23 tagged cognitive memory, measured the same way as everything else here.
Browse within: agent-memory 11context-engineering 7
Skill Claude CodeCodex
Author, measure and publish a YantrikDB knowledge pack. Use when asked to create a pack, turn documentation or a domain into a pack, package knowledge or skills for a local model, or publish to packs.yantrikdb.com. Covers the three tiers (constitution / corpus / coverage), the measurement that decides whether a pack…
Skill Claude CodeCodex
Persistent cognitive memory via YantrikDB's MCP server. Semantic recall, remember, belief revision, knowledge graph, contradiction detection, and procedural learning that survive across sessions and agents. Tools are auto-discovered from the server at runtime.
Skill Claude CodeCodex
Give this agent durable memory across sessions using YantrikDB. Use at the start of every session to load prior context, whenever the user or a job references past decisions, people, preferences, or earlier runs, and whenever something worth keeping is learned (a decision, a fact, a working method, a qualified lead, a…
Skill Claude CodeCodex
Persist a specific fact, preference, or decision the user just stated using CogmemAi, so it carries across all future sessions. Use the moment the user says "remember this", "remember that", "don't forget", "make a note", "keep this in mind for next time", "from now on", "going forward", or states a personal/project…
Skill Claude CodeCodex
After resolving any bug, save what broke, the root cause, and the fix as a CogmemAi memory so the same problem never has to be debugged twice. Use immediately after a bug is fixed, after diagnosing a flaky test, after recovering from a production incident, or after the user says "got it working", "that fixed it"…
Skill Claude CodeCodex
Before debugging any new bug, error, or unexpected behavior, search CogmemAi for an existing fix from this or any prior session. Use the moment a bug, error message, stack trace, failed test, or unexpected behavior appears, BEFORE running diagnostic commands or reading code. Eliminates duplicate debugging across the…
Skill Claude CodeCodex
Cortadel is a self-hosted, bi-temporal graph memory server for AI agents — one .NET container exposing a REST API and an MCP endpoint over FalkorDB or Memgraph, with intent-aware writes (store/invalidate/delete-entity/touch/resolve), LLM-verified dedup with a negation guard, and hybrid BM25+vector+RRF retrieval…
Skill Claude CodeCodex
Retract or permanently erase a Cortadel memory. Use when the user says "forget that...", "X is no longer true", "that's outdated", "delete this memory", or "permanently remove ". Default path is a natural-language retraction that keeps history queryable; hard, unrecoverable deletion only happens on an explicit…
Skill Claude CodeCodex
Run Cortadel entity reconciliation and review queued merge suggestions with the judge's confidence and reasoning. Use when the user asks to find or merge duplicate entities, run reconciliation, or review pending merge suggestions. mem0 has no equivalent — it has no reversible entity-reconciliation engine.
Skill Claude CodeCodex
Use when an agent should pick work up from Engram quickly and leave behind a clean structured handoff for the next session. Best for multi-step coding, investigations, releases, debugging, and any task where recent decisions and open loops matter.