Skip to content

A privacy-first Android chat app that runs large language models entirely on-device. No internet, no cloud, no tracking. Built with Kotlin, Jetpack Compose, and llama.cpp with optimized ARM NEON/SVE inference.

active 2026-04-042026-05-29 (UTC)

Complete coverage26,550 / 26,550 hourly files (100%) · 2 absent upstream2023-08-152026-08-25 (UTC)
Events
70
Pushes
34
Pull requests
0
Issues
9
Stars
16
Forks
3

Activity over time

Daily event counts in the loaded window

Line chart, 56 days from 2026-04-04 to 2026-05-29. Pushes: 34 total, peak 7 in a day. Pull requests: 0 total, peak 0 in a day. Issues: 9 total, peak 5 in a day. Comments: 6 total, peak 3 in a day. Stars: 16 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

ContributorContributionsPushesPRsComments
jegly453404
aryoda4002

Recent activity

Latest issues, pull requests and releases

  • Issue#7jegly2026-04-21 03:32
    Disallow users switching chat during a conversation (LLM generating tokens to answer)
  • Issue comment#4jegly2026-04-20 00:58
    Custom prompt is not stored when leaving the settings
  • Issue comment#4aryoda2026-04-19 14:48
    Custom prompt is not stored when leaving the settings
  • Releasejegly2026-04-19 09:00
  • Issue#5jegly2026-04-19 06:40
    OfflineLLM crashes when a prompt generates token and I open a new chat in parallel
  • Issue comment#5jegly2026-04-19 06:40
    OfflineLLM crashes when a prompt generates token and I open a new chat in parallel
  • Issue#4jegly2026-04-19 06:32
    Custom prompt is not stored when leaving the settings
  • Issue#4jegly2026-04-19 04:51
    Custom prompt is not stored when leaving the settings
  • Issue comment#4aryoda2026-04-19 00:49
    Custom prompt is not stored when leaving the settings
  • Issue#5jegly2026-04-19 00:10
    OfflineLLM crashes when a prompt generates token and I open a new chat in parallel
  • Issue#5jegly2026-04-19 00:10
    OfflineLLM crashes when a prompt generates token and I open a new chat in parallel
  • Issue#5aryoda2026-04-18 15:03
    OfflineLLM crashes when a prompt generates token and I open a new chat in parallel
  • Issue#3aryoda2026-04-17 23:10
    Spech2Text > language translation > text2speech (all offline)
  • Issue#2jegly2026-04-17 05:26
    Request disclosure on AI coding agent use
  • Issue comment#2jegly2026-04-17 05:25
    Request disclosure on AI coding agent use
  • Issue comment#1jegly2026-04-14 02:57
    Error: loadModel() failed
  • Releasejegly2026-04-04 03:49
    OfflineLLM

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 16 stars here means stars gained during the window, not the repo's star count.