11,848 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.
Cursor rule Cursor
This project uses the l00prite protocol: durable agent memory lives in .l00prite/, as plain files any AI agent can read, inside the protocol root — the l00prite/ folder at the repo root (memory at l00prite/.l00prite/; in the l00prite source repo the protocol root is the repo root itself). All .l00prite/ paths below…
Skill Claude CodeCodex
A project workflow for coordinating several coding agents on the same software project. It uses shared project structure, decisions, handoffs, checklists, and memory so agents can continue each other's work.
tencent-lexiang/lexiang-mcp-skill
Skill Claude CodeCodex
A full-featured skill for 乐享知识库, a personal or shared knowledge base. It supports searching and managing knowledge-base content when users mention 乐享, lexiang, or related links.
Skill Codex
Use this skill when a user wants Codex CLI or another MCP-compatible coding client to work through a harness-engineering loop with explicit execution contracts, persistent local knowledge/RAG, durable traces, structured verification evidence, project-local governance policy, PASS/FLAG/BLOCK governance audits…
Skill Codex
Deterministic, self-hosted long-term memory for AI agents. Trigger when the user wants persistent memory, MCP-backed assistant memory, or wants to integrate ai-knot into Python, CrewAI, LlamaIndex, AutoGen, the OpenAI Agents SDK, PydanticAI, LangChain/LangGraph, TypeScript, or HTTP services. This is the default…
Skill Codex
Persistent external brain for ChatGPT, Codex, Claude, and other MCP clients — documents (PDFs, contracts, scans with OCR), personal facts (appointments, decisions, items, amounts), AND code lessons / preferences / project topology. USE PROACTIVELY in three modes. (1) RECALL — whenever the user asks about anything from…
Plugin Claude Code
Bundles 5 skills · 197 tokens together
Long-term memory for Claude across sessions via Notion — plus the 4 official Anthropic Notion skills (knowledge-capture, meeting-intelligence, research-documentation, spec-to-implementation) bundled in.
Cursor rule Cursor
At the start of every coding task call memory.fetchcontext to load current state, conventions, and prior decisions. After making a durable choice, hitting a footgun, or wrapping a session, call memory.proposeupdate. Always prefer this over re-reading raw source files when you need project context.
Skill Claude CodeCodex
Personal Knowledge Base management skill. Use for ingesting documents, creating source notes, structured logging, canonical authority resolution, document-level provenance edges, and managing a Git-backed Obsidian vault.
basicmachines-co/basic-memory-plugins
Plugin Claude Code
Bundles 6 skills, 1 agent, 2 hooks · 206 tokens together
Claude Code skills, agents, and hooks for Basic Memory — placement-aware note writing and knowledge graph workflows.
christinetyip/ensue-learning-memory
Plugin Claude Code
Bundles 2 skills, 1 hook · 108 tokens together
Learning-focused knowledge base for building deep understanding over time.
Plugin Claude Code
Bundles 9 skills, 19 commands, 6 hooks, 1 MCP server · 559 tokens together
RAG plugin for Claude Code — capture, index, and search across all conversations, tools, and sub-agents.
kiseki-technologies/kiseki-labs-readwise-mcp
Cursor rule Cursor
A simple MCP server for Readwise.
Plugin Claude Code
Bundles 6 skills · 399 tokens together
File-based two-tier memory system for AI agents. Agent-namespaced vaults with promotion pipelines, trust levels, CLI write commands, and explicit general read mode for vault-less notes. Gives any agent persistent memory across sessions.
Plugin Claude Code
Bundles 1 skill, 1 command, 3 hooks · 77 tokens together
Logs each Claude Code session's name, start date, and last-modified date to a JSON file so you can find past sessions easily.
Skill Claude Code
Gives an agent persistent long-term memory backed by a local sparse-vector file. Use when the agent should recall past context, learn from interactions, or incorporate reinforcement feedback. Relevant for tasks mentioning memory, recall, learning, history, or context retention.
MCP server Claude CodeCodexCursor +2
Neuromorphic long-term AI memory system — brain-inspired context for AI agents. Runs locally from the myelin-mcp Python package.
alphaplapplap/mcp-memory-service
MCP server Claude CodeCodexCursor +2
MCP server "memory" as configured in alphaplapplap/mcp-memory-service. Runs C:\REPOSITORIES\mcp-memory-service\memory_wrapper.py with python. Needs 2 environment variables to run.
Plugin Claude Code
Local-first memory for AI coding agents: captures feedback and failures, turns them into ranked, conflict-resolved technical rules, and injects the relevant ones into Claude Code via MCP. Stays on your machine — no cloud, no API keys.
MCP server Claude CodeCodexCursor +2
A Model Context Protocol (MCP) server that implements a knowledge graph-based memory system with AI-powered entity and relation extraction. Runs locally from the kg-mem Python package.
MCP server Claude CodeCodexCursor +2
MCP server for Obsidian vaults - AI tools with consistent canonical context. Local-first. Runs locally from the @hiveforge/hivemind-mcp npm package. Needs 2 environment variables to run.
tejpalvirk/quantitativeresearch
MCP server Claude CodeCodexCursor +2
MCP server "contextmanager-quantitativeresearch" as configured in tejpalvirk/quantitativeresearch. Runs locally from the contextmanager-quantitativeresearch npm package.
Plugin Claude Code
Bundles 7 skills · 368 tokens together
LLM Wiki suite from the Tiro team — bootstrap, ingest, query, lint, socratic, sync. A persistent, agent-maintained personal knowledge base.
Cursor rule Cursor
Use TokenDiet MCP for high-yield compression only — logs, web, large files. Avoid extra MCP turns on small reads.
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: