12,529 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.
Plugin Claude Code
Bundles 1 skill, 1 agent, 1 hook · 145 tokens together
CodeAlive context engine for semantic code search and AI-powered codebase Q&A. Enables AI coding agents to understand entire codebases beyond just open files — search across all indexed repositories, trace cross-service dependencies, discover usage patterns, and get synthesized answers to architectural questions.…
MCP server Claude CodeCodexCursor +2
Persistent memory for AI coding tools via MCP. Remembers across sessions and machines. Runs locally from the memoir-cli npm package.
Plugin Claude Code
Bundles 9 skills, 3 hooks · 326 tokens together
Persistent project-aware memory for AI coding tools. Built on MCP. Structural map, decisions, session history — zero native deps.
Plugin Claude Code
Bundles 2 skills, 1 command, 1 agent, 3 hooks, 1 MCP server · 134 tokens together
Multi-tiered memory and knowledge base with semantic search, auto-compaction, and built-in evaluation. Works across Claude Code, Copilot CLI, OpenCode, Cline, and Cursor.
Cursor rule Cursor
ALWAYS INCLUDE to HAVE Project Context.
AdrianV101/obsidian-pkm-plugin
Plugin Claude Code
Bundles 6 skills, 2 commands, 3 agents, 2 hooks · 1,200 tokens together
Bidirectional knowledge flow between Claude Code and Obsidian — 20 MCP tools, skills, and hooks for PKM.
ozankasikci/global-agent-memory
Skill Codex
Retrieve and curate durable, project-aware knowledge through the Global Agent Memory MCP server. Use before substantial planning, implementation, refactoring, debugging, handoff preparation, or investigation when prior decisions, exact identifiers, recurring errors, verified solutions, preferences, or conventions may…
nmeierpolys/mcp-structured-memory
MCP server Claude CodeCodexCursor +2
A Model Context Protocol server that automatically maintains structured, domain-specific memory documents for focused projects. Runs locally from the @nmeierpolys/mcp-structured-memory npm package.
MCP server Claude CodeCodexCursor +2
Local-first memory for AI coding agents: shell history with exit codes, git diffs, docs, MCP. Runs locally from the nexusmem npm package.
Skill Claude CodeCodex
Emit privacy-safe receipts for context selection, deferral, hydration, compaction, pruning, delegation, usage attribution, and boundary handoffs.
studiomeyer-io/local-memory-mcp
MCP server Claude CodeCodexCursor +2
Persistent local AI memory. SQLite + FTS5 + vector search, knowledge graph. No cloud, no API keys. Runs locally from the @studiomeyer/local-memory-mcp npm package. Needs 4 environment variables to run.
Skill Claude CodeCodex
Use when a repository needs one lightweight repository memory profile that evolves with the codebase to reduce drift, prevent structural mistakes, and keep current repository truth plus durable working context explicit. Trigger for requests to refresh current-state or architecture docs from live code, classify or…
Skill Codex
A setup and note-taking workflow for saving articles, videos, podcasts, and local files as Markdown notes in Obsidian, a local knowledge-management app. It can optionally accept input through Feishu or WorkBuddy and copy verified notes to Feishu Docs after authorization.
prime-radiant-inc/ledger-memory
Plugin Claude Code
Ledger-backed persistent memory for coding agents.
Cursor rule Cursor
At the start of every coding task call memory.fetchcontext to load current state, conventions, and prior decisions. After making a durable choice, hitting a footgun, or wrapping a session, call memory.proposeupdate. Always prefer this over re-reading raw source files when you need project context.
Cursor rule Cursor
Hunch engineering memory — consult the hunch MCP tools before editing.
Skill Claude Code
Activate at the start of any session where memoryweb MCP tools are available. Covers filing, connecting, and retrieving knowledge through the memoryweb graph — any coding, architecture, backlog, or general work an agent is tracking for this user.
Plugin Claude Code
(Alpha) Persistent memory, architectural decisions, and safety guardrails for Claude Code. Your agent starts every session with full project context — stack, decisions, patterns, safety rules, and a handoff from the previous session.
MCP server Claude CodeCodexCursor +2
MCP server for Midas — local-first, source-traceable agent memory with no LLM at ingest. Runs locally from the midas-memory-mcp Python package. Needs 4 environment variables to run.
Plugin Claude Code
Bundles 25 skills, 7 agents, 12 hooks · 1,073 tokens together
Skills and agents for the software lifecycle in Claude Code: research, design, planning, test-first building, code review, security checks and release. Includes a local code index, per-project workspace notes, stack-specific guidance at session start, and optional Jira and Confluence access.
Skill Claude CodeCodex
Persistent memory for agents. Stores preferences, decisions, facts, and events as a connected knowledge graph. Recalled by who, what, when, or why.
Plugin Claude Code
Bundles 1 skill, 3 commands, 3 hooks, 1 MCP server · 89 tokens together
The memory layer for agent teams. Deterministic retrieval, hard per-project isolation, zero LLM in the critical path.
yejianye/ob-smart-connections-mcp
MCP server Claude CodeCodexCursor +2
MCP server for Smart Connections - semantic search for Obsidian vaults. Runs locally from the @yejianye/smart-connections-mcp npm package.
shivamsharmxa/obsidian-mcp-server
MCP server Claude CodeCodexCursor +2
A local MCP server that exposes your Obsidian vault as structured tools for Claude.ai. Runs locally from the obsidian-claude-mcp npm package.
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: