Memory and context skills

6,583 tagged Memory and context, measured the same way as everything else here.

Browse within: LLM 230agent 160agent-memory 156cli 133agentic-ai 125agents 119ai-memory 111claude-code-plugin 79ai-coding 76context-engineering 60ai-tools 58knowledge-base 58skills 58open-source 56

rag-query

937

butchokoy25/lightrag-claude-skills

Skill Claude CodeCodex

Query the personal LightRAG knowledge graph for persistent memory across sessions.

not rated 2 5mo ago A 16 tokens original MIT

relay

938

mosuvo/relay

Skill Claude Code

Capture the full context of the CURRENT Claude chat into a complete, portable briefing the user can paste into a NEW chat to continue seamlessly. Use ONLY when the user explicitly asks — e.g. "relay", "relay this", "handover", "hand off", "handoff", "continue in a new chat", "this chat is getting long", "carry this…

not rated 2 2mo ago A 164 tokens original MIT

synapse

939

ANTHO56200/synapse-memory

Skill Claude Code

Perpetual memory and shared brain for Claude Code. A two-level memory system — per-project memory plus a global cross-project brain — that makes Claude remember everything across all sessions and all projects. USE THIS SKILL whenever a session starts in any project, whenever the user mentions memory, remembering…

not rated 2 2mo ago D 140 tokens original MIT

distill-habits

940

betayyang/claude-habit-distiller

Skill Claude CodeCodex

Review recent Claude Code conversations, distill the user's stable habits and preferences, persist them into a long-term habit ledger, and maintain a "My Habits" block in the global CLAUDE.md within a character budget. The more you use Claude Code, the more it knows you. Trigger manually with /distill-habits, or on a…

not rated 2 changed 6d ago A 87 tokens original MIT

loop-memory

941

haidrrrry/loop-engineering-skills

Skill Claude CodeCodex

Give the agent episodic memory so it improves every cycle instead of repeating mistakes. Use this skill whenever working in a project that has a .loop/LESSONS.md file, whenever a task is being retried after a failure, whenever the user says "remember this", "don't make that mistake again", "learn from this", or "why…

not rated 2 2mo ago A 107 tokens original MIT

memory-onboard

942

tmj-90/gaffer

Skill Claude CodeCodex

Use this skill when the user types /memory-onboard (or asks "set up memory for this repo" / "onboard this repo to memory" / "what should be in lore for this repo?"). It runs a repo-aware onboarding interview that produces DRAFT lore records grounded in concrete repo signals (README, ADRs, recent commits, deprecation…

not rated 2 5d ago A 196 tokens original Apache-2.0

compact-manual

943

mario-hernandez/claude-compact-manual

Skill Claude Code

Claude Code skill for deterministic context compaction. Compresses the current Claude Code session to the clipboard for a manual rewind+paste workflow. A deterministic alternative to /compact that extracts literal dialog and truncates only tool outputs — no LLM summarization. Use when the user says 'compact the…

not rated 2 4mo ago A 81 tokens original MIT

graphifychat

944

soumyakantabera/graphifychat

Skill Claude CodeCodex

Turn any conversation into a queryable knowledge graph. Three-layer portable memory file: TRON (structured input+output capture with emotion, psychology, intent — every turn), Sparse6 (layered relational graph with community detection, hyperedges, confidence scores — every turn), GRAPHREPORT (god nodes + surprising…

not rated 2 4mo ago A 172 tokens original MIT

swarmvault

945

anitagraviti-sys/swarmvault

Skill Claude CodeCodex

Use SwarmVault when the user needs a local-first knowledge vault that writes durable markdown, graph, search, dashboard, review, context-pack, task-ledger, retrieval, and MCP artifacts to disk from books, notes, transcripts, exports, datasets, slide decks, files, URLs, code, and recurring source workflows.

not rated 2 today A 69 tokens original MIT

session-handoff

946

AdityaVasireddy/agent-skills

Skill Claude CodeCodex

Use when the user says "session handoff", "wrap up session", "hand off", "handoff summary", "let's wrap up", "summarize before I clear", or wants a structured end-of-session summary before clearing context. Also use proactively when the user says they are about to /clear and no handoff has been produced yet. Generates…

not rated 2 3d ago A 148 tokens original MIT

farzadgmma/Engineering-Knowledge-Governance-Console

Skill Claude CodeCodex

Distill verified engineering knowledge from incidents, debugging sessions, code reviews, and expert-model analysis into evidence-backed project rules. Use when asked to analyze an incident, convert an expert answer into a rule, create or update an ADR or external contract, promote or deprecate a rule, or scan relevant…

not rated 2 1mo ago A 90 tokens

open-skill

948

KalenTang666/OpenSkill

Skill Claude Code

Cross-domain AI skill asset manager. Discover, analyze, migrate, and sync your Skills, Memory, and Preferences across 8 AI platforms (Claude, Codex, Cursor, Copilot, Gemini, VS Code, Windsurf, OpenClaw). Features smart matching, hook automation, security scanning, growth gamification, and cross-device sync.

not rated 2 5mo ago A 73 tokens original MIT

knowledge-capture

949

Empty8492/knowledge-capture

Skill Codex

A knowledge-management system that keeps changing project facts in a project folder and stores verified, reusable knowledge in Obsidian, a note-taking application. It separates facts, source claims, inferences, and items still needing verification.

not rated 2 1mo ago A 159 tokens original MIT

memory-map

950

shandar/memory-map

Skill Claude CodeCodex

Two-tier project memory system. Maintains a global Claude memory snapshot of all ongoing projects AND a per-project STATUS.md file in each project folder that captures last-session state, next actions, blockers, and key locations — so context survives long absences. Operates in two modes. WRITE mode triggers when the…

not rated 2 4mo ago A 215 tokens original MIT

second-brain-attach

951

YusenZhang0601/context-canopy

Skill Codex

A setup process for connecting a new or reset AI agent to a local Second Brain—a personal collection of rules, identity information, and reusable skills. It installs the required skills, connects the supporting service, and checks the setup in a fresh session.

not rated 2 20d ago A 111 tokens original MIT

context-compression

952

dzhokhov/markdown-agent-vault-ru

Skill Claude CodeCodex

A skill for condensing the history of meetings and projects into a short memory file. It records decisions, changes, outdated agreements, open questions, and key meetings.

not rated 2 6d ago A 187 tokens original MIT

wpc0323/StructuredMemoryManager

Skill Claude CodeCodex

A structured long-term memory tool for storing and retrieving user preferences, past decisions, task summaries, and habits across conversations. It can search memories by meaning as well as keywords.

not rated 2 1mo ago A 60 tokens original MIT

emergent-judgment

954

thebrierfox/emergent-judgment

Skill Claude CodeCodex

Metacognitive framework for persistent AI agents to recognize, preserve, and cultivate emergent judgment — the pattern-matching intuition that develops through accumulated experience but is invisible to introspection and destroyed by compaction. Use this skill whenever the agent completes a significant task (audit…

not rated 2 6mo ago A 214 tokens original MIT

obsidian

955

Rayan55050/progressive-agent

Skill Claude CodeCodex

A skill for working with an Obsidian vault, which is a folder of Markdown notes used as a personal knowledge base. It covers creating, extending, searching, and organizing notes, including links, tags, folders, and daily entries.

not rated 2 2d ago A 15 tokens original MIT

innate-memory

956

vima-tech/Innate

Skill Claude Code

Innate procedural knowledge layer for coding, debugging, and analysis sessions. ACTIVATE when: (1) user says "remember", "save", "log", "follow this rule", "don't forget", "recall", or "what did we learn"; (2) a non-obvious solution, workaround, constraint, or invariant was discovered during this session; (3) starting…

not rated 2 11d ago A 156 tokens original MIT

chatgpt-migrator

957

JamsusMaximus/chatgpt-migrator

Skill Claude CodeCodex

Migrate from ChatGPT to Claude. Trigger on: ChatGPT export/history/migration, switching from ChatGPT, or folders with conversations-.json or chat.html files.

not rated 2 6mo ago A 42 tokens original Apache-2.0

waihona

958

bjamba/kamaaina

Skill Claude CodeCodex

Waihona manages a context-base: indexed external memory on disk that a small model traverses to load only what a task needs. Format spec: design/context-base/context-base.md in the Kamaʻāina repo.

not rated 2 1mo ago A 0 tokens original MIT

know-me

959

doublesq97-ui/know-me

Skill Codex

Collaboration-profile interview that creates or refreshes a reusable AI Collaboration Manual. Use when the user invokes Know Me ($know-me or /know-me), chooses first use, quick start, or deep calibration, asks for an AI collaboration manual, provides an existing manual to update, wants stable long-term collaboration…

not rated 2 1mo ago A 97 tokens original MIT

agentverse-memory

960

fetchai/agentverse-skills

Skill Claude Code

Give any AI agent persistent, graph-native memory via Agentverse Memory — a managed MCP service with 35 JSON-RPC tools covering 4 memory types (episodic, semantic/graph, procedural, working) plus shared multi-agent memory spaces. Zero LLM at write time (<5ms writes, $0 ingest). Graph memory on every tier — including…

not rated 2 2mo ago A 127 tokens original Apache-2.0

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: