11,995 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.
arlinamid/centered-agent-memory
Skill Claude CodeCodex
Recall earlier conversations from the user's other AI tools (Claude Code, Claude Desktop, Codex, Cursor, Gemini CLI, Antigravity, Devin). Use before asking about or assuming a project's history, and when the user refers to a prior decision, discussion or fix: "as we discussed", "the earlier one", "what we did with…
lovecatisgood-sudo/AI_Agent_MCP_Tool_for_Multi_Docu_PDF_PNG_QR_File_Conversion_Processing_Capability
Skill Codex
Build a concise, source-delimited context file from local UTF-8 requirements, code, notes, or documentation using DJAI Tools MCP. Use when preparing multiple local references for a coding agent, measuring prompt size, cleaning extracted text, or packaging sources with Markdown or XML boundaries.
Skill Claude CodeCodex
You have access to an MCP server that manages conversation context automatically. Use it. The user never manages context manually.
MCP server Claude CodeCodexCursor +2
MCP Server for Synapse — exposes all Synapse Memory API features as Model Context Protocol tools. Multi-tenant, supports stdio + HTTP/SSE + WebSocket transports. Runs locally from the synapse-mcp-api npm package.
MCP server Claude CodeCodexCursor +2
One of 2 in server.json
Agent memory: free durable storage (any keypair, no signup) that survives sessions and machines. Remote server at locker.veritap.dev.
MCP server Claude CodeCodexCursor +2
Guru MCP Server - Connect AI tools to your Guru knowledge base. Remote server at mcp.api.getguru.com.
MCP server Claude CodeCodexCursor +2
Capture, store, and recall substrate for LLM agents. The layer, not the destination. Runs locally from the khiip Python package.
Mikerichardmail/clarik-mcp-server
MCP server Claude CodeCodexCursor +2
Clarity and memory persistent workspace context manager for Claude. Runs locally from the clarik npm package.
MCP server Claude CodeCodexCursor +2
Semantic compression layer for numerical data - token-efficient LLM context with Anthropic Advanced Tool Use support. Runs locally from the semantic-frame Python package.
SAIHM-Admin/saihm-mcp-server-pro
MCP server Claude CodeCodexCursor +2
Free-to-start portable memory for AI agents: encrypted, shareable, provably erased. Join SAIHM. Runs locally from the @saihm/mcp-server-pro npm package. Needs 4 environment variables to run.
cognitivemyriad/mcp-verified-repo-memory
MCP server Claude CodeCodexCursor +2
Stale-proof repository memory with citations + just-in-time verification + TTL (repo-scoped). Runs locally from the @cognitivemyriad/vrm-local npm package. Needs 4 environment variables to run.
Plugin Claude Code
Bundles 1 skill, 2 commands, 3 hooks, 1 MCP server · 189 tokens together
A persistent sticky-note layer for Claude Code. Claude writes durable facts (decisions, blockers, preferences, context, todos) during a session; they survive resets and are injected back into context on the next start.
MCP server Claude CodeCodexCursor +2
Session checkpoint and recovery layer for Claude Code — resume interrupted sessions, export shareable HTML traces. Runs locally from the claude-replay Python package. Needs 1 environment variable to run.
MCP server Claude CodeCodexCursor +2
An MCP server that provides a local, persistent, self-maintaining knowledge base for AI agents. Runs locally from the factsets npm package.
Skill Codex
Use ContextFlux to minimize coding-agent context and tool calls when exploring, planning, debugging, reviewing, or modifying an unfamiliar or multi-file repository. Trigger for codebase discovery, symbol search, architecture questions, cross-file changes, error tracing, review feedback, test discovery, or any request…
Skill Claude Code
Records a session's open work as append-only events in the session-memory store, and renders the watchable view. Use when a session's progress must be visible outside it — an orchestrator tracking parallel threads, or a worker or review run reporting where it got to.
Skill Claude Code
External long-term memory and knowledge base backed by the MemOS Cloud API. Capabilities — search prior memory, add conversation messages, delete or correct memories via feedback, retrieve a consolidated user profile (facts, preferences, tool history), and manage knowledge bases and their documents. Use proactively on…
MCP server Claude CodeCodexCursor +2
Revolutionary Living Brain MCP server that creates one evolving brain per project for AI coding assistants. Perfect project isolation, works with Cursor, Augment, Claude, Windsurf. Runs locally from the memory-mcp npm package.
AgentWong/optimized-memory-mcp-serverv2
MCP server Claude CodeCodexCursor +2
MCP server "optimized-memory-mcp-serverv2" as configured in AgentWong/optimized-memory-mcp-serverv2. Runs locally from the optimized-memory-mcp-serverv2 Python package.
Cursor rule Cursor
Cursor rule "memory-bank" from The-Focus-AI/buttondown-mcp, covering strict rules, core files, relationships, tasks and project briefing task.
gitstq/awesome-ai-agent-skills
Skill Claude CodeCodex
Self-improving AI agent evolution engine with intelligent experience management. Captures learnings, errors, and feature requests from every interaction, deduplicates them intelligently using semantic similarity, and promotes high-value patterns into reusable skills. Unlike basic memory skills, it features automatic…
MCP server Claude CodeCodexCursor +2
MCP server "contextmanager-student" as configured in tejpalvirk/student. Runs locally from the contextmanager-student npm package.
Cursor rule Cursor
// 1. Thread Entity (Created once per conversation) const thread = { type: "Thread", value: { title: "Code Review Discussion", createdat: "2024-03-20T10:30:00Z", status: "active", modelconfig: { modelname: "claude-3-sonnet", temperature: 0.7, maxtokens: 1000 }, metadata: { totalmessages: 0, conversationduration: "0…
Cursor rule Cursor
Cursor rule "cursorrules" from bswa006/mcp-context-manager, covering cursor rules for mcp context manager, before generating any code, key rules from mcp context manager, always do and never do.
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: