Memory and context skills

6,517 tagged Memory and context, measured the same way as everything else here.

Browse within: LLM 232agent-memory 159agent 155cli 136agentic-ai 126agents 120ai-memory 112claude-code-plugin 83ai-coding 78context-engineering 62obsidian 61ai-tools 60long-term-memory 60knowledge-base 59

flomo-daily-echo

385

plidezus/flomo-skills

Skill Codex

A skill that creates a discussion prompt from yesterday's flomo notes and related older notes. Flomo is a note-taking service.

not rated 34 3mo ago A 74 tokens

agentMemory

386

webzler/agentMemory

Skill Claude CodeCodex

A hybrid memory system that provides persistent, searchable knowledge management for AI agents.

not rated 33 +1 7mo ago A 18 tokens copy · 86% MIT

bee-cli

387

bee-computer/bee-skill

Skill Claude CodeCodex

Access real-time context and life history from Bee, a wearable AI that captures and transcribes the owner's conversations. ALWAYS start with 'bee now' for the last 10 hours of conversations with full utterances - the highest-value context for relevant help. Use this skill when: (1) you need to know what's happening…

not rated 33 +2 3mo ago A 160 tokens

context

388

ktg-one/context

Skill Claude CodeCodex

CONTEXT: Cognitive Order Normalized in Transformer EXtract Truncated. Cross-model context handoff via Progressive Density Layering, MLDoE expert compression, Japanese semantic density, and Negentropic Coherence Lattice validation. Creates portable carry-packets that transfer cognitive state between AI sessions. Use…

not rated 32 6mo ago A 99 tokens original MIT

kage-memory

389

kage-core/Kage

Skill Claude CodeCodex

Trustworthy, code-grounded repo memory for coding agents. Before any task, recall grounded repo knowledge (decisions, bugs, conventions, code paths); after learning something durable, capture it; never act on stale or hallucinated memory. Use at the start of every task, when debugging, and after solving something…

not rated 32 10d ago A 69 tokens GPL-3.0

mnemos

390

ncz-os/mnemos

Skill Claude CodeCodex

Configure and use MNEMOS for persistent cross-session memory with Hermes — shared memory pool across profiles, full-text and semantic search, compression with quality manifests, knowledge-graph triples, and session transcript ingestion. Use when setting up MNEMOS, troubleshooting memory retrieval, storing…

not rated 31 today A SkillSpector: warn 72 tokens original Apache-2.0

ldm-session-handoff

391

Holden323/ldm-skill

Skill Codex

A session handoff workflow that saves a conversation, its key decisions, and instructions for restarting it later.

not rated 31 7d ago A SkillSpector: pass 125 tokens original MIT

quietloop

392

zealxz/quietloop

Skill Claude CodeCodex

Use when designing or operating evidence-driven reflection, receipt-gated low-risk automation, privacy-preserving memory hygiene, or reliable notification recovery for Hermes-based personal agents. Do not use for generic journaling, unrestricted self-modification, or any workflow that cannot provide explicit approval…

not rated 31 +6 29d ago A 59 tokens original MIT

hello-goodbye

393

YS-Chu/hello-goodbye

Skill Claude CodeCodex

A set of instructions for giving an AI companion lasting memory between separate chats. It stores personal details, shared history, feelings, and recent summaries in files, then reads and updates them when a chat starts or ends.

not rated 31 +26 25d ago A 123 tokens original MIT

memory-loop

394

yucai0302/memory-loop

Skill Claude CodeCodex

Update project memory after completing a task, making a key decision, discovering a gotcha, or changing active goals. Use this skill at the end of any meaningful unit of work to write structured entries into .claude/memory/MEMORY.md following the project schema. Also use when the user asks to save memory, update…

not rated 30 2mo ago A 76 tokens

remem

395

majiayu000/remem

Skill Claude Code needs its repo

Use when the user asks Codex to recall prior project context, save durable decisions or bug fixes, inspect remem memory health, or activate remem automatic memory hooks from the Codex plugin.

not rated 30 changed 2d ago A SkillSpector: pass 42 tokens original MIT

session-index

396

lee-fuhr/claude-session-index

Skill Claude CodeCodex

Search, analyze, and synthesize across all your Claude Code sessions. Ask "what did I try last time?" and get answers with resume links.

not rated 29 5mo ago A 33 tokens original MIT

mxSave

397

MicrotronX/mxLore

Skill Claude Code

Use when the user says "save state", "/mxSave", "session end", "before /compact", "wrap up", or otherwise wants to persist the current mx-project state (clean settings, update CLAUDE.md + docs/status.md, create session notes in MCP-DB, sync orchestrate-state deltas, emit clear-cycle tip). Loop-capable. Fires at…

not rated 29 changed today A 84 tokens

comet-cc-memory

398

Dirac-Robot/comet-cc

Skill Claude CodeCodex

Search, read, and cross-reference the persistent memory store that the CoMeT-CC plugin has been building across this and prior Claude Code sessions. Use when the user references "before", "earlier", "last time", "that thing you worked on", "you already did…", or when you have a hunch that a relevant…

not rated 29 4mo ago A 115 tokens

librarian

399

ngmeyer/librarian-mcp

Skill Claude Code

Orchestrate vault knowledge workflows using the Librarian MCP server. Ingest solutions, search prior art, explore the knowledge graph, log daily learnings.

not rated 29 2mo ago B 35 tokens original MIT

build-personal-brain

400

mikeshu2001/personal-brain-builder

Skill Codex

Create, resume, validate, connect, or maintain a private cross-project memory for AI assistants. Use when a person asks to build a personal memory from local work folders and past assistant conversations, continue an interrupted memory audit, connect an existing memory to another local assistant, verify that the…

not rated 29 +2 6d ago A SkillSpector: warn 81 tokens original MIT

remnote

401

robert7/remnote-mcp-server

Skill Claude CodeCodex

Search, read, and write RemNote notes and personal knowledge base content via remnote-cli. Use for note-taking, journaling, tags, tables, and knowledge-base navigation; require confirm write before mutating commands.

not rated 29 +3 3d ago A SkillSpector: pass 50 tokens original MIT

cogito-engine

402

xbmaxx/cogito-engine

Skill Claude CodeCodex ⚠ unsafe

A framework for giving an agent awareness of its activity, attention, timing, and repeated behaviour. It also combines memory scoring, safety handling for untrusted data, decision guidance, focus tracking, and tool-use records.

not rated 28 +2 1mo ago C ⚑ AI: unsafe 278 tokens

star-your-harness

403

SpaceZephyr/build-your-harness

Skill Claude CodeCodex needs its repo

A guided setup for creating an AI work folder, sometimes called an AI harness, with organized instructions, background information, memory, tools, and review practices.

not rated 28 +4 23d ago A SkillSpector: pass 190 tokens original MIT

notebrain-assistant

404

nmdra/notebrain-cli

Skill Claude Code

Search and explore an Obsidian vault through the NoteBrain CLI (semantic search, tags, backlinks, connections, hidden links, boosted retrieval). Use it whenever the user mentions their notes, knowledge base, Obsidian vault, semantic search, finding connections or unlinked notes, or asks exploratory questions like…

not rated 27 6d ago A SkillSpector: pass 130 tokens original MIT

agent-handoff

405

WeirdSky924/agent-handoff-skill

Skill Codex

Cross-platform skill for Codex, Claude Code, and DeepSeek Harness (DSH) that creates, updates, compacts, rotates, repairs, and reviews durable repository handoffs. Use when bootstrapping cross-session memory; creating or maintaining AGENTHANDOFF.md and .agent-handoff files; adding AGENTS.md or .claude/CLAUDE.md rules…

not rated 26 11d ago A 105 tokens original MIT

docs-context

406

lujiafa/houtu-project-skills

Skill Claude CodeCodex

Super Base Context — project doc loader & synchronizer. Triggers even without explicit "load docs"/"sync docs." READ MODE — load architecture/modules/coding/decision docs when work references project state: code work (write/modify/remove); design (features/APIs/schemas/architecture); review (modules, past solutions)…

not rated 26 4mo ago A 203 tokens original MIT

self-improvement

407

alleneee/skill-agent

Skill Claude CodeCodex

A process for recording useful lessons from unexpected failures, user corrections, missing abilities, and reusable project patterns.

not rated 26 +1 5mo ago A Socket: passSnyk: pass 60 tokens

a2wave-memory

408

LilithGames/a2wave

Skill Claude CodeCodex

Progressively recall and maintain a2wave cross-session memory through a compact startup catalog, bounded topics, and searchable history.

not rated 26 +1 yesterday A SkillSpector: pass 29 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: