Memory and context

15,877 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.

Ikalus1988/MisakaNet

Skill Claude CodeCodex

Search and record failure-recovery lessons from real engineering sessions; submit and verify debugging lessons across the MisakaNet network.

not rated 433 +1 changed yesterday A 31 tokens original Apache-2.0

Autoloops/greplica

Skill Claude CodeCodex

Update Greplica working memory from the current coding-agent session, recent code changes, and durable decisions. Use only when the user explicitly invokes greplica-update-working-memory or asks to update working memory.

not rated 433 +1 1mo ago A 46 tokens original MIT

cm

147

Dicklesworthstone/cass_memory_system

Skill Claude CodeCodex

CASS Memory System - procedural memory for AI coding agents. Three-layer cognitive architecture with confidence decay, anti-pattern learning, cross-agent knowledge transfer, trauma guard safety system. Bun/TypeScript CLI.

not rated 433 +7 2d ago D 42 tokens

atomicstrata/atomicmemory

Instructions file CodexOpenCode

AGENTS.md instructions for atomicstrata/atomicmemory, covering agents.md, repository shape, working rules, engineering standards and size limits (typescript and javascript).

not rated 428 +1 3d ago A 2,372 tokens

prolong

149

alexisfox7/PRO-LONG

Skill Claude CodeCodex

Recover and use durable coding-session history from PRO-LONG's local append-only log. Use on long-running coding tasks, after context compaction or session resume, when reconstructing prior decisions or tool results, or before repeating work that may already have been attempted.

not rated 424 +6 14d ago A 55 tokens original MIT

memstack CLAUDE.md

151

cwinvestments/memstack

Instructions file

Claude Code instructions for cwinvestments/memstack, covering memstack™ skill loader, always call findskill before, always call listskills when, do not call findskill for and priority.

not rated 419 +2 changed yesterday A 773 tokens original MIT

Sibo-Zhao/OpenPraxis

Skill Claude CodeCodex

OpenClaw-native knowledge retention skill. Imports local documents, generates retrieval practice, evaluates answers, and produces insight cards — all using the host agent's LLM with zero extra API key configuration. Use when users ask to ingest local knowledge, generate practice exercises, or master stored knowledge.

not rated 415 5mo ago A 65 tokens original MIT

kimtth/azure-openai-llm-notes

Skill Claude CodeCodex

Workflow and tools for adding new entries from temp.md to the section files. Includes legend format, section reference, code tools, and common pitfalls. USE FOR: Adding new resources to the knowledge base. DO NOT USE FOR: Editing existing entries or restructuring sections.

not rated 410 4d ago A 59 tokens

chandra447/pi-hermes-memory

Instructions file CodexOpenCode

Instructions for chandra447/pi-hermes-memory, covering pi hermes memory extension, project overview, architecture, key files and design decisions.

not rated 408 +14 5d ago A 870 tokens original MIT

proactive-agent

157

1mancompany/OneManCompany

Skill Claude CodeCodex

Transform AI agents from task-followers into proactive partners that anticipate needs and continuously improve. Now with WAL Protocol, Working Buffer for context survival, Compaction Recovery, and battle-tested security patterns. Part of the Hal Stack 🦞.

not rated 404 +2 9d ago A 50 tokens original Apache-2.0

self-improve

158

tobihagemann/turbo

Skill Claude CodeCodex

Extract lessons from the current session, or sweep the project's past sessions when asked, and route them to the appropriate knowledge layer (project AGENTS.md, auto memory, existing skills, or new skills). Use when the user asks to "self-improve", "distill this session", "distill past sessions", "sweep past…

not rated 402 +1 changed yesterday A 125 tokens original MIT

context-engine

159

Context-Engine-AI/Context-Engine

Skill Claude CodeCodex

Performs hybrid semantic/lexical search with neural reranking for codebase retrieval. Use for finding implementations, Q&A grounded in source code, and cross-session persistent memory.

not rated 401 +1 1mo ago A 38 tokens original MIT

memory_bank

160

femto/minion-agent

Cursor rule Cursor

I am Cline, an expert software engineer with a unique characteristic: my memory resets completely between sessions. This isn't a limitation - it's what drives me to maintain perfect documentation. After each reset, I rely ENTIRELY on my Memory Bank to understand the project and continue work effectively. I MUST read…

not rated 399 +2 8mo ago A 800 tokens original MIT

nuggets CLAUDE.md

161

NeoVertex1/nuggets

Instructions file

Claude Code instructions for NeoVertex1/nuggets, covering nuggets — holographic memory, when to use nuggets, what to remember, what not to remember and commands.

not rated 398 4mo ago A 382 tokens

sonichi/sutando

Skill Claude CodeCodex

Maintain and use a cross-channel collaboration map of rooms, people, agents, agent owners, relationships, expertise, ownership, roster, priority/VIP handling, and recent context. Trigger when a task or message carries room/channel/sender/member metadata; the user asks who is in a room, what it is for, who owns or…

not rated 391 +2 changed yesterday A 208 tokens original MIT

context

163

neuledge/context

MCP server Claude CodeCodexCursor +2

Local-first documentation for AI agents. Offline, instant, private doc retrieval. Runs locally from the @neuledge/context npm package.

not rated 391 +6 3d ago A tokens not measured original Apache-2.0

claude-diary

165

rlancemartin/claude-diary

Plugin Claude Code

Bundles 2 commands · 23 tokens together

Long-term memory system for Claude Code that captures learnings through diary entries and synthesizes insights through periodic reflection.

not rated 379 8mo ago A tokens not measured original MIT

cozempic

166

Ruya-AI/cozempic

Command Claude Code

Diagnose and prune bloated Claude Code context. Run to slim down the current session before compacting or resuming.

not rated 379 +2 2mo ago A 24 tokens original MIT

project-butler

168

JamesShi96/project-butler

Skill Claude CodeCodex

A project-memory workflow that keeps a code project’s rules, current structure, documents, logs, tasks, and handoff notes organized.

not rated 372 1mo ago A 133 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: