steps.
- Compare models, prompts, datasets, and configurations from the CLI.
- Run evaluation workflows with coding agents using the Quantiles agent skill.

## Quickstart

Install the CLI and run SimpleQA Verified:

```bash
curl -fsSL https://cli.quantiles.io/install.sh | bash
qt run simpleqa-verified
qt show 1 --json
```

This first run uses the built-in demo model, so it requires no model API key and incurs no inference cost. Use it to verify the workflow, then configure a provider-backed model for a real evaluation.

## Documentation & Resources

- [Documentation](https://quantiles.io/documentation) — Everything needed to use Quantiles.
- [Quickstart](https://quantiles.io/documentation/quickstart) — Install Quantiles and run your first evaluation.
- [GitHub](https://github.com/quantiles-evals/quantiles) — Explore the source code and contribute.
- [Agent skill](https://github.com/quantiles-evals/skill) — Run and analyze AI evaluations with a coding agent.

### Articles 

- **Oct 1, 2026** | [Does your SKILL.md help coding agents?](https://huggingface.co/blog/phranzia/does-your-skill-md-help-coding-agents)
- **Sept 24, 2026** | [Evaluating AI Agent Tool Use](https://huggingface.co/blog/phranzia/evaluating-ai-agent-tool-use)
- **Sept 17, 2026** | [Measuring Agent Recovery](https://huggingface.co/blog/phranzia/measuring-agent-recovery)
- **Sept 14, 2026** | [Measure, Understand, and Improve Agent Latency](https://huggingface.co/blog/phranzia/measure-understand-and-improve-agent-latency)
- **Sept 4, 2026** | [Using Execution Traces to Evaluate AI Agent Behavior](https://huggingface.co/blog/phranzia/using-execution-traces-to-evaluate-agent-behavior)
- **Aug 27, 2026** | [How to Evaluate AI Agents](https://huggingface.co/blog/phranzia/how-to-evaluate-ai-agents)
- **Aug 4, 2026** | [Build an AI Evaluation from a Hugging Face Dataset Without Writing Python](https://huggingface.co/blog/phranzia/build-an-ai-evaluation-from-a-hugging-face-dataset)

Quantiles is available under the [Apache License 2.0](https://github.com/quantiles-evals/quantiles/blob/main/LICENSE).