Skip to content

webmachinelearning/prompt-api

View on GitHub ↗Related repositories →

💬 A proposal for a web API for prompting browser-provided language models

active 2025-01-282026-06-24 (UTC)

Partial coverage11,977 / 13,470 hourly files (89%) · 2 absent upstream · 1,489 failed, retryable2025-01-262026-08-10 (UTC)— sampled evenly across the window, so rankings and trends hold; absolute counts scale up.
Events
676
Pushes
60
Pull requests
48
Issues
77
Stars
177
Forks
33

Activity over time

Daily event counts in the loaded window

Line chart, 513 days from 2025-01-28 to 2026-06-24. Pushes: 60 total, peak 6 in a day. Pull requests: 48 total, peak 6 in a day. Issues: 77 total, peak 10 in a day. Comments: 181 total, peak 10 in a day. Stars: 177 total, peak 4 in a day.

  • Pushes
  • Pull requests
  • Issues
  • Comments
  • Stars

Stars, PRs, issues and forks are under-captured in the later part of this window. GH Archive progressively stopped capturing non-push events during 2026 — −95% or worse by the end of the window. Every series here except Pushes fades for that reason, so a decline above reflects the archive, not this repository. Pushes stay reliable throughout, so read them, and the contributor counts derived from them, as the real signal. Data health has the measurements.

Top contributors

Pushes, PRs, issues, reviews and comments — stars and forks excluded, so this is contribution rather than popularity

Recent activity

Latest issues, pull requests and releases

  • Issue comment#169reillyeon2026-05-30 01:34
    [Tag Review] - Model selection and availability
  • Issue comment#89nalyd892026-05-03 10:45
    Add multiple modalities in a single message
  • Issue comment#202GaurangTandon2026-04-21 04:31
    Feature request: Add `LanguageModel.isValidConstraint()` to check the validity of responseConstraint ahead of time
  • Pull request#201michaelwasserman2026-04-09 22:56
  • Issue comment#200tomayac2026-04-07 08:58
    Prompt API Demo Project - LazyBookmarks
  • Issue#177michaelwasserman2026-04-06 22:17
    [Tag Review] - Quota vs. context window
  • Issue#197sushraja-msft2026-03-28 00:21
    Use of dictionary for LanguageModelCreateOptions , LanguageModelPromptOptions
  • Issue comment#196michaelwasserman2026-03-27 23:08
    Update sampling parameter sections for experimentation
  • Issue comment#193noamr2026-03-11 21:40
    Make input strings nullable to avoid unintended coercion
  • Issue comment#193reillyeon2026-03-11 21:24
    Make input strings nullable to avoid unintended coercion
  • Issue comment#192michaelwasserman2026-03-10 20:03
    Rename API input usage features
  • Issue comment#192jakobhoeg2026-03-10 19:59
    Rename API input usage features
  • Issue comment#177isaacahouma2026-02-28 01:35
    [Tag Review] - Quota vs. context window
  • Pull request#192isaacahouma2026-02-21 00:19
  • Pull request#189isaacahouma2026-02-20 20:59
  • Issue comment#190michaelwasserman2026-02-20 04:28
    Language support question: Prompt API seems to understand non-en/es/ja inputs when inputLanguage is omitted (e.g., hu)
  • Issue#188michaelwasserman2026-02-18 23:00
    Crash analytics telemetry question
  • Issue comment#188michaelwasserman2026-02-18 23:00
    Crash analytics telemetry question
  • Pull request#189isaacahouma2026-02-11 22:51
  • Issue#187michaelwasserman2026-02-03 21:51
    Batch inference API for efficient parallel prompt processing
  • Issue comment#186michaelwasserman2026-02-03 21:49
    Lightweight single-turn prompting mode
  • Issue comment#186cb8382671-cpu2026-01-31 23:20
    Lightweight single-turn prompting mode
  • Issue comment#186cb8382671-cpu2026-01-31 23:19
    Lightweight single-turn prompting mode
  • Issue#181anssiko2026-01-30 12:12
    [Tag Review] - Structured Output
  • Issue#170anssiko2026-01-30 12:12
    [Tag Review] - Interoperable model parameters

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 177 stars here means stars gained during the window, not the repo's star count.