Project Status
Ultimate Memory is being built design-first: the complete system — requirements, architecture, data model, and every load-bearing decision with its rationale — was designed and reviewed before implementation began. That design is public in the repository and is the authority these docs summarize.
There is no installable release yet. If you need a working memory library today, this isn't one — yet. If you want to follow (or join) a system being built in the open against a fully argued design, read on.
What exists today
- The complete design — in
plan/: requirements, binding per-subsystem designs, the research and analyses behind them, and a build-order roadmap. - The decision log —
decisions.md: every architecture decision (D1, D2, …) with context, rationale, and its later refinements. If you want to know why something is the way it is, start there. - Design-conformance evals — a suite of acceptance checks (in
plan/implementation_evals/) that judge the implementation against the binding design as it lands. - Early scaffolding — the Python project skeleton and CI are in place; pipeline functionality is landing phase by phase.
The build order
Implementation follows plan/plans/roadmap.md — nine phases, each keyed to the designs it realizes:
| Phase | What it delivers |
|---|---|
| 0 | Foundations: scaffolding, migrations, task queues, the eval harness |
| 1 | Walking skeleton — one document end-to-end, minimal retrieval |
| 2 | Truth machinery — entity resolution, adjudication, supersession |
| 3 | Evidence lifecycle — document versions, watched sources, efficient re-ingestion |
| 4 | Projections — the knowledge graph and the browsable corpus filesystem |
| 5 | Retrieval complete — full query surface, MCP/CLI, the consumption skill |
| 6 | Plane K — compiled and authored knowledge pages |
| 7 | Scale and operations — backfill, load tests, budgets, hard-delete end-to-end |
| 8 | Competitive benchmarks — published methodology and results |
How these docs grow
These pages are part of the repository and ship with the code: every change that alters user-facing behavior updates its documentation in the same pull request. As each phase lands, its pages appear here — getting started, ingestion and connectors, retrieval, configuration, deployment, and the API/CLI/MCP references. Until a page exists, the design documents linked above are the truth.
Following along
- Watch the GitHub repository — work lands as reviewed pull requests referencing roadmap work packages.
- Read the decision log for the ideas; skim merged PRs for the build.