rikkahub-sillytavern-android

RikkaHub Plus · Lantern

An AI chat client for Android that is also a SillyTavern-compatible endpoint

Chat out of the box · prefix caching saves tokens · memory that doesn't fade · character cards / lorebooks / presets imported with official SillyTavern semantics

English | 简体中文 | Divergence map | Divergence map (EN)

A deeply customized fork of RikkaHub (merged with upstream v3.0.0, plus 2150+ commits of additions), natively implemented in Kotlin + Jetpack Compose.

• Just want a good AI chat app: plug in any API and start talking — multi-provider, streaming, voice calls, plugin tools, memory, cache savings. No "tavern" concepts required.
• Migrating from desktop SillyTavern: character cards, lorebooks, presets, regex and themes import losslessly with official semantics — no Termux, no Node.js.

Both routes share the same client and don't interfere with each other.

Website & docs: rikkahub.luoca.cn · Documentation (installation, configuration, tavern imports, plugin development)

Tavern compatibility

Memory & caching

Multi-dimensional memory settings	Prefix divergence diagnostics (character-level diff)

This fork's exclusives

HuaDeng Settings (compatibility & helpers)	HuaDeng Settings (access & automation)	Jev decisioning

Plugin system

✨ Fork features

🗺️ Where this fork sits between its two upstreams (click to expand)

Two upstream lineages meet here — knowing them makes the diff readable:

rikkahub/rikkahub (original upstream, v2.5.6)
        │
        ├──► heikeyangle-code/rikkahub-plus (intermediate fork, mingli2)
        │            │  tavern system / macro engine / slash commands / group chats
        │            ▼
        └──► MiaoWuNYA/rikkahub-sillytavern-android  ← this repo
                     │  cache optimization / plugins / memory / proxy fix / on-device
                     │
                     ├─ also from orangechat & Tumin: three-layer memory, couples space,
                     │  life hub, appearance customization, early plugin system
                     └─ also ported from Rikkahub-Revised: semantic memory RAG, rolling compression

• vs. original upstream rikkahub: everything preserved; the tavern/plugin/memory work is purely additive
• vs. intermediate heikeyangle-code/rikkahub-plus (mingli2): the tavern core comes from it; this fork adds cache optimization, plugins, memory, proxy fix, voice, and privacy hardening on top
• vs. other same-origin forks: see Credits — feature provenance is stated per project

🚀 Quick start

1. Grab the latest APK from Releases (arm64-v8a, Android 8.0+)
2. Settings → Models & Services → Providers, add your API; then Default models & prompts to pick models for chat / title / compression
3. Start chatting. Want more:
   • Import a character card (Assistants page → import, PNG / V2 / V3 JSON; lorebooks and presets come along automatically)
   • Import lorebooks / presets / regex / QR (Settings → Extensions)
   • Try a SillyTavern theme (Settings → Preferences → Chat appearance → import theme)
   • Add plugins (Settings → Plugins → import ZIP; bundled plugins work out of the box)

In-app update: Settings → About → Check for updates (GitHub Releases API, with an auto-fallback mirror for mainland China)

💬 Chat features (this fork's core enhancements)

⚡ Prompt Prefix Cache Optimization

Major providers (DeepSeek / Kimi / Claude, etc.) offer automatic prefix caching: a byte-identical prefix to the previous request is a cache hit, billed far below the normal rate. But in chat, plenty of content changes every turn (timestamps, recent chats, memories, random numbers, rolling summaries) — one divergence kills the whole cache.

Drawing on the DeepSeek Harness prefix-stability design, this fork eliminates those divergence points one by one:

Diagnostics: a built-in prefix divergence view compares consecutive requests item by item, shows the common prefix and estimated hit rate, and supports character-level diff location — you can always see exactly why a cache missed. A prompt viewer also shows the exact prompt sent this turn.

Actual results vary by conversation shape: in steady, append-only chats the hit rate improves noticeably; the exact gain depends on how often content changes and on each provider's pricing.

🧠 Memory & Long Conversations

• Semantic memory RAG (ported from Rikkahub-Revised): memories split into FACT / EPISODIC, embedded with the vector model and retrieved via cosine similarity (with a lexical fallback of word terms + CJK bigrams); episodic memories get recency weighting; results are injected within a budget
• Three-layer memory (from orangechat/Tumin): a fixed-memory section (independently editable without touching the character card) + a recent-life stream (cross-conversation memory of the current chat; unread events from other conversations auto-injected) + long-term recall via lexical-overlap scoring; the stream is auto-summarized in the background past a threshold
• Enhanced memory_tool: a list read operation plus fact / episodic distinction — the model can review existing memories before writing or updating
• Memory management page: view / edit / delete entries per assistant
• Rolling context compression: past a threshold (auto-computed from the model's context window or set manually), a compression model rolls earlier turns into a summary (originals preserved, replaced only at request time), injected as a system message — staying in-window without losing persona or foreshadowing
• Recent chats reference: optionally inject the assistant's recent conversation list for cross-session continuity
• Transient-content pruning: web-search results / images / audio / video older than two turns are dropped from requests (with the message ID so the AI can retrieve the original via read_history_message)
• First-turn auto memory: the first turn injects the most recent memories (no relevance query exists yet), later turns recall by relevance — the AI knows you from the first message

Memory features (memory tool / RAG / three-layer memory / cross-window life stream) are on by default — memory helps the AI know you better and isn't sacrificed to save context. Existing assistants keep their settings and can opt out per assistant.

🧿 Jev decisioning (TypeSafe System One)

Settings → HuaDeng Settings → Jev decisioning. Jev is a dedicated small model that only judges — it never generates text (~100ms end to end, output tokens free). It mounts as an invisible decision layer inside the client: paste an API key and it works. Two takeover switches: