aikohanasaki/SillyTavern-MemoryBooks

Saves SillyTavern chat memories to lorebooks

What it solves

It addresses the problem of losing important plot points and character developments in long AI chats. As conversations grow, older messages often fall out of the active context window, causing the AI to forget key events, decisions, and relationships.

How it works

This extension converts completed scenes or specific portions of a chat into structured, editable lorebook entries. These entries act as a durable record of the conversation, allowing the AI to access critical information without needing the entire raw chat history to be sent with every request.

Who it’s for

Users of SillyTavern who engage in long-term roleplay or storytelling and want to maintain consistent narrative continuity over time.

Highlights

  • Supports both manual control over scene boundaries and automated memory creation.
  • Preserves specific details like promises, discoveries, and unresolved threads.
  • Integrates with SillyTavern's lorebook system to manage long-term memory.

Related

  • Project
    YuriyLin/PaperRead

    PaperRead is a desktop research workspace that guides you from paper discovery to deep reading. It helps you search, organize candidates, track reading status, generate grounded summaries, and read with AI assistance — all in a single Traditional Chinese-first interface.

  • Project
    Tiledesk/tiledesk

    An open-source live chat and conversational app development platform that integrates AI chatbots with human agents across multiple channels.

  • Project
    bibinprathap/VeritasGraph

    VeritasGraph is an open‑source Python framework that replaces vector‑based RAG with a graph‑plus‑tree retrieval engine. It builds a provenance‑rich knowledge graph from documents, lets LLM‑driven agents reason over that graph, and provides a Studio UI for governed agent orchestration (guard‑rails, memory, tool catalog). It runs locally via Ollama or in production with Docker + Neo4j, and offers an MCP server for zero‑trust IDE integration. Key benefits are deterministic multi‑hop retrieval, verifiable citations, explicit abstention, and full on‑prem privacy.

  • Project
    facebookresearch/atlas-lean

    ATLAS is a research project that uses large language models to automatically translate textbook mathematics into formal Lean 4 libraries, providing reusable, machine‑checkable mathematics for theorem proving and AI research.