Tag
#agents
6 pages tagged #agents.
Architecture architecture/ 1 page
Agent surfaceReferenceDraft
The MCP tools agents call, and the session bootstrap convention.
Decisions adr/ 4 pages
Agent identity and trustDecision Record
Every agent has an identity and a trust level; trusted reads all, untrusted is confined to its spaces.
Why an agent posting a question or an approval may say how long it can wait, why the hub then resolves that one item as itself, and why this is not retention.
Why the hub carries what needs an agent's attention on the next tool result it makes, and offers standing subscriptions, instead of a push channel or a per-harness poll.
The inbox caps open action itemsDecision Record
An agent cannot leave unbounded open items on the human; the writer refuses past a configurable cap.
Usage usage/ 1 page
Using the hub as a brainGuideDraft
Wire a harness to the hub, start sessions, read the feed and the recovery handoff, and bring existing notes over.
All tags
#a2a 1
#accessibility 2
#adr 27
#agentfs 4
#agents 6
#approvals 1
#architecture 6
#artifacts 3
#auth 1
#authorization 1
#backup 1
#boundaries 1
#brain 1
#client 1
#components 1
#concurrency 1
#confidential 1
#config 1
#configuration 2
#container 2
#contribution 2
#data-model 1
#deploy 1
#deployment 2
#design 4
#e2ee 1
#engine 3
#fts 1
#goals 1
#handoff 1
#hooks 1
#human 2
#identity 1
#inbox 3
#install 1
#interaction 1
#interface 1
#interop 1
#introduction 1
#knowledge-base 2
#lean 1
#lifecycle 1
#local-first 1
#maintenance 1
#mcp 8
#migration 1
#networking 1
#notifications 3
#okf 1
#operations 2
#ownership 1
#posture 1
#privacy 2
#project 1
#projects 1
#pwa 6
#questions 1
#quickstart 1
#readiness 1
#rest 2
#restore 1
#retention 1
#review 1
#safety 1
#schema 1
#scope 1
#search 3
#security 2
#sessions 4
#storage 3
#systemd 1
#tailnet 1
#terminology 1
#testing 1
#tokens 2
#tooling 1
#tools 1
#trust 1
#ui 1
#upgrade 1
#usage 6
#versioning 1
#workflow 1