memory

Featured

Recall reviewed lessons or deliberately mine and curate experience. Use when: prior evidence can change an action, or learning is requested; no mandatory recall or lesson.

AI & Automation 434 stars 40 forks Updated today Apache-2.0

Install

View on GitHub

Quality Score: 97/100

Stars 20%
88
Recency 20%
100
Frontmatter 20%
70
Documentation 15%
100
Issue Health 10%
50
License 10%
100
Description 5%
100

Skill Content

# Memory Use maintained experience only when it helps an actual task. Memory is optional: no mandatory recall at RPI entry, lesson at completion, worksheet, page quota or background mining. A trivial edit can proceed directly to implementation. ## Choose one operation | Need | Read on demand | |---|---| | An earlier constraint may change the next action | [Recall](references/recall.md) | | Learn from a bounded set of episodes, failures or corrections | [Mine / learn](references/mine-learn.md) | | Update, qualify, consolidate or retire a supported claim | [Curate / qualify / retire](references/curate.md) | | Find repeated operational friction in supplied history | [Toil evidence](#toil-evidence) | Mine/learn includes bounded verdicts, corrections and failed or harmful reuse; it is not a required completion step. The optional [OKF page profile](references/learn/okf-page-profile.md) checks structure only. Do not load every operation reference just because Memory was selected. ## One authority per fact BD or the caller's tracker owns work/status/dependencies/handoffs; Git owns content and delivery history; native sessions and CASS own episode evidence. The caller-selected reviewed external Markdown topic pages hold reusable claims, not another work account. Search and update an existing topic page before making a new one. Do not make one lesson file per session, copy a transcript lake, or silently initialize a memory store. Source evidence is not policy. A useful entry sta...

Details

Author
boshu2
Repository
boshu2/agentops
Created
10 months ago
Last Updated
today
Language
Go
License
Apache-2.0

Bundled in these plugins

Similar Skills

Semantically similar based on skill content — not just same category

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
AI & Automation Listed

memory-recall

Retrieve relevant project memory before acting on a task — checking past decisions, related episodes, and semantic facts so work doesn't contradict or duplicate what's already known, following the read-before-reasoning discipline. Use before starting any non-trivial task, before proposing an architectural approach, or when something in the current task sounds like it might have come up before.

1 Updated 1 months ago
NITISH-R-G
AI & Automation Listed

memory-recall

Recalls durable Atmina memory with verify-before-act. Orients, matches applies_to via exhaustive list_files (not search), searches wiki/ with recency boosts, reads the smallest set, and verifies artifact claims on the computed attestation block before acting — never substituting a near match, never writing memory. Use when recalling, looking up, or acting on a decision, procedure, fact, preference, relationship, or open question already on file in an Atmina Knowledge Base, or when the user asks to remember, look up, or bring them up to speed.

0 Updated yesterday
latentminds-ai