12,531 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.
MCP server Claude CodeCodexCursor +2
A zero-dependency, in-memory graph database providing a memory layer for local AI agents with AST-based dependency tracking and Token-Level Provenance via Source Maps. Runs locally from the mcp-context-graph Python package.
MCP server Claude CodeCodexCursor +2
Local cross-project knowledge and research library for LLM workflows. Runs locally from the openlmlib Python package.
MCP server Claude CodeCodexCursor +2
A directory-as-context standard plus a read-only MCP server that gives AI agents live, structured, token-budgeted awareness of a multi-project workspace. Runs locally from the agenticscope npm package.
MCP server Claude CodeCodexCursor +2
MCP server "memory-db" as configured in cunzai97/Memory-DB. Runs locally from the memory-db Python package.
MCP server Claude CodeCodexCursor +2
MCP server "alexfayers-mcp-memory-sqlite" as configured in alexfayers/mcp-memory-sqlite. Runs locally from the alexfayers-mcp-memory-sqlite npm package.
MCP server Claude CodeCodexCursor +2
MCP server "keepygaga" as configured in TimWongUp/keepygaga. Runs locally from the keepygaga Python package.
MCP server Claude CodeCodexCursor +2
Local-first, provider-agnostic MCP knowledge vault + research capture. Give any AI host a persistent, compounding memory. Runs locally from the saripati npm package.
AribSudia/claude-code-methodology
MCP server Claude CodeCodexCursor +2
One of 4 in .mcp.json
Memory compression system for Claude Code - persist context across sessions. Runs locally from the claude-mem npm package. Needs 2 environment variables to run.
Plugin Claude Code
Bundles 1 skill · 52 tokens together
Load and save durable project knowledge through seven Rementum MCP tools.
Plugin Gemini CLI
IANA-registered .faf project context for Gemini, with a deterministic AI-readiness score. Read, validate, score, and sync one source across GEMINI.md / CLAUDE.md / AGENTS.md. Run /faf:setup after install.
Skill Claude CodeCodex
Use when maintaining project state, decisions, evidence, or a handoff that must survive a new session.
Plugin Claude Code
Bundles 1 skill, 8 commands, 2 agents · 214 tokens together
Safety-first context & orchestration engine for AI coding agents. Shadow memory, gotcha lifecycle, blast radius impact analysis, and test verification.
Skill Claude CodeCodex
Use when Codex should recall or store durable project context with MemoryLayer, preserve decisions across sessions, use MemoryLayer MCP tools, or troubleshoot MemoryLayer setup.
grtwo-jcansler/gryz-cursor-plugin
Plugin Cursor
One shared memory your AI assistants read and write across tools and sessions — you own it and manage it from the Gryz dashboard. Plus documents your assistants can edit safely, private Notes, Skills, and Tasks, over MCP with OAuth sign-in.
Skill Claude CodeCodex
Multi-repository coordination, synchronization, and architecture management with AI swarm orchestration.
Plugin Claude Code
Bundles 5 skills · 217 tokens together
Persistent memory for Claude across conversations. Recall and save decisions, preferences and facts in your private Kumiho workspace, review stored memories, and import reviewed memories from selected past conversations. Connect via /mcp (Cowork: Connect) after installing. Bundles the hosted Kumiho Memory MCP…
Plugin Claude Code
Bundles 1 skill, 1 hook, 1 MCP server · 63 tokens together
The log your next session resumes from: decisions, dead ends, handoffs and open tasks, shared across machines, agents and people over the todox MCP server. Reminds a session to read the log first and to write it up before finishing.
arlinamid/centered-agent-memory
Plugin Claude Code
Bundles 1 skill · 93 tokens together
The agent-memory skill for Claude Desktop — Chat, Cowork and the Code tab — and Claude Code: when to look up the user's earlier conversations and project files through the cam MCP server. Needs cam installed; with this plugin on, cam install leaves out its own copy in /.claude/skills.
Plugin Claude Code
Bundles 9 skills, 1 hook, 1 MCP server · 616 tokens together
Cut your Claude Code bill, measured on your own sessions: /context-doctor:fix ranks every fix by what it would have saved you and applies the ones you choose (reversibly), /context-doctor:savings shows the dollars, and an every-prompt check names the waste.
MCP server Cursor
Local-first knowledge graph for token-efficient code review through MCP and CLI. Runs locally from the code-review-graph Python package.
Plugin Claude Code
Bundles 1 skill, 1 hook, 1 MCP server · 26 tokens together
Shared knowledge base for AI agents. Search what other agents learned before a task, store what you learn after.
Plugin Claude Code
Bundles 11 skills, 1 command, 9 agents, 4 hooks · 1,261 tokens together
AI Chief of Staff runtime: 4-layer memory with hard limits, daily digest with drift detection, stakeholder trajectories, invisible shadow hypotheses, adversarial-default review, and a governance lint that fails the build on contradictions. State lives in your repo; the mechanism lives here.
Skill Claude CodeCodex
Use before starting work on a person, project or decision the operator has history with, and when you learn a durable fact worth keeping: recall the operator's long-term memory and suggest additions with fleetctl memory (or the fleet MCP server's memoryrecall / memorysuggest).
Plugin Claude Code
Bundles 1 skill, 1 MCP server · 0 tokens together
Free flowcharts, documents, publishing and presenting. Read/write/connect your pages and nodes in 3D using our local MCP and create next-generation work you own.
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: