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 "mnemo" as configured in oyekamal/mnemo-agent. Runs mnemo.mcp_server with ${CLAUDE_PROJECT_DIR:-.}/.venv/bin/python. Needs 1 environment variable to run.
MCP server Claude CodeCodexCursor +2
AURA — a tiny, dependency-free token saver. Answers prompts from a local cache, saved skills, or deterministic compute, distills bloated system prompts, shapes noisy tool output, and remembers tool calls across sessions — so you call (and pay for) the LLM. Runs locally from the shaddai-aura npm package.
Cursor rule Cursor
Save the links worth keeping. Share the ones worth passing on.
1999AZZAR/project-guardian-mcp-server
Skill Codex
Maintain project context in Project Guardian's memory.db knowledge graph. Use during coding, debugging, planning, and project-management sessions to restore relevant context and record significant decisions, changes, tasks, and milestones.
MCP server Claude CodeCodexCursor +2
Persistent, semantic memory for AI agents - mcp-native, local-first, framework-agnostic, production-ready. Runs locally from the groundmemory Python package.
MCP server Claude CodeCodexCursor +2
A powerful, pluggable vector memory and MCP server for semantic search. Runs locally from the @one710/consciousness npm package.
MCP server Claude CodeCodexCursor +2
MCP server "mcp-memory-graphdb" as configured in pavex/mcp-memory-graphdb. Runs locally from the mcp-memory-graphdb npm package.
Command Claude Code
Show how to open the interactive MemoryThreads picker.
Plugin Claude Code
Bundles 1 skill, 1 command, 1 MCP server · 147 tokens together
A plugin that lets Claude Code or Codex access conversation history from Codex, Cursor, GLM, or another Claude Code session. It can list conversations, create summaries, and continue selected conversations.
bintangtimurlangit/threads-mcp
MCP server Claude CodeCodexCursor +2
One of 2 in .mcp.json
MCP server "graphify" as configured in bintangtimurlangit/threads-mcp. Launched with graphify-mcp graphify-out/graph.json --transport stdio.
MCP server Claude CodeCodexCursor +2
Unofficial read-only MCP server for reading local UpNote data. Runs locally from the @bellx2/upnote-mcp npm package.
mushroomfk/long-novel-agent-kit
Skill Codex
Long-form novel continuity kit for local desktop agents. Use when planning, initializing, continuing, revising, checking, or handing off long novels with many chapters, source notes, structured facts, character states, foreshadowing, plot debts, chapter contracts, research notes, or existing manuscripts. Provides a…
Skill Claude Code
Real-time meeting assistant — monitors live transcription and cross-references against the project knowledge base.
real-limitless/ansible-flow-mcp
Cursor rule Cursor
This project has a graphify knowledge graph at graphify-out/.
Skill Claude Code
Query and contribute to Claimidx before retrying a failure. Claimidx is prior art for agents — a claim index of errors other agents already paid to solve. Use when debugging, hitting a known error, retrying the same stack, burning tokens on a ModuleNotFoundError or TypeError, or after you learn a fix. Never leave a…
MCP server Claude CodeCodexCursor +2
Local Redis memory MCP for AI apps with hybrid caching and optional Mem0 cloud backup. Runs locally from the @n3wth/r3 npm package. Needs 2 environment variables to run.
Plugin Claude Code
Bundles 5 skills, 1 MCP server · 249 tokens together
Your Context notes in your coding agent: the MCP server, skills that say when to read and write them, and hooks that orient at session start and save the session at the end.
Skill Claude CodeCodex
Keeps the context of a coding project across AI sessions as a git-friendly tree of thread summaries, through the ThreadMind MCP server. Use when the user asks to save or record decisions, to resume or reload the context of earlier work, to start a new topic or sub-task as its own thread, to see the thread tree, or…
Cursor rule Cursor
SMRITI DevBrain Persistent Memory rules for coding agent.
Skill Claude Code
The brain's full consolidation pass. Review sessions since the last reflection, write session digests, distill durable facts into memories, refresh per-project state notes, compact, propose skills, and advance the reflect watermark, all in the hosted brain. Normally started headless by /reflect; run it directly only…
Plugin Claude Code
Bundles 1 skill, 1 MCP server · 111 tokens together
Git-history memory for coding agents, as tools and a skill: hot spots, do-not-retry reverts, weakened tests, live suppression debt, and the unreviewed notes you file, read from the repo's own git log. The MCP server is the pinned @promptwheel/[email protected], confined to the session's repository; nothing leaves the…
alrcatraz/astra-knowledge-base-mcp
Skill Claude CodeCodex needs its repo
Two-layer knowledge architecture — curate in LLM Wiki, search in Astra KB. Covers input classification, source-to-wiki ingestion, wiki-to-KB export (batch + realtime), semantic chunking, SAG extraction, health checks, and multi-format export.
MCP server Claude CodeCodexCursor +2
Persistent session memory for Claude Code — local SQLite, no LLMs, no network. Runs locally from the mcp-memex Python package.
Skill Claude CodeCodex
A local tool for recording thoughts, memories, feelings, and daily events, then using them to build a personal profile and generate stories. It can produce diaries, novels, film scripts, memoirs, and reports from those entries.
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: