Zephr

Use cases / Team lead

Your team's AI knowledgeshould survive tool switches.

Today Zephr gives every developer local continuity and one shared rule contract. Shared memory, cross-machine sync, and collaborative review are planned for the managed cloud and are not available — which is stated here, at the top, rather than discovered during a rollout.

Team memory planned (managed cloud)local rules shippedteam memory plannedno date committed
The problem

Every teammate starts from zero.

Without a shared evidence layer, each developer re-teaches the AI from scratch. A decision made in one session does not carry into another person's session, and project rules live in files that tools may or may not read.

Two developers, one decision, twice

Each side is a separate local graph today. Nothing is wrong with either record — the loss is that neither one knows the other exists.

Developer A · Claude CodeLocal only

Knows the auth decision

Captured the decision, cited the file, and had it reviewed. The record is complete and correct — and reachable from exactly one laptop.

~/.zephr/ledger.sqlite · machine A
Developer B · CursorRe-derived

Re-invents the same decision

Asks the same question a month later, gets a plausible answer, and captures it fresh. Two records now exist for one decision, and nothing reconciles them.

~/.zephr/ledger.sqlite · machine B

The managed cloud closes this by making the reviewed belief shared, scope-bound, and governed. Until the tenancy and security gates pass, it stays open.

Illustrative example — not live data. Cross-developer sharing requires the managed cloud and its tenancy gate.

What exists today

The foundations are in place. The sharing is not.

Zephr already gives every developer local continuity and a common tool contract, and the record format is the one a team tier would share. Three of the six capabilities below are shipped; the three that make it a team product are not.

  • Project rules via zephr_rules

    Shipped

    Worktree-scoped review and contradiction policies that every connected tool reads through the same contract, instead of an advisory file each client may or may not honour.

    eight-tool MCP contract

  • Local evidence graph per developer

    Shipped

    Each developer already carries their own admitted scope and provenance chain. The record format is the one the team tier will share — not a throwaway local variant.

    core evidence graph · ADR-012

  • TrustBench suite

    Shipped

    CI-blocking deterministic tests the team can run before any cloud claim exists. Trust behaviour is verified in your pipeline, not asserted in ours.

    deterministic suite · ADR-013

  • Team-scoped recall

    Planned (managed cloud)

    Shared verified beliefs, filtered by review state and organization admission, so a teammate inherits what was reviewed rather than everything that was ever captured.

    gated on the ADR-010 tenancy gate

  • Cross-machine sync

    Planned (managed cloud)

    Outbox up, delta pull down, with organization-tenant isolation adversarially tested before any external user exists.

    gated on the ZEP-1 security review

  • Collaborative review

    Planned (managed cloud)

    A shared review queue, contradiction resolution, and approval receipts as durable objects rather than chat messages.

    Review Phase B · designed, not built

Shipped capabilities run locally. Team-scoped capabilities depend on the managed-cloud security review (ZEP-1) and partner readiness (ZEP-231).

What is planned

Team memory, step by step — with no date attached.

The route from local continuity to shared memory is documented and gated on evidence. Each step below is a plan, not a schedule, and it is listed in the order the gates have to clear.

  1. 01

    Shared project rules

    Rules move from advisory files to governed policy. The Trust Firewall evaluates them before retrieval rather than apologising afterwards. Partly shipped: the rule contract exists, organization-wide policy does not.

  2. 02

    Team-scoped memory

    Beliefs bind to the project and its ref topology rather than to one user, so an admitted teammate inherits the reviewed set. Requires the managed cloud.

  3. 03

    Cross-machine sync

    The managed cloud stores the evidence graph and encrypted source manifests. Local mode remains the offline alternative, not a downgrade path. Requires the managed cloud.

All three steps planned (managed cloud)No ship date is committed for any of them.

Read the trust model.

The trust and security page explains how Zephr governs scope admission, review state, and audit receipts — the primitives team-scoped memory will be built on.