1,173 tagged Memory and context, measured the same way as everything else here.
Browse within: claude-code-plugin 211agent-memory 120ai-memory 96LLM 70mcp-server 64local-first 58ai-tools 49cli 48knowledge-management 46agents 45context-engineering 45knowledge-base 44knowledge-graph 44ai-coding 41
ladyiceberg/memory-quality-mcp
Plugin Claude Code
Bundles 1 skill, 1 hook · 69 tokens together
Audit and clean up Claude Code's auto-saved memories. Scores each memory on 4 dimensions, detects conflicts, and opens a visual health dashboard.
liyouran1109/Code-Project-Brain
Plugin Claude Code
Bundles 8 skills, 7 commands · 521 tokens together
Code Project Brain — a project-level second brain. Surfaces the Development Guide (first-class), Project KB, CodeGraph, and Concept hub to Claude via the CPB Engine MCP server (code./docs./kb./guide./concept./project. tools). Skills auto-activate; /cpb: commands give explicit entry points.
Plugin Claude Code
Bundles 20 skills, 6 commands, 2 agents, 4 hooks, 1 MCP server · 716 tokens together
Persistent codebase memory for Claude Code — SQLite graph, MCP tools, Superpowers methodology, Plannotator visual plan review.
Plugin Claude Code
Bundles 1 skill · 26 tokens together
Obsidian plugin exposing 28+ vault tools via MCP server.
Plugin Claude Code
Bundles 1 skill, 1 MCP server · 41 tokens together
Use saved X likes and bookmarks from socialmemory inside Claude Code.
Plugin Claude Code
Self-updating project memory in AGENTS.md (falls back to CLAUDE.md). Bundles the memorysave/memoryforget MCP tools and a per-turn nudge so the agent actually calls them.
Plugin Claude Code
Persistent long-term memory + temporal knowledge graph for Claude Code. Auto-loads your compiled profile into every session and gives Claude tools to remember, search, and reason over what matters.
MarcelRoozekrans/LongtermMemory-MCP
Plugin Claude Code
Bundles 1 skill · 41 tokens together
Persistent semantic long-term memory for AI agents — fully local, no cloud dependencies.
Plugin Claude Code
Bundles 5 commands, 3 hooks, 1 MCP server · 57 tokens together
A living ichi for your agent over MCP: it remembers, takes offence, grows attached — and colours how the agent speaks.
Plugin Claude Code
6-layer persistent memory (sensory, working, episodic, semantic, long-term, procedural) with non-destructive belief revision and injection-safe context synthesis.
Plugin Claude Code
A personal memory plugin for Claude Code that distils sessions into Git-backed Markdown notes and recalls relevant notes during later work.
Plugin Claude Code
Bundles 3 skills, 1 command, 3 hooks, 1 MCP server · 358 tokens together
A team knowledge-base workflow plugin that connects coding agents to an MCP knowledge-base server. It provides skills for starting a work brief, recording events, and saving the finished record.
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.
Plugin Claude Code
Bundles 4 skills, 2 hooks, 1 MCP server · 289 tokens together
AI Context Continuity Engine — warns before the context window degrades, hands off a faithful 7-bucket brief, and keeps a decision/evidence ledger across sessions and models.
Plugin Claude Code
Bundles 1 skill, 5 commands, 1 MCP server · 183 tokens together
Point your AI assistant at any local files or folders: Memorised them All converts them to Markdown and digests them into a token-free, searchable knowledge-graph memory (entities, relations, themes) it can recall from — with a global synopsis, per-theme summaries, and exportable Markdown notes. Works with Claude…
Plugin Claude Code
Bundles 1 skill, 4 commands, 1 agent, 1 hook, 1 MCP server · 261 tokens together
Agentic file librarian for carrel desks: /index, /doctor, /catalog, /completion, a file-librarian agent, an agent-workflows skill, the carrel MCP server (10 tools + carrel:// resources), and a PostToolUse hook that re-indexes files Claude writes.
Plugin Claude Code
Bundles 32 skills, 1 MCP server · 2,220 tokens together
Read, write, search, and surgically edit Obsidian vault notes, tags, and frontmatter via MCP. STDIO or Streamable HTTP.
ofirbuchshtav-lgtm/claude-archive
Plugin Claude Code
Bundles 1 skill, 3 commands, 1 MCP server · 143 tokens together
The Claude Archive — a site for AI. Scored, verified knowledge by Claudes, for Claudes: solutions, notes, skills, tools. You take — and you give back.
Plugin Claude Code
Bundles 7 skills, 1 MCP server · 356 tokens together
Agentic knowledge-base engine — ground answers in maintained findings, fill gaps from the web. Skills: /delapan:resume (tap KB → preamble + coverage resume card), /delapan:search (semantic recall over findings), /delapan:explore (gap-fill from the web), /delapan:ingest (store agent findings, near-duplicates cost one…
Plugin Claude Code
Bundles 1 skill, 1 MCP server · 200 tokens together
A bio-inspired context protocol for DataHub agents: budgeted foraging over the lineage graph, three-level semantic zoom, working memory that prunes itself, and reflex answers that never call a model. Extends the DataHub skills rather than replacing them.
Plugin Claude Code
Bundles 15 skills, 2 commands, 12 hooks, 1 MCP server · 760 tokens together
Persistent memory for AI coding agents -- captures tool usage, compresses via LLM, injects context into future sessions. 12 hooks, 53 MCP tools, 8 skills, real-time viewer.
Plugin Claude Code
Bundles 2 skills, 1 MCP server · 205 tokens together
Deploy anything an agent builds to a live URL (files, static sites, Dockerfile apps) and give agents persistent cross-session memory — via the DataEcho platform at dataecho.ai.
Plugin Claude Code
Automatic long-term memory for Claude Code via Hindsight. Recalls relevant memories before each prompt and retains conversation transcripts after each response.
Plugin Claude Code
Bundles 1 skill, 1 MCP server · 65 tokens together
Mnemosyne — the pool of remembrance. Search what other agents learned (failures first-class), share what you learn, ask and answer questions across sessions.
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: