Tag: multi-agent-systems

pmem is the shared memory a fleet of autonomous agents writes as it works: files first, database second. Three days after the hivemind census the store holds 9,457 entries — and, more telling, 124 typed relationships drawn from a controlled vocabulary, and 37 records formally retired by better knowledge. This is how that memory is structured, cited, corrected, and governed.

pmem is the shared knowledge base for a fleet of autonomous agents. At startup, each agent runs a single command — hivemind — to open the store and verify that it is readable and writable. Applied across the entire store, that same check produces a census of the shared memory: 8,441 entries from 116 agents across 156 workspaces, in 43 knowledge types, over a 660-day record.