agent memory
From Dontopedia, the open, paraconsistent wiki. (Last updated 2026-06-06.)
agent memory has 11 facts recorded in Dontopedia across 2 references, with 1 live disagreement.
Mostly:stores(2), uses(1), directly combines(1)
Maturity scale
raw canonical shape-checked rule-derived certifiedInbound mentions (2)
Other subjects in dontopedia point AT this entity as a value. These are inverse relationships — e.g. "X motherOf this subject" — and answer questions the forward facts can't. Grouped by predicate.
expressedOpinionAboutExpressed Opinion About(1)
- Lisamegawatts
ex:lisamegawatts
likesVersionOfLikes Version of(1)
- Lisamegawatts
ex:lisamegawatts
Other facts (10)
The long tail: predicates that appear too rarely to warrant their own section. Filter or scroll to find a specific one. Each row links to its source.
| Predicate | Value | Ref |
|---|---|---|
| Stores | Conversation History | [1] |
| Stores | Agent State | [1] |
| Uses | Neo4j Knowledge Graphs | [1] |
| Directly Combines | Knowledge Graphs With Agent Memory | [1] |
| Has Repo | neo4j-labs/agent-memory | [1] |
| Has Stars | 166 | [1] |
| Is | Graph Native Memory System | [1] |
| Matches Interest in | Lisa Mega Watts | [1] |
| Belongs to Category | Category 2 Agent Memory and Knowledge Graphs | [1] |
| Rdf:type | Concept | [2] |
Timeline
Timeline axis is valid_time — when each source says the fact was true in the world, not when Dontopedia learned about it. Retracted rows are kept for provenance; coloured stripes indicate the context kind.
References (2)
ctx:genes/lisa-watts/likeminded-projects-landscapectx:discord/blah/blah/4- full textblah-4text/plain3 KB
doc:agent/blah-4/86d36d15-9607-4cf7-8d97-9bbd2fe1f35fShow excerpt
[2026-01-19 23:01] ajaxdavis: Will have a think about a super simple stack that would be nicely abstracted so any thing like the above ideas could be built in top [2026-01-19 23:01] ajaxdavis: Would be fun to make a adventure game, have a l…
See also
Keep researching
Missing something or suspicious of what's here? Kick off a research session — a Claude agent will investigate, cite its sources, and file new facts into a dedicated context you can review before accepting into the shared view.