Unverified50% confidenceFactExact time
All three kinds of LedgerLens memory (episodic, semantic, and procedural) are stored as graph nodes and edges: episodic memory as Session nodes with a Message chain, semantic memory as Finding nodes with a full-text index, and procedural memory as Playbook and PlaybookStep nodes.
1
Sources
50%
Confidence
Long-term
Relevance
10/18/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe so-called memory provided by current mainstream tools (Claude Code, Cursor, Codex) is essentially a "storage" layer, that is, stuffing markdown files in full into the context window at the start of a session.71% similarUnverifiedA memory system is usually accomplished through the collaboration of three components: writing (extracting facts, rules and decisions worth retaining long-term from conversations), retrieval (recalling relevant entries by semantic similarity or keywords), and injection (automatically splicing the recalled content into the system prompt or the first round of context).70% similarUnverifiedparadigm-memory organizes memories into a navigable cognitive map rather than a single large text file.69% similarUnverifiedCompared to a storage layer, a memory runtime is responsible not only for reading and writing data, but also for the state management logic of runtime behaviors such as memory creation, indexing, expiration, merging, and conflict resolution.69% similarUnverifiedGraphicle's memory retrieval unit is a node on the code graph rather than a free-text chunk, strongly binding memory to code locations.68% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1063703API
curl https://kongchang.com/api/v1/knowledge/claims/1063703MCP
get_claim(id=1063703)