claude-memory/graph/solutions/cognitive-memory-v30-rich-edges-hybrid-embeddings-mcp-server-9ea720.md

id	type	title	tags	importance	confidence	created	updated	relations
9ea72015-0b85-4a42-9ae1-144866f8d86f	solution	Cognitive Memory v3.0: Rich Edges + Hybrid Embeddings + MCP Server	cognitive-memory mcp architecture upgrade	0.9	0.8	2026-02-19T20:10:42.128691+00:00	2026-03-01T22:16:57.253418+00:00	target type direction strength edge_id dc6b6c6f-1319-47cf-a691-dd40751ff121 BUILDS_ON incoming 0.85 78728fca-82c7-4c30-b677-aadc663fb40b target type direction strength edge_id 89f32ef3-2d87-4b8c-aa6e-ce5a7f60566c BUILDS_ON incoming 0.8 6100de8d-c1dc-4ec9-8981-5c65a396da0e target type direction strength edge_id b1ba1b27-d2bf-44f9-a1f5-0ace2017dc18 BUILDS_ON incoming 0.8 f5227880-ea2c-4330-b7f1-eb367fc12c9e target type direction strength edge_id dc9c2638-360e-4e15-990c-76fcd16672c0 FOLLOWS incoming 0.8 30dd2fb7-f75f-4083-8b7c-52b8ce95cfc8 target type direction strength edge_id a41644f1-2dd1-4706-8fc8-e2242c1702cb FOLLOWS incoming 0.85 aea53b08-79a6-446a-bd1c-13f37b872c4e target type direction strength edge_id 089f4cd8-4b2b-49a5-aac1-af2811b8ea7d RELATED_TO incoming 0.8 2f7fc7c4-66b6-44d1-be62-2ba56af9b687 target type direction strength edge_id 8023fae6-eec1-4c93-bac8-1bd85dd61bae BUILDS_ON incoming 0.76 454fe3a6-e243-4cc0-bb9a-f12426f8deb3 target type direction strength edge_id ee85bf89-93f0-48e4-b911-7ddc18a735b5 BUILDS_ON incoming 0.85 bc703713-c85f-478c-be2c-0f0cd35f53c7 target type direction strength edge_id ab3ffc18-1707-42ff-ad7e-bffb16f6fdef BUILDS_ON incoming 0.75 13e98a58-b81d-49b0-89b9-0f23d3d24657 target type direction strength edge_id 21be13ae-c01b-4bf1-917a-9e1ef18312a8 RELATED_TO incoming 0.6 776d09a5-d1b3-4fe3-ac8a-5b41e40460d1 target type direction strength edge_id 2d6f02bc-5a7c-404d-a566-36107aaaf6e6 RELATED_TO incoming 0.82 f30f5536-be57-4afc-ad64-bb4e2b84bc19 target type direction strength edge_id e301095c-7d4c-45d8-8352-9491e4ad6603 BUILDS_ON incoming 0.73 2eee0082-215a-41b9-90bc-ea2d757138ff

Major upgrade to cognitive-memory skill. Phase 1: Rich edges as first-class markdown files in graph/edges/ with bidirectional frontmatter refs (edge_id field). relate() returns edge_id string instead of bool. Cascade deletion on memory delete. CLI: edge-get, edge-search, edge-update, edge-delete. Phase 2: Hybrid embedding providers (Ollama local + OpenAI optional) with automatic fallback chain. _config.json stores provider settings (gitignored). Dimension mismatch safety triggers re-embedding on provider switch. Phase 3: MCP server (mcp_server.py) with 18 tools via JSON-RPC 2.0 stdio protocol. Registered in ~/.claude.json. Phase 4: Updated SKILL.md, SCHEMA.md, feature.json to v3.0.0. Index version bumped from 1 to 2 (adds edges section). All stdlib-only, no external dependencies.