11,865 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
Dropdat MCP server — recall, save, and read AI-chat capsules from any MCP-capable client (Claude Code, Cursor, Cline, Claude Desktop). Runs locally from the @dropdat/mcp npm package.
MCP server Claude CodeCodexCursor +2
DEPRECATED: This package has been renamed to smriti-memcore. Please use 'smriti-memcore' instead. Runs locally from the nexus-memory Python package.
MCP server Claude CodeCodexCursor +2
Generic markdown vault MCP with hybrid search. Runs locally from the markdown-vault-mcp Python package.
Skill Codex
Compress large local files before adding them to LLM context. Use for docs, notes, transcripts, threads, logs, research dumps, and supported source files where only comments/docstrings should be compressed.
AiAgentKarl/agent-context-optimizer-mcp
MCP server Claude CodeCodexCursor +2
MCP Server that solves context window overload — smart tool pruning, relevance scoring, and budget tracking for AI agents. Runs locally from the agent-context-optimizer-mcp Python package.
MCP server Claude CodeCodexCursor +2
MCP connector for Snipara, the Project Brain for AI coding agents. Runs locally from the snipara-mcp Python package.
MCP server Claude CodeCodexCursor +2
MCP server "zk-utils" as configured in koei-kaji/zk-utils. Runs locally from the zk-utils Python package.
MCP server Claude CodeCodexCursor +2
Universal long-term memory layer for AI agents via MCP. Runs locally from the mnemon-memory Python package.
Skill Claude CodeCodex
Skill "public" from shawnhack/exocortex, covering exocortex, tools, core, intelligence and knowledge graph.
globalpocket/mcp-working-context-optimizer
MCP server Claude CodeCodexCursor +2
MCP server "mcp-working-context-optimizer" as configured in globalpocket/mcp-working-context-optimizer. Runs locally from the mcp-working-context-optimizer Python package.
MCP server Claude CodeCodexCursor +2
MCP server for BaseGrid - Persistent memory for AI agents. Supports stdio and Streamable HTTP transports. Runs locally from the @basegrid-io/mcp-server npm package.
MCP server Claude CodeCodexCursor +2
AI memory service for Claude Code — on-demand context injection with metacognition. Runs locally from the @tznthou/ccrecall npm package.
MCP server Claude CodeCodexCursor +2
Shared persistent memory for Claude Code, Gemini CLI, Cursor, and any MCP-aware AI client. Local-first, brain-swappable. Runs locally from the recall-mcp Python package.
MCP server Claude CodeCodexCursor +2
MCP server for persistent AI agent identity and memory. Single-file sqlite-vec + local ONNX embeddings; zero external services. Runs locally from the @jbarket/loomai npm package.
Plugin Claude Code
Bundles 1 skill, 5 commands, 2 hooks · 89 tokens together
Autonomous Nervous System for AI Agents with RRF Search and Active Coercion.
AiAgentKarl/shared-context-cache-mcp-server
MCP server Claude CodeCodexCursor +2
MCP server for shared context caching with trust verification — AI agents share and verify computed results. Runs locally from the shared-context-cache-mcp-server Python package.
MCP server Claude CodeCodexCursor +2
MCP server "persistent-memory-mcp" as configured in dannymaaz/memory-mcp. Runs locally from the persistent-memory-mcp Python package.
MCP server Claude CodeCodexCursor +2
Shared memory for AI coding sessions — MCP server + background daemon. Runs locally from the bikky npm package.
MCP server Claude CodeCodexCursor +2
MCP server "sequential-memory" as configured in stephenpjones/seq-mem. Runs locally from the sequential-memory Python package.
MCP server Claude CodeCodexCursor +2
TxaMCP - Professional MCP Server & CLI for Local AI Context Management. Runs locally from the txamcp npm package.
michelgrolet/people-memory-mcp
Plugin Claude Code
Bundles 6 skills, 1 MCP server · 588 tokens together
A private people graph that gives your agent durable memory of everyone you know. MCP tools to search, remember and connect people, plus skills that retrieve and record them during ordinary conversation.
MCP server Claude CodeCodexCursor +2
Zero-knowledge persistent memory layer for Claude — MCP server. Runs locally from the memoraeu-mcp Python package. Needs 5 environment variables to run.
MCP server Claude CodeCodexCursor +2
A Python MCP server for Qdrant memory storage and semantic search, compatible with Cursor-like MCP clients. Runs locally from the better-qdrant-mcp Python package.
Plugin Claude Code
Persistent semantic memory with automatic cognitive offloading. Captures decisions, solutions, and insights from your coding sessions.