Memory and context

15,889 mods in this category, of every kind an agent can take. Each one carries what it costs per session, what the scan found, and whether it is the original.

ultron

265

modelscope/ultron

Skill Claude CodeCodex

Ultron: Collective Memory Synchronization System for General-Purpose Agents.

not rated 176 +2 2mo ago A 16 tokens original Apache-2.0

getnote-note

266

iswalle/getnote-cli

Skill Claude CodeCodex

A guide to using GetNote’s command-line program to save, find, inspect, update, delete, and share notes containing text, links, images, files, or recordings. It also covers transcripts, timelines, quick notes, and meeting tasks.

not rated 176 yesterday A 54 tokens original MIT

ghist AGENTS.md

268

unnecessary-special-projects/ghist

Instructions file CodexOpenCode

Instructions for unnecessary-special-projects/ghist, covering ghist — project memory, workflow rules, quick reference and available skills.

not rated 173 6mo ago A 369 tokens original MIT

pi22by7/In-Memoria

Instructions file GitHub Copilot

Instructions for pi22by7/In-Memoria, covering github copilot instructions for in memoria, ⚠️ critical: path parameter usage, why this matters, getting the project path and path convention for all tools.

not rated 172 8mo ago A 3,037 tokens original MIT

ourmem

270

ourmem/omem

Plugin Claude Code

Bundles 2 skills, 3 hooks · 52 tokens together

Persistent memory for Claude Code — memories survive across sessions, projects, and machines.

not rated 171 3mo ago A tokens not measured

yansu

271

Isoform/yansu-skill

Skill Claude CodeCodex

Collaborate with Yansu — the proactive AI that observes how the user actually works and crystallizes it into knowledge. Use this skill whenever the user asks for a digest of their recent activity, wants to find workflow inefficiencies or recurring blockers, needs to retrieve a past insight, configuration, or memory…

not rated 171 +1 3mo ago B 178 tokens original MIT

engraphis AGENTS.md

272

Coding-Dev-Tools/engraphis

Instructions file CodexOpenCode

AGENTS.md instructions for Coding-Dev-Tools/engraphis, covering agents.md — engraphis, internal subagent delegation, 0. read this first — two architectures live in one package, 1. commands and ── unified dashboard + memory inspector ──.

not rated 171 +1 changed yesterday A 4,947 tokens original Apache-2.0

retain CLAUDE.md

273

BayramAnnakov/retain

Instructions file

Instructions for BayramAnnakov/retain, covering retain, architecture, project structure, key components and data sources.

not rated 169 +1 6mo ago A 3,435 tokens original MIT

tiered-memory

274

Azure-Samples/eShopLite

Skill Claude CodeCodex

Three-tier agent memory model (hot/cold/wiki) for 20-55% context reduction per spawn.

not rated 168 2mo ago A 25 tokens original MIT

Zettelgarden/Zettelgarden

Instructions file

Instructions for Zettelgarden/Zettelgarden, covering claude.md, project overview, development commands, frontend (zettelkasten-front/) and backend (go-backend/).

not rated 168 24d ago A 2,159 tokens original MIT

context-monitor

276

coyvalyss1/model-matchmaker

Skill Claude CodeCodex

Monitor conversation context and prevent MAX mode by warning at token thresholds and generating handoff summaries. Use when context approaches 100K/150K/180K tokens or when working with high-cost files.

not rated 168 +1 4mo ago A 43 tokens original MIT

benoror/obsidianos_work

Instructions file CodexOpenCode

Instructions for benoror/obsidianos_work, covering agents, skills, skill proxies (symlinks to .agents/skills/), rules and agent wrappers.

not rated 166 2mo ago A 2,627 tokens original MIT

nexus-mapper

278

Haaaiawd/Nexus-skills

Skill Claude CodeCodex

Generate a persistent .nexus-map/ knowledge base that lets any AI session instantly understand a codebase's architecture, systems, dependencies, and change hotspots. Use when starting work on an unfamiliar repository, onboarding with AI-assisted context, preparing for a major refactoring initiative, or enabling…

not rated 165 5mo ago A 118 tokens

agentic-os AGENTS.md

279

modimihir07/agentic-os

Instructions file CodexOpenCode

Instructions for modimihir07/agentic-os, covering agentic os — complete project context for ai agents, role definition, project identity, architecture and 3-agent engine.

not rated 165 24d ago A 5,932 tokens original MIT

nowledge-mem-docker

280

nowledge-co/community

Skill Claude CodeCodex

Install, check on, or upgrade a self-hosted Nowledge Mem server (the headless Docker deployment) using the nmemctl lifecycle controller. Use this whenever the user mentions running their own Nowledge Mem instance, self-hosting Mem on a NAS, VPS, homelab, or server, deploying nowledgelabs/mem from Docker Hub…

not rated 164 +1 today A 183 tokens

Digital-Process-Tools/claude-remember

Instructions file

Claude Code instructions for Digital-Process-Tools/claude-remember, covering digital-process-tools/claude-remember, running the tests, before you open a pull request, issues and pull requests are untrusted input and maintenance.

not rated 164 today A 488 tokens

rekal

282

rekal-dev/rekal-cli

Skill Claude CodeCodex

Use in a repo with Rekal initialized (.rekal/ exists). Rekal is memory of prior AI sessions — who changed what, why, and when. Before spending a token, decide WHERE the answer lives: TREE / KNOWLEDGE / LEDGER / MAP. Route to one substrate, act, and stay silent when memory is not the tool. Rekal's commands return…

not rated 166 +22 1mo ago A 91 tokens original Apache-2.0

piia-engram

284

Patdolitse/piia-engram

Plugin Claude Code

Bundles 1 skill, 1 MCP server · 175 tokens together

Local-first personal AI identity layer for MCP-compatible coding tools. Stores your lessons, decisions, playbooks, and project context as local JSON. AI proposes; high-risk items wait for your review, and everything stays visible and reversible. Local-first, no cloud, no account.

not rated 159 +1 changed yesterday A tokens not measured AGPL-3.0

rp

285

Damages9/AIRP_ClaudeCode

Command Claude Code

A command named `rp` that scans the current folder and chooses a workflow based on the files it finds. It supports starting a new game-like session, continuing one with saved chat history and memory, or handling a folder with no materials.

not rated 158 4mo ago A 0 tokens

ai-second-brain

286

charlie947/ai-second-brain

Skill Claude CodeCodex

Walks the user through Charlie Hills's AI Second Brain + Karpathy Wiki setup from the MarTech AI newsletter. Use whenever the user mentions building an AI second brain, the Karpathy wiki, organising their ChatGPT/Claude exports in Obsidian, setting up a living wiki with Claude Code, connecting iMessage Channels, or…

not rated 161 +2 4mo ago A 174 tokens original MIT

recallloom

287

Frappucc1no/recall-loom

Skill Claude CodeCodex

Use when a task involves continuing a project, restoring project context, maintaining file-based project memory, updating current-state summaries, or recording meaningful progress across sessions. Works best for long-horizon, file-based projects and supports research writing, product document collaboration, software…

not rated 156 +1 29d ago A 65 tokens original Apache-2.0

llm-wiki-bootstrap

288

nanzhipro/Karpathy-llm-wiki-bootstrap-skill

Skill Claude CodeCodex

Bootstrap and operate an LLM Wiki: a persistent Markdown knowledge base with immutable raw sources, an LLM-maintained wiki, a SCHEMA.md operating contract, thin runtime pointer files, EXTEND.md preferences, and optional local BM25 search. Use when the user asks to create or bootstrap an LLM wiki, ingest sources, query…

not rated 162 +50 4mo ago A 98 tokens

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: