2026-07-29Shipped
Continuity Format v1: signing handoffs between agents
Ed25519 source signatures, one-time HMAC destination binding, and auth-before-parse.
docs/architecture/adr/ADR-014-slipstream-continuity.md5 min read
Engineering
Evidence, not marketing.
Every article on this page links to its source evidence — an ADR, a test run, or a design decision. No fabricated scores. No invented certifications. No AI slop.
evidence-backed·source-linked·no fabricated claims
Articles
Writing about what we actually shipped.
Each post is adapted from a source document in the repo. If a claim sounds surprising, the source link at the bottom of the post is the place to check.
2026-07-29Shipped
Bi-temporal beliefs and the evidence graph
Valid-time, transaction-time, and why verification is a cascade rather than a score.
docs/architecture/adr/ADR-012-memory-model.md6 min read
2026-07-29Shipped
Why Zephr says 'not evaluated' instead of guessing
Trust over fluency: when evidence is missing or contradictory, the system stops rather than fabricate.
docs/product/vision.md4 min read
2026-07-29Shipped
Every connection is bound: immutable scope binding in Zephr
Project, repository, worktree — admitted once and immutable for the lifetime of the connection.
docs/architecture/adr/ADR-009-scope-admission-cloud.md5 min read
2026-07-29Shipped
How TrustBench tests AI memory like software
Deterministic scenarios, a single measured feature, and an honest list of what we have not evaluated yet.
docs/trust/TRUSTBENCH-EVIDENCE.md5 min read
Read the security model.
The documentation covers the architecture, tool contract, TrustBench methodology, and trust model in detail. Every claim links to its source.