Mneme Graph is here. 🧠⚡️ The era of graph-native memory starts now. mneme-cli@0.4.0 is live. Welcome to Mneme Graph.🔔 ▸ what just shipped every Mneme project now has TWO new default tables, auto-provisioned at signup: entities (id, kind, name, properties jsonb, embedding vector(1536)) relations (id, src_id, dst_id, kind, weight, properties jsonb) indexes auto-added: btree on kind / src_kind / dst_kind, GIN on properties. graph-structured memory, lives in the same Postgres schema as your pgvector tables. no separate graph db. no extra service. ▸ try it in 30 seconds $ npm i -g mneme-cli@latest $ mneme › /entity add person “vitalik” {“wallet”:“0xd8da6…”} ✓ entity #1 person:vitalik › /entity add token “MNEME” ✓ entity #2 token:MNEME › /relate person:vitalik holds token:MNEME {“since”:“2026-05-30”} ✓ edge #1 person:vitalik ─[holds]→ token:MNEME › /entity add person “jesse” › /relate person:jesse created token:MNEME › /neighbors 2 hops=2 ┌────┬────────┬─────────┬──────┐ │ id │ kind │ name │ hops │ ├────┼────────┼─────────┼──────┤ │ 1 │ person │ vitalik │ 1 │ │ 3 │ person │ jesse │ 1 │ └────┴────────┴─────────┴──────┘ › /path 1 3 max=3 ✓ path found · 2 hop(s) person:vitalik → token:MNEME → person:jesse shortest path = recursive CTE with array-based cycle detection. undirected traversal follows edges in both directions. cycle-safe. ▸ the killer move: hybrid retrieval pure vector search misses entities that ARE related but don’t embed similarly to your query. pure graph traversal misses fuzzy semantic matches. solution: do both, then rank by sim × decay^hops. await m.graph.semanticNeighbors({ embedding: queryEmbedding, seed_k: 10, hops: 2, decay: 0.5, }); one SQL roundtrip. ▸ SDK surface m.graph.addEntity({ kind, name, properties, embedding }) m.graph.addRelation({ src, dst, kind, weight, properties }) m.graph.neighbors(id, { hops, edge_kinds }) m.graph.path(srcId, dstId, { max_hops }) m.graph.semanticNeighbors({ embedding, seed_k, hops, decay }) m.graph.listEntities({ kind, name_like, limit }) ▸ what Mneme schemas look like now memory — memories, documents, kvs, events (pgvector) graph — entities relations hybrid retrieval (NEW) streams — live Base events auto-INSERT chat — schema-aware claude that knows ALL of the above four primitives. one schema. one wallet. one prompt. ▸ what’s next actions (write the chain — send / swap / vote / mint) lands next sprint. mneme keeps shipping. every 72 hours. CA: 0x3FcDbEBD5e7BaB79477cFDcA2CDCF6e904C27b07