Status

Research Progress

A dated record of completed work, current work and what comes next. Every completed stage ends with automated tests on the target machine and a written report.

What we are building: a guard that lets AI models reach an organisation’s data only within their rights, and a safe long-term memory for a personal AI.

Memory pilot
Completed
Engine stages closed
G0, G1
Automated tests in a full run
2,600+
Registered decisions and rules
480+
Formal-verification stages accepted
3
Research notes published
8

Ahead

  1. Now

    The engine at scale (G2)

    In progress

    The first part of G2 is nearly complete; large-scale measurements are under way. We will publish them once they are final.

  2. Later

    A port of the core to Rust

    Planned

    The core of the engine will be rebuilt in Rust.

Completed

  1. Engine foundation complete (G1)

    Completed

    The foundation of the memory engine passed an independent code audit and three rounds of re-checks. The stage closed only when no critical finding remained. Every decision is registered and linked to the tests that check it.

  2. New memory architecture

    Completed

    New memory architecture adopted, built on the 41 axioms and 12 invariants set in September. The protocols were fixed before any engine code was written. Mutation testing of the pilot found 34 gaps in its tests; each is now a required check for the new engine.

  3. Memory pilot completed

    Completed

    Four rounds of external audit checked whether the prototype kept its own promises; the last found nothing new. A first load test was run on large synthetic stores.

  4. First controlled evaluation with models

    Completed

    Two agent models from different providers worked with the memory prototype only through the controlled access layer. On a closed synthetic task set, both answered all 13 memory-dependent tasks correctly with the memory; without it, both stated that the answer could not be known instead of guessing, and no answer cited a wrong record. In an adversarial trial with nine goals — such as reading another area, writing as someone else or going around the access layer — neither model reached a goal. The providers’ own safeguards limited part of that trial, so we treat it as a first check, not a security result.

  5. Scale and a controlled access layer

    Completed

    Reading and writing were measured on stores of up to 100,000 entries and met the target. Models now reach the memory only through one local access layer: a separate pass for every run, a tamper-evident log of every call, and an independent checker that verifies a run without trusting the access layer itself.

  6. Failures, recovery, reading and write protection

    Completed

    The prototype was tested against crashes and interrupted writes, with no losses and no duplicates after recovery. Agents gained scoped reading, in which a record outside a reader’s area is indistinguishable from one that does not exist. Write protection against memory poisoning was added and tested against a catalog of attacks.

  7. Memory pilot begins

    Completed

    The first stages of a working memory prototype: a contract for records, a journal that is never rewritten, a single gate for every write, answers to “what was true then” and “what was known then”, corrections without rewriting history, and obligations that are not lost.

  8. Formal verification track opened

    Completed

    Three preparatory stages were completed and accepted: a baseline of definitions, a targeted review of existing verification work, and a register of proof obligations — the properties the memory must be proven to have.

  9. Implementation and proof plans

    Completed

    A detailed plan for implementing and accepting the memory, and a separate plan for its formal proofs.

  10. First research notes

    Completed

    Research Notes 001–003 on continuity, reasoning effort and revision.

  11. Public research layer

    Completed

    This website, with research directions and concept visuals.