The runtime that powers the attention layer.
Memory, model routing, scheduling,
proactive execution. Open source.

// the manifesto

Most software waits for you. None of it notices.

Two layers between a person and the rest of their tools — the layer that holds the model of what matters, and the layer that acts on it without being asked — have been missing this whole time. Lila Core is the runtime that builds both.

Read the manifesto →
// what it is

Lila Core is the engine under Lila.

It exists because the surface a person uses — phone, laptop, Slack thread, any of it — is not the part that matters. The part that matters is the model of attention underneath: what is on a user's mind this week, who they're in the middle of a conversation with, what they captured at 11pm and meant to come back to. That model has to be persistent, it has to be portable across surfaces, and it has to be composed by something other than the user. Lila Core is the runtime that does that work.

// architecture

Transport-agnostic. Memory-centered. Routed.

Surfaces read from and write to a single working-memory store in Postgres. A consolidation runtime — scheduled and on-demand — folds new events into that memory through model-routed jobs. Nightly LLM-driven consolidation produces a generative working-memory layer the surfaces draw from. Source-ID receipts on every surfaced item. Surfaces are interchangeable; the runtime is the source of truth.

  surfaces          runtime             memory
  iOS                consolidator          working_memory
  web      ───►    model router    ───►    postgres
  slack              scheduler           + semantic recall
    ...              proactive ops       + source receipts
                          
                          
                       cron + on-demand
// repo

Read it, fork it, run it.

github.com/my92agsr/lila-core

MIT-licensed. Issues open. Architecture and contribution notes in the README.

// philosophy

Why this is open.

Surfaces are interchangeable. Memory is the substrate. The runtime that pays attention to a person's life shouldn't be a black box, so this one isn't — it can be inspected, forked, or replaced. The reference client that runs on top of it is lila.surf. The full argument for why this layer should exist at all is in the manifesto.

Built by Matt Walker.