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
Local-first memory for AI coding agents: captures feedback and failures, turns them into ranked, conflict-resolved technical rules, and injects the relevant ones into Claude Code via MCP. Stays on your machine — no cloud, no API keys.
MCP server Claude CodeCodexCursor +2
A Model Context Protocol (MCP) server that implements a knowledge graph-based memory system with AI-powered entity and relation extraction. Runs locally from the kg-mem Python package.
tejpalvirk/quantitativeresearch
MCP server Claude CodeCodexCursor +2
MCP server "contextmanager-quantitativeresearch" as configured in tejpalvirk/quantitativeresearch. Runs locally from the contextmanager-quantitativeresearch npm package.
Cursor rule Cursor
Use TokenDiet MCP for high-yield compression only — logs, web, large files. Avoid extra MCP turns on small reads.
MCP server Claude CodeCodexCursor +2
MCP server "tinycontext" as configured in TinySuiteHQ/TinyContext. Runs in Docker (docker.io/marcellm01/tinycontext:v0.5.1). Needs 8 environment variables to run.
Skill Claude CodeCodex
Normative metadata schema v1 for all context-server records. Defines the kind registry (usermessage, report, plan, handoff, checkpoint, note, issue, upstreamissue, comment), required and optional metadata fields per kind, status vocabularies, the typed links object with its design rules, and the filter recipes that…
Plugin Claude Code
Context compression and persistent retrieval for Claude Code.
Plugin Claude Code
Bundles 6 skills · 612 tokens together
Agentic workflow with memory and tribal knowledge. Transforms Claude from goldfish to elephant with persistent knowledge across sessions.
Plugin Claude Code
Bundles 1 skill, 1 command · 55 tokens together
Single-line statusline HUD for Claude Code — model, thinking depth, context bar, subagents, 5h/7d/spend limits, top-model weekly gauge, folder · branch; DeepSeek / GLM / MiniMax balance.
Skill Claude CodeCodex
Ambient intelligence mode — continuous context awareness without explicit commands.
MCP server Claude CodeCodexCursor +2
Deterministic context budgeting for coding-agent workflows. Runs locally from the redcon Python package.
MCP server Claude CodeCodexCursor +2
Persistent project memory for LLMs via SQLite. Never re-explain your project again. Runs locally from the mindpm npm package. Needs 2 environment variables to run.
PAIR-Systems-Inc/goodmem-claude-code-plugin
Plugin Claude Code
Bundles 4 skills, 2 MCP servers · 191 tokens together
GoodMem memory infrastructure for AI agents. Use Python SDK skills to write code that manages embedders, spaces, and memories, or use MCP tools to perform GoodMem operations directly via natural language.
MCP server Claude CodeCodexCursor +2
Making AI Accountable Over Time - MCP server for persistent memory, automatic verification, and evidence-based grounding. Runs locally from the cortex-mcp Python package.
MCP server Claude CodeCodexCursor +2
MCP server "live-memory" as configured in Cloud-Temple/live-memory. Runs locally from the live-memory Python package.
Skill Claude CodeCodex
Wire mnemostack into OpenClaw as an MCP server, alongside the native OpenClaw memory tools (memorysearch / memoryget). The two coexist — mnemostack handles the hybrid pipeline (Vector + BM25 + Memgraph + Temporal + 8-stage rerank), while the native tools do fast file-scoped retrieval.
MCP server Claude CodeCodexCursor +2
Local-first, zero-API memory for AI agents. Persistent, private, and yours. Runs locally from the localmem-mcp Python package.
Skill Claude CodeCodex
Persistent cross-session memory via Engram's MCP tools (engramrecall, engramremember, engramcontext, engramfeedback, engramforget, engramstatus). Use this skill at the START of any session on a known project or with a known user — recall before acting. Also use it whenever the user states a preference, makes a…
knowledge-bridge-labs/llmwiki-serve
MCP server Claude CodeCodexCursor +2
Serve existing Markdown, Obsidian-style, or LLMWiki folders as cited agent-readable context. Runs locally from the llmwiki-serve Python package.
Plugin Claude Code
Bundles 1 skill, 11 hooks, 1 MCP server · 89 tokens together
A Lively plugin that connects AI sessions with an organisation's knowledge, projects, and domain map.
Cursor rule Cursor
Required handoff contract for nested TranscreveAI executions.
MCP server Claude CodeCodexCursor +2
Evidence-first local MCP server and CLI for codebase discovery, search, and source-backed tracing adapters. Runs locally from the project-context-mcp npm package.
Skill Claude Code
Long-term memory for coding agents. Auto-applies at the start of any coding task — recall past context before answering, capture decisions/learnings/fixes after work, use CodeGraph instead of grep for symbol lookup. Invoke when you see [remem-mcp] in your context or when starting any non-trivial coding work.
Skill Claude CodeCodex
Manage Active updates, atomic session handoffs, and human-gated Long-Term proposals. Use when asked to remember something, preserve a decision, log meaningful work, or review memory.
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: