# orailnoor/cross-platform-llm-client

A unified cross-platform AI client supporting seamless transitions between standard cloud APIs and on-device, offline execution of custom and uncensored language models.

Repository: https://github.com/orailnoor/cross-platform-llm-client
Canonical: https://ross.abutalabs.com/products/cross-platform-llm-client
Language: C++
License: MIT
License Family: permissive
Last push: 2026-07-21T02:24:29+00:00

## Health v2 (maintenance only)
Score: 72/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 93, release rhythm 81, longevity 9
- inputs: {"age_days": 130, "days_push": 44, "days_rel": 44, "gap_med": 84, "n_releases_24m": 2}
- flags: young
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1051, forks 212 (observed 2026-08-28T04:03:23.046366+00:00)

## What it is
PrivateLM is a cross-platform AI chat client built with Flutter that unifies local on-device LLM inference (GGUF models with Vulkan GPU acceleration on Android) with cloud API access to providers like OpenAI, Anthropic, and Gemini. It supports multimodal text-and-image chat, persistent local storage of sessions, and automatic device-based configuration of context and token limits.

## Use cases
- run uncensored language models offline on my android phone
- chat with local gguf models without internet
- switch between local and cloud llm providers in one app
- private ai chat that keeps data on device
- run vision models like qwen2-vl on mobile
- generate images on-device with a phone gpu
- unified client for openai anthropic and gemini apis

## When to choose
- you want offline, on-device LLM inference on Android with GPU acceleration
- you need a single client that falls back to multiple cloud providers
- privacy matters and you want chats stored locally only
- you want multimodal (text + image) chat with both local and cloud models

## When to avoid
- you need local inference on iOS or desktop, which is not supported yet
- you require heavy cloud-only workloads beyond what phone hardware can run
- you need a server-side or API-first integration rather than an end-user app

## Facets
- artifact type: application
- maturity: active
- function: llm-inference, chatbot, chat-interface, image-processing, http-client, state-management, file-upload
- domain: large-language-models, chatbots, artificial-intelligence, mobile-development, privacy, cross-platform
- platform: cross-platform
- tags: gguf, on-device-inference, vulkan-gpu, flutter-app, local-first, multimodal-chat, cloud-api-fallback, uncensored-models, hive-storage, getx, android, mobile, web-server, flutter

## Member repositories
- orailnoor/cross-platform-llm-client (main) score 72

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:23.046366+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T07:00:10.212148+00:00, confidence not recorded.
  - readme: https://github.com/orailnoor/cross-platform-llm-client (fetched 2026-08-28T04:03:23.046366+00:00, sha 56d9ff11e4dd)
- Data as of 2026-08-30T08:39:29.467469+00:00.