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
MCP server for Elephantasm Long-Term Agentic Memory — plug-and-play memory for any AI agent. Runs locally from the elephantasm-mcp Python package.
Plugin Claude Code
Bundles 4 skills, 1 agent, 3 hooks, 1 MCP server · 281 tokens together
Persistent knowledge management with pce-memory v2: raw observe, distill/promote pipeline, intent-aware activate, and layer-aware sync.
MCP server Claude CodeCodexCursor +2
Reduce Claude Code token usage by 70-90% with cross-session memory and four-layer optimization: semantic codebase indexing, PostToolUse tool compression, turn summarization, and session consolidation. MCP server powered by Ollama — zero API calls, runs en. Runs locally from the cctx-optimizer npm package.
MCP server Claude CodeCodexCursor +2
Versioned context store with hybrid search for AI agents. Stdio + HTTP MCP server and CLI. Runs locally from the membot npm package.
Skill Claude Code
Local, API-key-free persistent memory over MCP (SQLite + FTS5, no LLM/embeddings). Use when the user asks to remember, recall, or search something persistent across sessions ("hafızaya al", "hatırla", "bunu unutma", "remember this", "what did I say about..."), or wants to set up/troubleshoot the memorry MCP server…
lestercoyoyjr/Centralaizer-public
Cursor rule Cursor
Centralaizer shared-memory hub — recall before, remember after.
sujkh85/infinite-context-keeper-node
MCP server Claude CodeCodexCursor +2
MCP server: persistent memory, compaction, semantic recall (Node.js port). Runs locally from the infinite-context npm package.
MCP server Claude CodeCodexCursor +2
MCP server for Compresh — production-grade context compression with TUL 2.0 query-aware retrieval (paid tier) over the open tulbase core. Runs locally from the compresh-mcp Python package.
MCP server Claude CodeCodexCursor +2
MCP proxy that compresses tool schemas — up to -98% tokens, 100% signal preserved. Runs locally from the refract-mcp Python package.
MCP server Claude CodeCodexCursor +2
Local multimodal memory for AI agents — cross-modal vision-language search. Runs locally from the recallforge Python package.
MCP server Claude CodeCodexCursor +2
MCP server for mem.ai API integration. Runs locally from the @hskksk/mem-ai-mcp-server npm package.
MCP server Claude CodeCodexCursor +2
Reflection's autonomous runtime — wake, read prior state, do useful work, write back, sleep. Runs locally from the reflect-mcp Python package.
MCP server Claude CodeCodexCursor +2
BrainRegion（脑区）：AI collaboration infrastructure for review, consultation, planning, and memory. Runs locally from the brainregion Python package.
MCP server Claude CodeCodexCursor +2
Git-native, shareable project memory for AI coding agents — fully local, no cloud. Runs locally from the ctxmem Python package.
clawdbrunner/universal-memory-service
MCP server Claude CodeCodexCursor +2
MCP server "universal-memory-service" as configured in clawdbrunner/universal-memory-service. Runs locally from the universal-memory-service Python package.
MCP server Claude CodeCodexCursor +2
Memory Vault MCP Server — Markdown + SQLite knowledge store with bidirectional [[wikilinks]] for AI agents. Runs locally from the vault-mcp Python package.
MCP server Claude CodeCodexCursor +2
Agnostic persistent memory server for AI tools via MCP. Knowledge graph stored in SQLite with FTS5 keyword search, multi-tenant by namespace. Runs locally from the @jalipata/mcp-memory npm package.
MCP server Claude CodeCodexCursor +2
Persistent memory layer that saves and recalls your project context and preferences. Remote server at mcp.memxus.com.
MCP server Claude CodeCodexCursor +2
A local memory system for coding agents that stores past interactions and retrieves relevant information later. It runs through MCP, a standard way for AI tools to connect to programs.
SiamAlSobari/mnemo-agent-memory
Skill Claude CodeCodex
Memory engine + markdown notes + knowledge graph for AI coding agent.
Plugin Claude Code
Bundles 1 skill, 1 hook, 1 MCP server · 56 tokens together
Associative long-term memory — recall by key-graph association, plus passive memory surfacing on every prompt.
nikitacometa/mnemon-memory-mcp
MCP server Claude CodeCodexCursor +2
Persistent layered memory MCP server for AI agents — SQLite + FTS5 backend. Runs locally from the mnemon-mcp npm package. Needs 3 environment variables to run.
MCP server Claude CodeCodexCursor +2
MCP server "server-smart-memory" as configured in MauriceIsrael/SmartMemory. Runs locally from the @modelcontextprotocol/server-smart-memory npm package.
Skill Claude Code
Mandatory long-term memory workflow for Codex, Claude Code, and MCP clients backed by the local Ariadne server (Qdrant + bge-m3). Always use at the start or resumption of substantive project work, after context compaction, when prior work or decisions may matter, and immediately after durable decisions, gotchas…
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: