1,159 tagged Memory and context, measured the same way as everything else here.
Browse within: claude-code-plugin 212agent-memory 119ai-memory 96LLM 70mcp-server 63ai-tools 49cli 47knowledge-management 46local-first 45agents 44context-engineering 44knowledge-graph 44knowledge-base 43ai-coding 41
ogham-mcp/ogham-superpowers-bridge
Plugin Claude Code
Bundles 2 skills, 1 hook · 104 tokens together
Orchestrator-mediated Ogham memory bridge for the superpowers subagent pipeline: per-dispatch lesson recall + staged distilled flush, with subagent isolation preserved by construction.
harrystamatoukos/ai-conversation-extractor
Plugin Claude Code
Bundles 2 skills, 3 commands, 1 hook · 148 tokens together
Extract valuable insights, decisions, patterns, and ideas from AI conversation exports (ChatGPT, Claude, Claude Code) into Obsidian-compatible notes. Includes a mirror analysis feature that builds a living psychological profile from your conversation patterns. Processes your chat history day-by-day using a Ralph…
Plugin Claude Code
Bundles 7 skills, 2 agents · 623 tokens together
Bootstrap an LLM-maintained knowledge base via a prism-driven interview: start from sample raw inputs (facts), derive the right page types, kinds, and relationships (concepts & categories) with the ontology-prism / KEOPS method, then scaffold the schema, conventions, and operating skills for the new wiki — and dogfood.
Plugin Claude Code
Bundles 4 skills, 3 hooks · 136 tokens together
Captures and retrieves the decisional context behind code changes — constraints, choices, and reasoning — so future agents don't repeat mistakes or lose established patterns across sessions.
Plugin Claude Code
Bundles 6 skills, 1 agent, 1 hook, 1 MCP server · 206 tokens together
AI-accessible knowledge you actually own — plain markdown on your disk.
Plugin Claude Code
Bundles 3 commands · 0 tokens together
Bodai plugin for the Session-Buddy memory MCP server.
Plugin Claude Code
Bundles 2 skills, 1 MCP server · 198 tokens together
Agent-driven knowledge base with immutable raw sources, mutable wiki pages, BM25 search, code analysis, and self-checking lint. Use when managing knowledge bases, importing documents, writing wiki pages, or parsing source code.
Plugin Claude Code
Bundles 1 skill, 1 MCP server · 50 tokens together
Autonomous virtual robot brain — perception, LLM reasoning, episodic memory, personality engine.
daniellmorris/local-claude-chat-history-mcp
Plugin Claude Code
Search your local Claude Code and Claude Cowork conversation history — list recent sessions, full-text search transcripts, and read full conversations stored on your own machine.
Plugin Claude Code
Bundles 2 skills · 67 tokens together
Give your AI a memory it never forgets. Local-first persistent memory with semantic search, temporal validity, knowledge graph, memory tiers, and privacy controls. 28 MCP tools.
Plugin Claude Code
Bundles 1 skill, 4 hooks, 1 MCP server · 38 tokens together
Persistent memory for AI coding agents. Survives across sessions and compactions.
Plugin Claude Code
Bundles 3 skills, 3 commands, 1 agent, 10 hooks · 176 tokens together
Enforcement, memory and parallel-session coordination for solo founders running several Claude Code sessions on one repository.
Plugin Claude Code
Bundles 2 skills, 3 commands · 355 tokens together
Memory-first reasoning layer for Claude Code. Kills cross-chat AI amnesia.
Plugin Claude Code
Bundles 4 skills, 1 command, 1 MCP server · 832 tokens together
Build and operate McBrain — a persistent, LLM-maintained personal knowledge base based on Karpathy's LLM Wiki pattern. Bundles cooperating skills for one-shot vault setup, day-to-day operations (ingest/query/lint/synth), and a local research tracker with a creator skill and a queue runner that drains research tasks…
Plugin Claude Code
Bundles 3 skills · 153 tokens together
Build and maintain persistent personal knowledge base for deep technical research.
Plugin Claude Code
Bundles 1 skill · 95 tokens together
Load and maintain durable project knowledge through Rementum.
Plugin Claude Code
Bundles 6 skills · 641 tokens together
Memory and lore. Karpathy LLM-Wiki 3-layer under the neutral .llmwiki/ root (insight + wiki + raw): bootstrap-wiki, ingest-finding (reversible diff-log + cross-page update), lint-wiki (four wiki-rot modes), plaud-note-taking (PLAUD Whisper transcript correction into .llmwiki/raw/transcripts/), plus five hooks …
Plugin Gemini CLI
Stack-aware developer intelligence for your agent: CVE scans, dependency health, upgrade plans, decision memory. Privacy-first — only public package names leave the machine.
Plugin Gemini CLI
IANA-registered .faf project context for Gemini, with a deterministic AI-readiness score. Read, validate, score, and sync one source across GEMINI.md / CLAUDE.md / AGENTS.md. Run /faf:setup after install.
Plugin Claude Code
Bundles 2 skills, 2 commands · 129 tokens together
Obsidian-based 3-tier memory system — hippocampus for Claude Code. Persistent, searchable, graph-linked.
Plugin Claude Code
Session recall MCP server — hybrid FTS5 + vector search over past Claude Code sessions.
Plugin Claude Code
Bundles 1 skill, 2 MCP servers · 71 tokens together
Shared memory for AI coding agents. Decisions, fixes, and gotchas persist per repo — local by default, shared with your team via threadctx.dev. What one teammate's agent learns, everyone's agents remember.
Plugin Claude Code
Bundles 1 skill, 1 MCP server · 75 tokens together
AI-native structured memory for agents (lore/doc) for Claude Code. This plugin is a free distribution channel for the LinkLore MCP server; team sync, cross-project sharing, and cloud backup are a paid backend service (subscription) at linklore.io.
Plugin Claude Code
Bundles 2 skills, 1 MCP server · 161 tokens together
Persistent, queryable memory for your agent: a real Postgres it asks in plain English over MCP, so it can GROUP BY / JOIN / aggregate over what it remembered instead of recalling the nearest few rows. Bundles the hosted MCP server plus two skills that teach the agent when to use it.
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: