OfflineLLM
Private on-device AI chat for Android — runs any GGUF model locally via llama.cpp with ARM-optimised SIMD. Zero network permissions, encrypted settings, biometric lock, tamper detection. + GPU Acceleration
jegly/OfflineLLM
View on GitHub ↗Private on-device AI chat for Android — runs any GGUF model locally via llama.cpp with ARM-optimised SIMD. Zero network permissions, encrypted settings, biometric lock, tamper detection. + GPU Acceleration
OfflineLLM grew +12.9% in the last 30 days, ranks 516th of 1,057 in Personal Assistants / Agent Platforms, actively maintained, last commit today.
Star trajectory
115 days tracked+12.9% in 30d, above the Personal Assistants / Agent Platforms median of +2.4%.
Last commit today, fresher than the median of 8d.
How it compares in Personal Assistants / Agent Platforms
Ranked 516th of 1,057 by stars.
- Language
- Kotlin
- License
- Other
- Contributors
- 3
- Forks
- 27
- Watchers
- 5
- Open issues
- 0
- Releases
- 10
- Created
- 2026-04-04
- Stars this week
- +4
You've seen where OfflineLLM stands today.
Get the moves before everyone else: the 5 Personal Assistants / Agent Platforms repos climbing fastest, every Tuesday.
Free weekly digest. Double opt-in, unsubscribe anytime.