From 76f8d773f95958138e822e0bc62c76b42ae1edfc Mon Sep 17 00:00:00 2001 From: phranzia <9207473+phranzia@users.noreply.github.com> Date: Fri, 24 Jul 2026 15:10:02 -0700 Subject: [PATCH 1/4] Add badges and links Also updated release date of custom no-code evaluations. --- README.md | 16 +++++++++++++++- docs/assets/quantiles-wordmark.svg | 4 ++++ 2 files changed, 19 insertions(+), 1 deletion(-) create mode 100644 docs/assets/quantiles-wordmark.svg diff --git a/README.md b/README.md index 2313164..00a5d06 100644 --- a/README.md +++ b/README.md @@ -1,4 +1,18 @@ -# Quantiles +

+ + Quantiles + +

+ +

Local-first AI evaluation for developers and coding agents.

+ +

+ CI + GitHub Release + License + Documentation + Agent Skill +

Quantiles is open-source, local-first evaluation infrastructure for applied AI systems, designed for developer and coding-agent workflows. diff --git a/docs/assets/quantiles-wordmark.svg b/docs/assets/quantiles-wordmark.svg new file mode 100644 index 0000000..ec5eeef --- /dev/null +++ b/docs/assets/quantiles-wordmark.svg @@ -0,0 +1,4 @@ + + Quantiles + + From de91e493482082edc9d093e6c275600f82dd2176 Mon Sep 17 00:00:00 2001 From: phranzia <9207473+phranzia@users.noreply.github.com> Date: Fri, 24 Jul 2026 15:14:27 -0700 Subject: [PATCH 2/4] update CI link --- README.md | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/README.md b/README.md index 00a5d06..9b1b2c1 100644 --- a/README.md +++ b/README.md @@ -7,8 +7,7 @@

Local-first AI evaluation for developers and coding agents.

- CI - GitHub Release + CLI CI License Documentation Agent Skill @@ -22,7 +21,7 @@ Quantiles centralizes its components in this monorepo so developers, researchers ## ![New](./docs/assets/new-badge.svg) What's New -**[2026.07.07]** Added `custom_nocode` evaluations, which let users configure custom evals in `quantiles.toml` without writing or maintaining custom code. See the [custom no-code evaluation documentation](https://quantiles.io/documentation/custom-evaluations/custom-nocode-evaluations) for details. +**[2026.07.19]** Added `custom_nocode` evaluations, which let users configure custom evals in `quantiles.toml` without writing or maintaining custom code. See the [custom no-code evaluation documentation](https://quantiles.io/documentation/custom-evaluations/custom-nocode-evaluations) for details. ## Why use Quantiles? From 86d9a605b6aee9bf0e577d1ba24e1ccf40e0e945 Mon Sep 17 00:00:00 2001 From: phranzia <9207473+phranzia@users.noreply.github.com> Date: Fri, 24 Jul 2026 15:25:05 -0700 Subject: [PATCH 3/4] Add hugging face badge --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index 9b1b2c1..20bc51a 100644 --- a/README.md +++ b/README.md @@ -7,10 +7,10 @@

Local-first AI evaluation for developers and coding agents.

- CLI CI License Documentation Agent Skill + Quantiles on Hugging Face

Quantiles is open-source, local-first evaluation infrastructure for applied AI systems, designed for developer and coding-agent workflows. From b3d825778c0e2b12697c681cc7b6fefec98826c4 Mon Sep 17 00:00:00 2001 From: phranzia <9207473+phranzia@users.noreply.github.com> Date: Fri, 24 Jul 2026 15:31:01 -0700 Subject: [PATCH 4/4] Add badges and links --- README.md | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/README.md b/README.md index 20bc51a..63db577 100644 --- a/README.md +++ b/README.md @@ -1,8 +1,8 @@ -

+

Quantiles -

+

Local-first AI evaluation for developers and coding agents.

@@ -10,9 +10,11 @@ License Documentation Agent Skill - Quantiles on Hugging Face + Quantiles on Hugging Face

+--- + Quantiles is open-source, local-first evaluation infrastructure for applied AI systems, designed for developer and coding-agent workflows. Use the `qt` CLI and Python SDK to create, run, analyze, and compare evaluations for models, prompts, and agents with resource-efficient local execution. Quantiles records metrics, sample-level results, execution history, and evaluation traces so you can measure system behavior, detect regressions, validate changes, and ship higher-quality, more reliable AI systems.