memory-save

Solid

DEPRECATED since B5 (2026-05-13) and disabled. Long-term-memory writes go through the wiki pipeline (Awareness layer, SessionRollupWorker, WikiCurator). Use when nothing — this skill must not be re-enabled; "merk dir" phrases belong to the normal brain pipeline.

AI & Automation 30 stars 11 forks Updated today MIT

Install

View on GitHub

Quality Score: 85/100

Stars 20%

Recency 20%

100

Frontmatter 20%

Documentation 15%

Issue Health 10%

License 10%

100

Description 5%

100

Skill Content

> **Note (B5, 2026-05-13):** This skill is disabled. The empty > `triggers:` block means it never matches a voice phrase, and the > `state: disabled` keeps both invocation paths (trigger and run-skill) > closed. Long-term-memory writes flow through the B5 pipeline > (Awareness → SessionRollupWorker → WikiCurator → Obsidian vault). > Full deletion is queued for the B4 hard-cut. # Memory Save (deprecated) Historical behavior, for reference only: the user stated a fact ("merk dir: X" / "remember this: X"), the trigger captured the tail as `content`, and the fact was persisted into core memory with a one-word spoken confirmation. That entire flow now lives in the brain pipeline plus the wiki tier (`wiki-ingest` for deterministic saves) — do not rebuild it here.

Details

Author: PersonalJarvis
Repository: PersonalJarvis/PersonalJarvis
Created: 2 months ago
Last Updated: today
Language: Python
License: MIT

Similar Skills

Semantically similar based on skill content — not just same category

AI & Automation Listed

using-memory

Use whenever you READ FROM or WRITE TO the agent-memory layer — recall a remembered fact, persist a durable fact about how the user wants to work, pin a hard rule, or correct a stored memory. READ via /ultra-memory:memory-recall (trusted CLI) or the type-scoped knowledge MCP; WRITE only through the memory verbs (/ultra-memory:memory-save, /ultra-memory:memory-pin, /ultra-memory:memory-verify, /ultra-memory:memory-edit, /ultra-memory:memory-inbox) — NEVER raw SQLite. Trigger before any memory read or write.

1 Updated 2 weeks ago

phense

AI & Automation Listed

memory-write

Captures a durable fact to project memory through the kit's safe write path (Poison_Guard secret/injection screening + home-path sanitization + dedup + conflict detection) — preferring the cmk MCP tools (mk_remember / mk_forget / mk_trust) when connected, falling back to the cmk CLI. Use when the user says "remember this", "note this", "save this", "from now on", "going forward", "I prefer", "I don't like", "we decided", "we agreed", or otherwise states a durable preference, decision, or environment fact worth carrying across sessions. Also covers correcting a saved fact ("update memory: X is now Y"), removing one ("forget about X"), and adjusting how much a saved fact is trusted ("trust this", "that's important — keep it", "that's not important / I'm not sure about that / low priority"). Skip throwaway chatter and facts that only matter to the current task.

6 Updated 4 days ago

LH8PPL

AI & Automation Listed

bettermemory

Verification-grade memory between sessions. Use bettermemory's MCP tools (memory_search, memory_show, memory_write, memory_verify, memory_record_use, etc.) instead of writing to files when the user asks you to "remember" something or references shared context from a past session. Default is to NOT call memory_search; only retrieve when the user references context you don't have ("my project", "the script we wrote") or a request is ambiguous in a way stored preferences could resolve. Every hit carries a staleness_verdict (calendar + path-drift + commit-drift); when it isn't "fresh", spot-check a claim before relying and call memory_verify to attest. Every use should record a claim_excerpt so retrievals stay auditable.

0 Updated today

0Mattias