Skip to content

SALT

SALT flow animation

SALT keeps long context small. It compresses documents and whole conversations down to the sentences that carry the most information, spreading the budget across a document's themes instead of ranking everything by one score, so the minor points that answer real questions survive. Any model, plain text out, less compute in.

  • 🧂 salt


    Compress a document or dataset in one shot. The engine itself, and the surface the evaluation runs on.

    Usage

  • 🤖 saltChat


    A chat REPL where SALT is the conversation memory, so long chats and attached files stay recallable at a fixed prompt size. Each turn searches the files and the time the question names.

    Chatbot mode

  • 🔌 saltServe


    A persistent model server chats connect to and resume against with their cache still warm.

    Serving

  • 🤝 Agents


    Name smaller models beside the chat model and hand them work, with this conversation's memory selected for the task and nothing committed. One can answer a turn outright.

    Agents

  • 🔌 MCP server


    salt-mcp puts compression, conversation memory and the helper models behind the Model Context Protocol, for editors and agent runtimes, and reads only when told to.

    MCP server

  • 🎛 Options


    Every flag of the four commands in one line each, including the off by default switches that make long sessions better.

    Options

  • 🧩 Architecture


    The ideas behind the features: the keyword trie, coverage selection, the memory contract, and where each stage lives.

    Architecture

  • 📈 Results


    A 44.60 LongBench average with Llama 3.1 8B at a 20% token budget, per dataset.

    Results

  • 📝 Paper


    The EMNLP 2026 Main Conference paper behind all of it, with the abstract, the citation, and what changed in the repository since.

    Paper

🧭 New here

  1. Install the environment and the four commands.
  2. Compress one document and read what SALT kept.
  3. Chat with two files attached and watch the memory block choose which one to read, and what to remember from it.
  4. Read why selection spreads the budget across themes instead of ranking sentences.

📜 What each version changed

The Changelog explains what every version changed in plain language.

📝 Paper

SALT is described in a Main Conference paper at EMNLP 2026, held in Budapest, and available in the ACL Anthology and as arXiv:2607.17486. The Paper page carries the abstract and the citation, and explains how the selector the paper describes, tagged v1.0.0, relates to the coverage selector current releases default to.