6,588 tagged Memory and context, measured the same way as everything else here.
Browse within: LLM 232agent 160agent-memory 154cli 133agentic-ai 126agents 119ai-memory 111claude-code-plugin 80ai-coding 76cursor 73context-engineering 60knowledge-base 59ai-tools 58skills 57
dimosgit/grounded-knowledge-engine
Skill Codex
Use Grounded Knowledge Engine to select an isolated workspace, answer from local evidence, resume an explicitly identified project, create an explicit project checkpoint, and retain durable knowledge. Trigger when a user asks about their documents, workspace or client context, previous research, project state…
Skill Claude CodeCodex
Capacity trend analysis and projections: disk growth rates, resource consumption patterns, and time-to-exhaustion estimates. AUTO-CONSULT when: disk usage exceeds 60%, memory usage is consistently high, user asks about server capacity or growth trends, or during periodic maintenance reviews.
Skill Codex
A guided tool for moving AI coding memories, settings, and project knowledge between computers or coding tools using dotvibe.
Skill Claude CodeCodex
A knowledge-base assistant for managing stored files and generating content from them, with optional online search and importing. It requires an API key and supports configuration through a file or environment variable.
Skill Claude CodeCodex
A tool for mapping what a user knows, does not know, assumes without saying, and has not yet considered. It records these four areas as a cognitive map that can be reused later.
Shivansh12t/claude-code-memory-bank
Skill Claude Code
Project context memory system. Use /memory-bank architect to initialize, query, or update project memory files (productContext, activeContext, progress, decisions, patterns). Maintains persistent state across sessions via timestamped logs.
Skill Claude Code
Genera el snapshot de la sesión actual para retomar en la próxima sesión sin perder contexto. Invocar antes de cerrar o cuando el contexto se acerca al límite.
tommcfarlin/claude-code-onboard
Skill Claude Code
Onboard a Claude session on the current codebase with smart caching and delta updates. Optimized for git worktree workflows — onboard once, share context across all worktrees.
Skill Claude CodeCodex
Guidance on shrinking or fully resetting conversation context between auto-engineer iterations — when to use /compact (built-in summarise), /clear (built-in wipe), or a full process restart via scripts/restart-loop.sh.
Skill Claude Code
Recursive analysis, persistent memory recall, and knowledge storage.
Skill Claude Code
Naechtliche Konsolidierung — Wissen verdichten, Tiers rebalancen, Patterns ableiten, Skills evolven, Strategie reviewen.
Skill Claude CodeCodex
Long-term memory upgrade for OpenClaw agents — 3-speed architecture: QMD (<1ms working memory) + Zvec vector search (<10ms) + built-in memory enhancement. No API key required. Runs 100% locally.
kellyclaudeai/memory-system-v2
Skill Claude CodeCodex
Fast semantic memory system with JSON indexing, auto-consolidation, and <20ms search. Capture learnings, decisions, insights, events. Use when you need persistent memory across sessions or want to recall prior work/decisions.
Skill Claude CodeCodex
A workflow for processing files from an `unprocessed/` folder, including screen recordings, exported conversations, notes, PDFs, and images. It moves information through raw and wiki stages.
Skill Claude CodeCodex
This skill provides a work history. Always use this skill before answering any question that involves what the user has worked on, built, shipped, or contributed to — at any level of granularity or time range. Do not attempt to answer from memory or context alone; the data lives on disk and must be queried.
Skill Claude CodeCodex
Create a living agent from your Discord server. The agent embodies your community's identity, remembers every conversation, and grows as the community evolves. Talk to your Discord as if it were a person.
Skill Claude CodeCodex
Diagnose recurring Cron and skill-quality failures from transcripts and preserve evidence-backed strategies in the Wiki.
Skill Claude Code
Start a project-wiki — an agent-maintained knowledge base that turns scattered material (documents, meeting notes, web pages, research) into a durable, cross-linked wiki the agent builds, keeps current, and can answer questions from. This skill creates a new project-wiki in its own folder next to your current project…
Easternguy/hermes-backup-sync-skill
Skill Claude CodeCodex
Daily backup of Hermes config, skills, memory, and settings to a private GitHub repo. Pure shell script, no LLM overhead. Includes cache/strip logic for minimal repo size, secret templating, and a public-repo safety check.
Skill Claude CodeCodex
Two-tier memory system that makes agents true workplace collaborators. Decodes shorthand, acronyms, nicknames, and internal language so agents understand requests like a colleague would. AGENTS.md for working memory, memory/ directory for the full knowledge base.
Wayfound-AI/wayfound-agent-skills
Skill Claude CodeCodex
Lightweight self-supervision that piggybacks on your existing memory system. Adds a simple rubric to SOUL.md and a daily review cron job — no new infrastructure, no parallel systems. Your agent reviews its own day in 200 tokens, writes findings to memory where they compound naturally, and surfaces issues that need…
Skill Claude CodeCodex
Use this skill to inspect the current whiteboard.
QingmingPlusPlus/tri-memory-kit
Skill Claude CodeCodex
Use before substantial code, documentation, spec, skill, review, debugging, or planning work in this repository to locate relevant three-layer project memory from doc/spec/skills instead of rediscovering existing context.
Skill Claude CodeCodex
A workspace setup and maintenance guide for files such as AGENTS.md, CLAUDE.md, changelogs, session logs, and task lists.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: