TESIGN
SAVED

EN · KO

  1. TESIGN / RADAR
  2. 2026.09.21
  3. Promptfoo

Promptfoo

Test what your AI app actually answers

WHO USES ITPeople shipping AI features, and teams that must keep quality steady while the prompts keep changing.

Install to use

Test and compare what your prompts, agents and RAG apps actually answer.

★ 25.2k▲ +5 / 7dDaily star increases over 14 days. Hollow bars mean no data. The last day may be partial.2026-09-08 no data2026-09-09 +22026-09-10 no data2026-09-11 +22026-09-12 +22026-09-13 no data2026-09-14 no data2026-09-15 +32026-09-16 +22026-09-17 no data2026-09-18 no data2026-09-19 no data2026-09-20 no data2026-09-21 no datalargest one-day increase in the 14 days+3last 14 days · stars per dayhollow = no data

25,177 stars · checked on GitHub GitHub check 111 h late · 7-day +5 observed via GH Archive (as of )

A Promptfoo evaluation matrix: prompts and models across the top, test inputs down the side, each cell holding an answer and its pass mark.

TESIGN TAKE

It replaces "that feels better" with a table you can point at. The repository states plainly that it joined OpenAI and stays open source under MIT.

INSTALL

AT A GLANCE

LICENSE
MIT
USAGE
Use, change and redistribute, commercially too. Keep the notice.
LANGUAGE
TypeScript
PLATFORM
cli
ACTIVITY
last commit 4 days ago () · latest release [unconfirmed]
COMMUNITY
contributors [unconfirmed] · open issues [unconfirmed] · made by: [unconfirmed] Reference time unavailable
SOURCES
GitHub
OPEN SOURCE
YES
FIRST SEEN
CATEGORY
AI · DEV TOOLS

A summary, not legal advice.

WHY IT MATTERS

Every prompt change ends up judged by feel. Promptfoo runs the same inputs across models and prompt variants and lays the answers side by side in a matrix, with red-teaming for vulnerabilities in the same tool.

BUILD FROM THIS

  • A CLI and a library: install with npm, brew or pip, or run it with npx and install nothing. Provider keys go in as environment variables, results open as a browser matrix, and it drops into CI as a regression check.

WHO IT'S FOR

People shipping AI features, and teams that must keep quality steady while the prompts keep changing.

START IN 5 MINUTES

# Create an example with npx, run the eval and open the results view.

CAVEATS

  • Needs Node.js 22.22 or newer. Calls run on your own provider keys, so a large eval costs real money there, and there is a paid enterprise edition alongside.

RECEIPT

FIRST SEEN
AT SOURCE
KEPT
CREATED → FIRST SEEN
1236d
WHEN FIRST SEEN
25,177 ★
SOURCES
GitHub

The same facts in machine-readable form — View as Markdown · JSON

SIMILAR TOOLS

Up to five from AI by ★ total: edited entries first, then repository cards; this entry is highlighted. Drawn from the same stored snapshot as the rankings — a comparison, not a recommendation.

IMAGENAME★ TOTAL▲ 7dLICENSEPLATFORMLAST PUSH
ECC README banner: headline 'The operating system for AI agent harnesses', harness chips, and skill, agent and command lists.
eccSkills, memory and security for agents★ 263k▲ +424MITpermissivewindows · macos · linux · cli
Hermes Agent landing: blue background, the headline 'The agent that grows with you' and an engraving-style winged figure.
Hermes AgentSelf-improving personal agent★ 247k▲ +116MITpermissivelinux · macos · windows · android · cli
DeepSeek Harness landing: blue background, the headline 'Everything is a plugin' and a quick-start box with the npx command.
DeepSeek HarnessPlugin agent harness for developers★ 230k▲ +558MITpermissiveweb · cli
A Promptfoo evaluation matrix: prompts and models across the top, test inputs down the side, each cell holding an answer and its pass mark.
PromptfooTest what your AI app actually answersTHIS ENTRY★ 25.2k▲ +5MITpermissivecli
mattpocock/skillsCARD★ 261k▲ +339MITpermissive—

ALSO WORTH SEEING

outloudCheck if a PDF reads correctly aloudThe outloud window: findings on the left, the marked-up PDF page in the middle, and the screen-reader reading order on the right.Install to use
★ 7▲ 3 HN
A PDF accessibility checker that shows what a screen reader would actually say.ApeeyeSpin up mock REST endpoints fastThe Apeeye home screen: "Fake APIs. Real endpoints.", a button to open the Playground, and a row showing the workspace URL to copy.Use in the browser
★ 7▲ 2 HN
Mock REST endpoints in seconds — no login, no config, no database.VocaWinVoice typing that stays on your PCThe VocaWin site: a microphone mark, the line "voice typing that stays on this PC", and a button to download the beta.Install to use
★ 74▲ +5 / 7d
Hold a hotkey, speak, and the text appears at the cursor — Windows dictation that stays on the PC.txcriptContinue an AI session in another toolA terminal running txcript: the install finishes, then a continue command carries a session into another agent.Install to use
★ 125▲ +5 / 7d
Move an AI coding session from one agent to another and carry on where you left off.

TIMELINE

  1. Repository created
  2. FIRST SEEN BY TESIGN
  3. Published on TESIGN

SAME DAY

  1. 01

    Ruffle

    Play old Flash files again

    A Flash Player emulator that runs old SWF games and animations in today’s browser.

    Use in the browser
    ★ 18.6k▲ +5 / 7d
  2. 02

    SuperSplat

    Edit 3D Gaussian splats in a browser

    A browser editor for inspecting, cleaning up and publishing 3D Gaussian Splats.

    Use in the browser
    ★ 10.1k▲ +7 / 7d
  3. 03

    Acode

    Write and run code on an Android phone

    A code editor for Android with a built-in Linux terminal and instant preview.

    Install to use
    ★ 7k▲ +8 / 7d
  4. 04

    Monica

    Keep passwords on your own device

    A local-first password vault for Android that also holds your 2FA codes.

    Install to use
    ★ 1k▲ +6 / 7d
  5. 05

    miu

    Open very large text files fast

    A minimal text editor that opens very large files instantly and draws colour emoji.

    Install to use
    ★ 151▲ +6 / 7d
  6. 06

    Blurt

    Dictate into any Mac app

    Hold a key, talk, and polished text lands wherever you are typing on your Mac.

    Install to use
    ★ 30▲ +6 / 7d
  7. 07

    Inspo

    Give a coding agent design references

    A library of real production websites your coding agent can study before it writes UI.

    Install to use
    ★ 157▲ +26 / 7d
  8. 09

    Nuclei

    Scan your servers for known weak spots

    A fast vulnerability scanner driven by simple, readable YAML templates.

    Install to use
    ★ 31.2k▲ +10 / 7d
  9. 10

    OpenSchool

    Run a school’s records in one system

    An open school platform: records, attendance, timetables, marks and reports in one place.

    Self-host
    ★ 26▲ +8 / 7d