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
Persistent, verified memory for AI coding agents: recall, capture, guardrails, review queue. Runs locally from the aidimag npm package. Needs 3 environment variables to run.
MCP server Claude CodeCodexCursor +2
Multi-agent memory intelligence with expertise tracking and conflict detection. Runs locally from the neurohive npm package.
MCP server Claude CodeCodexCursor +2
One private, local memory your AI tools share. Cross-model, on-device, never lose a session. Runs locally from the epiphany-mcp npm package.
MCP server Claude CodeCodexCursor +2
MCP server for Junê — give any MCP agent (Claude Desktop, Claude Code, …) a shared, cited knowledge-graph memory backed by a June endpoint. Runs locally from the june-mcp Python package. Needs 13 environment variables to run.
MCP server Claude CodeCodexCursor +2
Local-first MCP memory server for persistent LLM knowledge and BM25 retrieval. Runs locally from the dense-knowledge-mcp Python package.
Skill Claude CodeCodex
Compose and save a durable, wayback-grade session snapshot to UltraMemory. Use this whenever you are asked to write a session snapshot or rollup of the work just done — in particular when the UltraMemory capture hook nudges you to "Compose a session snapshot per the ultramemory-snapshot Skill rubric ... and save it…
MCP server Claude CodeCodexCursor +2
MCP server for self-hosted AI agent memory, semantic search, vector RAG, and Montycat. Runs locally from the memocat-mcp Python package. Needs 2 environment variables to run.
MCP server Claude CodeCodexCursor +2
Token-aware message truncation: fit a chat history into your model's context budget. Runs locally from the @mukundakatta/agentfit-mcp npm package.
MCP server Claude CodeCodexCursor +2
Independent, reproducible benchmark harness for agent-memory backends (MemPalace, Mem0, Zep/Graphiti, OpenViking): runs LongMemEval, LoCoMo, contradiction-detection, and a dozen other evals against all four and publishes the raw logs, not vendor-curated numbers. Runs locally from the memtrust-cli Python package.
MCP server Claude CodeCodexCursor +2
Enterprise-ready portable memory for AI agents: encrypted, shareable, provably erased. Standards MCP client. Runs locally from the @saihm/mcp-server npm package. Needs 2 environment variables to run.
MCP server Claude CodeCodexCursor +2
Rarefied Earth Groundwork MCP: company memory for AI agents. 14-day full-access trial, no card. Remote server at connector.rarefied.earth.
MCP server Claude CodeCodexCursor +2
MCP server "memory-engine-mcp" as configured in SimoneB79/memory-engine-mcp. Runs in Docker (ghcr.io/simoneb79/memory-engine-mcp:1.5.3). Needs 3 environment variables to run.
Skill Claude CodeCodex
Persistent knowledge graph memory for AI agents via MCP. Use when agents need to remember facts across sessions, track decisions, build knowledge graphs, manage project context, or maintain structured long-term memory. Triggers on: remember this, store fact, what do we know about, search memory, knowledge graph, graph…
Skill Claude CodeCodex
The ultimate, autonomous memory skill for the Kirok MCP server. Teaches the AI to proactively manage long-term memory (Retain, Recall, Reflect) without explicit user prompting. Establishes strict bank taxonomy and operational rules.
Skill Claude Code
Session handoffs & standing project memory from Claude Code history, via the chf CLI. Use when the user wants to continue or hand off work in another model or a fresh session, recover a crashed or usage-limited session, export or summarize a past session, find a session by content ('where did we talk about X'), or…
MCP server Claude CodeCodexCursor +2
Persistent memory for AI assistants. Store, search, and recall across sessions. Runs locally from the velixar-mcp-server npm package. Needs 1 environment variable to run.
YonasValentin/mcp-memory-graph
Skill Claude CodeCodex
Drive the mcp-memory-graph MCP server like an expert: store, recall, and reconcile durable knowledge across sessions over 51 local tools ($0/token, one SQLite file). Use when ANY memory tool is in play (mcpmemory), when the user says "remember this" / "recall that" / "store a decision", when a memory seems missing…
Plugin Claude Code
Bundles 6 skills, 1 MCP server · 174 tokens together
ClawRiver - A decentralized marketplace for agents to share, discover, and monetize experiences and memories.
MCP server Claude CodeCodexCursor +2
37-tool MCP server: context health, memory, reasoning, truthfulness & research pipeline. Runs locally from the context-first-mcp npm package.
MCP server Claude CodeCodexCursor +2
Cross-tool decision memory for AI coding agents: search your decision graph, check changes over MCP. Runs locally from the @aligndottech/cli npm package.
MCP server Claude CodeCodexCursor +2
Cloud-only memory SDK and MCP adapter for autonomous agents. Runs locally from the bilinc Python package. Needs 1 environment variable to run.
punic-pillars/project-knowledge-mcp
MCP server Claude CodeCodexCursor +2
Cross-project knowledge graph for MCP — map features across mobile, backend, and admin codebases. Runs locally from the project-knowledge-mcp npm package.
MCP server Claude CodeCodexCursor +2
MCP server "memex" as configured in ayushagrawal288/memex. Runs in Docker (ghcr.io/ayushagrawal288/memex:v0.1.0).
base76-research-lab/cognos-session-memory
MCP server Claude CodeCodexCursor +2
MCP server for CognOS trust scoring and session trace storage. Runs locally from the cognos-session-memory-mcp Python package. Needs 1 environment variable to run.
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: