{"data":{"slug":"jegly-offlinellm","name":"OfflineLLM","tagline":"Private on-device AI chat for Android with local LLM support via ARM-optimised llama.cpp","github_url":"https://github.com/jegly/OfflineLLM","owner":"jegly","repo":"OfflineLLM","owner_avatar_url":"https://avatars.githubusercontent.com/u/239281279?v=4","primary_language":"Kotlin","stars":240,"forks":23,"topics":["android","android-ai","android-ai-app","android-llm","artificial-intelligence","edge-ai","gemma4","generative-ai","llamacpp","llm","local-ai","local-llm","local-llm-android","offlinellm","on-device-ai","privacy-first-ai","private-ai-assistant","private-local-ai","qwen3-5"],"archived":false,"github_pushed_at":"2026-08-18T11:37:55+00:00","maintenance_label":"Steady","stars_delta_30d":36,"url":"https://www.graphcanon.com/tools/jegly-offlinellm","markdown_url":"https://www.graphcanon.com/tools/jegly-offlinellm.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/jegly-offlinellm","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=jegly-offlinellm","description":"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","homepage_url":"https://jegly.xyz","license":"Other","open_issues":7,"watchers":5,"ai_summary":"An offline-capable Android application for private AI chat, supporting GGUF models using locally deployed AI frameworks like llama.cpp.","readme_excerpt":"## Install\n\nv5.1.1 ships as a single **Vanilla** APK — bring your own GGUF model and import it from Settings.\n\n> **Requires Android 13+ and arm64-v8a.** Vast majority of Android devices since 2019 are arm64.\n\n1. Download from [Releases](https://github.com/jegly/OfflineLLM/releases)\n2. **Settings → Apps → Install unknown apps** → allow your file manager\n3. Open the APK, tap Install, complete onboarding\n4. Settings → Model → **Import GGUF Model** (download one from [HuggingFace](https://huggingface.co))\n\nOr via ADB:\n\n```bash\nadb install OfflineLLM_V5.1.1_Signed_Release_Vanilla.apk\n```\n\n**Tamper detection:** release builds verify the APK signing certificate at launch. The app exits with an \"Unverified App\" dialog if anyone has re-signed the APK with a different key.\n\n---\n\n## License\n\nApache License 2.0. llama.cpp backend: MIT. Native wrapper adapted from [SmolChat-Android](https://github.com/shubham0204/SmolChat-Android) (Apache 2.0).\n\n---\n\n<div align=\"center\">\n\n**[www.jegly.xyz](https://www.jegly.xyz)**\n\n</div>","github_created_at":"2026-04-04T00:37:32+00:00","created_at":"2026-07-15T11:01:07.964958+00:00","updated_at":"2026-09-20T05:06:55.797526+00:00","categories":[{"slug":"inference-serving","name":"Inference & Serving","url":"https://www.graphcanon.com/categories/inference-serving","markdown_url":"https://www.graphcanon.com/categories/inference-serving.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/inference-serving"},{"slug":"llm-frameworks","name":"LLM Frameworks","url":"https://www.graphcanon.com/categories/llm-frameworks","markdown_url":"https://www.graphcanon.com/categories/llm-frameworks.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/llm-frameworks"}],"tags":[{"slug":"android","name":"android"},{"slug":"local-llm","name":"local-llm"},{"slug":"on-device-ai","name":"on-device-ai"},{"slug":"privacy-first-ai","name":"privacy-first-ai"},{"slug":"private-local-ai","name":"private-local-ai"}],"trust":{"provenance":{"is_fork":false,"github_id":1200895843,"owner_type":"User","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-09-20T05:06:54.017Z","maintenance":{"label":"Steady","score":60,"methodology":"github_public_v1","releases_90d":2,"days_since_push":32,"last_release_at":"2026-08-18T11:37:55Z","stars_delta_30d":36,"open_issues_delta_30d":7},"security_summary":{"status":"no_lockfile","scanner":null,"low_count":0,"high_count":0,"last_scan_at":"2026-07-15T11:01:09.178Z","medium_count":0,"scan_profile":"none","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-09-20T05:06:55.049Z"},"languages":{"value":["kotlin"],"source":"github.language","observed_at":"2026-09-20T05:06:55.049Z"},"license_spdx":{"value":"Other","source":"github.license","observed_at":"2026-09-20T05:06:55.049Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":null,"constraints":null,"when_to_use":["Need a privacy-first solution that operates fully offline","Working in environments without internet access","Require ARM-optimised performance on mobile devices"],"when_not_to_use":["Seeking real-time updates or cloud-based AI services","Prioritize integration with web-based features or platforms","Running x86 architecture, as the tool is optimised for ARM"],"source":"enrich:decision_facts","observed_at":"2026-07-17T10:28:58.462Z"},"constraint_facets":null,"decision_summary":[{"label":"Adopt for","value":"OfflineLLM provides private on-device AI chat for Android with ARM-optimised llama.cpp support, ideal for scenarios requiring privacy and offline capabilities."}]}}