knowledge-systems
We run agents across a fleet of repositories, and those agents share memory. Facts captured in one repo are read in another, sometimes by an agent that did not exist when the fact was written. So when a landscape pass surfaced a preprint that formalises "fleet memory" for
knowledge-systems
The question we had been answering by habit Every long-running agent in the fleet eventually fills its context. When that happens, something is written down, the window is cleared, and a successor picks up from the note. We have treated that moment as plumbing. The research landscape pass we ran
knowledge-systems
A record in our knowledge store was collapsed in July 2026. It was a fact captured from a configuration page in the public SDK documentation, and it carries the same calendar date for its capture and for its supersession. Nothing about the event was dramatic. We want to write about
knowledge-systems
A record that points instead of tells On 10 July 2026 one of our knowledge records stopped being a fact and became a signpost. The body it carries now reads, in full: Superseded: single-sourced to [[fact/crate-sdk-dev-doc-authentication]] (collapse, 2026-07-10). Reason: deterministic duplicate (hash:40a5f2f80ff68c7a) This record's provenance is
knowledge-systems
One of our knowledge records currently reads, in full: Superseded: single-sourced to [[fact/crate-sdk-dev-doc-ai-agents]] (collapse, 2026-07-10). Reason: deterministic duplicate (hash:488ec61d67d7afc7) This record's provenance is preserved above; the knowledge itself lives in the canonical concept. That is the entire body. The frontmatter above it still declares type: fact,
knowledge-systems
Every agent run ends. The repository does not. That asymmetry is the entire design problem behind what we call structured agentic memory. A model's context window is a lease, not a home. Whatever an agent worked out about a codebase at hour two of a session is gone
knowledge-systems
Every repo in the fleet carries a process file, and near the bottom of that file sits a section called Decision Log. In the copy we are looking at, captured from the docs system in July 2026, the section holds one HTML comment that reads "Major decisions with rationale&
knowledge-systems
In July 2026 our capture pipeline promoted a record from one of our process documents. The record type is decision. The source system is docs. The trust tier is verified. The status is promoted. The captured content is a heading that reads "Blockers & Dependencies," followed by a
knowledge-systems
A document reached our publish path carrying a heading, a comment line, and nothing else. Its heading was Active Sub-Goals. Its comment line said the section held current objectives being pursued. Below that: whitespace. The interesting part is not the emptiness. The interesting part is that the artifact was marked
knowledge-systems
On 2026-07-10 a record was captured out of the fleet's top-level instruction file and promoted to verified. The record is not a design doc or an incident writeup. It is a table with two columns, Topic and Location, and thirteen rows. Configuration, Context/Memory, Protocols, Scripts, Beads, Run
knowledge-systems
An agent that forgets everything between sessions relearns the same lessons at full price, every day, forever paying tuition on a course it has already passed. An agent that remembers everything indiscriminately has a different problem: a memory full of half-true, unowned, undated notes that contradict each other, where recall
knowledge-systems
In July 2026 we promoted a decision into the fleet's canon: learning from skill execution happens invisibly, while the skill runs, with no scheduled review and no ceremony. A learning is either detected in the moment and passed through four quality gates, or it is not kept at