Memory and context skills

6,540 tagged Memory and context, measured the same way as everything else here.

Browse within: LLM 226agent 161agent-memory 159cli 136agentic-ai 125agents 120ai-memory 110claude-code-plugin 81ai-coding 79ai-tools 61obsidian 61context-engineering 59knowledge-base 59skills 58

cobusgreyling/agent-skills

Skill Claude CodeCodex

Manage what enters and stays in the context window — pruning, compaction, summary fidelity, ordering — so the agent stays coherent on long runs without inflating cost. Use when the user is hitting context limits, running long agentic loops, paying for full-history replays, or asks "how do I keep context manageable?" /…

not rated 14 2mo ago A 82 tokens

linksee-memory

506

michielinksee/linksee-memory

Skill Claude Code

The bridge to the agent's "past self". Before any new task, file edit, decision, or right after a failure, recall past caveats (pain records) / learnings (growth log) / implementation history from linksee-memory. This is the only way to solve Claude Code's "memory amnesia every session" problem. The "never repeat the…

not rated 14 changed yesterday A 612 tokens original MIT

lore

507

jordanhindo/lore

Skill Claude CodeCodex

Use to recall anything from past agent sessions with the server-free lore CLI — the "what did we decide", "how did we build X", "why did we drop Y", "find that earlier conversation", "pull context from my last session" task. Trigger whenever you need memory of prior work (yours or another harness's) — searching…

not rated 14 +1 2mo ago A 298 tokens original MIT

openclaw

508

hypabase/hypabase

Skill Claude CodeCodex

Persistent memory for agents. Stores preferences, decisions, facts, and events as a connected knowledge graph. Recalled by who, what, when, or why.

not rated 14 5mo ago A 32 tokens original Apache-2.0

global-memory

509

ozankasikci/global-agent-memory

Skill Codex

Retrieve and curate durable, project-aware knowledge through the Global Agent Memory MCP server. Use before substantial planning, implementation, refactoring, debugging, handoff preparation, or investigation when prior decisions, exact identifiers, recurring errors, verified solutions, preferences, or conventions may…

not rated 14 changed 5d ago A 74 tokens original MIT

aka-kika/kika-obsidian-mcp

Skill Claude CodeCodex

Use this skill when a user asks an agent to inspect, organize, summarize, or update an Obsidian vault through this MCP server.

not rated 14 +1 1mo ago A 0 tokens original MIT

zifamem-integrate

511

zifacorp/zifamem

Skill Codex

Add the public ZifaMem Python SDK to an AI companion, roleplay agent, coding-agent harness, or chatbot runtime. Use when the user asks to integrate ZifaMem, add emotional long-term memory, wire session summaries, inject recall context into prompts, configure LLMProvider extraction, or adapt memory to Claude Code…

not rated 14 +1 1mo ago A 88 tokens

save

512

XTSoftwareLabs/neatcontext-plugins

Skill Codex

Save durable decisions, findings, plans, and implementation knowledge from the visible Codex conversation into a new or existing NeatContext context. Use only when the user explicitly invokes this skill or asks to preserve the current conversation as reusable context.

not rated 13 17d ago A SkillSpector: pass 49 tokens original MIT

shellbrain

513

cucupac/shellbrain

Skill Claude CodeCodex

Use when an agent should remember to ask Shellbrain for targeted recall at task start, subproblem changes, repeated failures, hypothesis changes, or closeout.

not rated 13 3d ago A 34 tokens

kb

514

hraness/kb

Skill Codex

Set up, evolve, or operate a hraness/kb local-first Markdown knowledge base for coding-agent memory. Use when a user asks to design KB conventions or a recurring KB ritual; search or query a KB or Obsidian vault; load or recover repository context, plans, decisions, concepts, backlinks, semantic search, or Git…

not rated 13 changed yesterday A SkillSpector: pass 155 tokens original MIT

inner-life

516

DKistenev/agent-inner-life

Skill Claude CodeCodex

Keeps a dated record of how an agent's work has been going — an evening journal, free thinking at night, and a way to read it back. Use when asked to run the inner-life evening or night routine, to note something in state, or to recall how a stretch went. Writes under inner-life/ and replaces a short summary in native…

not rated 13 19d ago A 83 tokens original MIT

synapse-layer

517

SynapseLayer/synapse-layer

Skill Claude CodeCodex

AES-256-GCM encrypted persistent memory layer for Hermes Agent. Provides encrypted cross-session memory, Trust Quotient (TQ) scoring, and automatic recall across ALL channels (Telegram, WhatsApp, CLI, Discord).

not rated 13 4d ago A SkillSpector: warn 48 tokens original Apache-2.0

install-memex

518

parallelclaw/memex-mvp

Skill Claude Code

Make Claude, Cursor, and OpenClaw remember every AI conversation forever — one local SQLite corpus shared across all of them. Installs memex (local-first MCP server) in 60 seconds via curl one-liner. Includes auto-capture daemon for Claude Code / Cowork / Cursor / Obsidian; v0.10 Telegram auto-detect (export from…

not rated 13 2mo ago A ✓ AI review 194 tokens original MIT

adopt-memory-bank

519

mehmetdemirci/comb-ai

Skill Claude Code

Add a COMB memory bank to an existing (brownfield) project by analyzing current codebase, dependencies, and architecture. Use when the project already has code but no memory bank.

not rated 13 6mo ago A 42 tokens original MIT

memtomem-remember

520

memtomem/memtomem

Skill Claude CodeCodex

Save an explicit user-requested memory with memtomem. Use only when the user clearly asks to remember, record, or persist information for later.

not rated 13 today A 36 tokens original Apache-2.0

mnemosyne-memory

521

Mnemosyne-OS/Mnemosyne-Neural-OS

Skill Claude CodeCodex

Give your agent a sovereign, governed long-term memory backed by Mnemosyne OS. Use whenever the user has Mnemosyne OS installed and you need to recall past decisions, project history, or notes across sessions — or to persist something worth remembering. Teaches the vault governance rules every agent must honor before…

not rated 13 +1 today A 72 tokens

context-receipts

522

caioribeiroclw-pixel/pluribus

Skill Claude CodeCodex

Emit privacy-safe receipts for context selection, deferral, hydration, compaction, pruning, delegation, usage attribution, and boundary handoffs.

not rated 13 1mo ago A 33 tokens original MIT

discover

523

constant-itis/mycelium-memory

Skill Claude CodeCodex

Find hidden connections in the mycelium network — semantic bridges, project hubs, orphan rescue.

not rated 13 7d ago A 20 tokens AGPL-3.0

crystalline-capture

524

jordiboehme/crystalline

Skill Claude CodeCodex

Use when durable knowledge is learned while working, when the user asks to update a Crystalline domain, or before writing or editing an engram so it is deduplicated, well-formed and linked correctly.

not rated 13 +2 changed 5d ago A 47 tokens AGPL-3.0

knowledge-base

525

zach-blumenfeld/knowledge-index

Skill Claude CodeCodex

Search, navigate, and read a markdown knowledge base — a directory of notes, docs, or a wiki — via an auto-built knowledge-graph index over documents, their sections, and the wikilinks between them, retrieving the right slice instead of grepping and reading whole files. Use when working in a folder of markdown …

not rated 13 +6 15d ago A ✓ AI review 94 tokens original Apache-2.0

supamem

526

dzmitrys-dev/supamem

Skill Claude CodeCodex

Project-agnostic dual-memory tooling — semantic + structural memory for AI coding agents.

not rated 12 19d ago A 20 tokens original MIT

akashi

527

ApiliumCode/mayros

Skill Claude Code

Connect the user's Akashi second brain (local, private, verifiable) over MCP and answer from cited vault passages with signed provenance. Query it BEFORE answering anything about the user's knowledge, projects, decisions, or conventions. Triggers - akashi, vault, my notes, second brain, remember this, what did I…

not rated 12 1mo ago A 69 tokens original MIT

crystal-kb

528

memorycrystal/memorycrystal

Skill Claude CodeCodex

Create, import, enumerate, maintain, and share Memory Crystal knowledge bases. Use when importing reference material, syncing a corpus, cleaning or auditing a KB, or managing which agents can read a KB.

not rated 12 8d ago A 45 tokens original MIT

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: