1,174 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
Plugin Claude Code
Bundles 5 skills, 1 MCP server · 481 tokens together
Long-term memory for AI agents. Save and recall conversation knowledge as a knowledge graph (MemoryWeft) via a hosted MCP server.
Plugin Claude Code
Bundles 1 skill, 1 MCP server · 88 tokens together
Shared AI-context layer for teams — one memory every teammate's agents search and update, so knowledge captured once reaches the whole team across sessions and tools.
Plugin Claude Code
Bundles 1 skill, 1 MCP server · 51 tokens together
A local-first knowledge engine for AI-assisted software work. Requires the free Wuniq desktop app, currently available for Windows and Linux.
Plugin Claude Code
Bundles 1 skill, 1 MCP server · 93 tokens together
Keep notes in your own daily notebook at notes.jpwilliams.dev — your AI writes into the same graph you do, and reads it back next session.
Plugin Claude Code
Bundles 1 skill, 3 hooks, 1 MCP server · 153 tokens together
A trust layer between Claude Code and its own past: memory with per-hit staleness verdicts, claim-level use attribution, measured effectiveness, and episodic run-state. Retrieval is opt-in at the tool surface, plus a score-gated recall hook that injects a single stored pointer on the 2% of prompts the silent-miss prob.
Plugin Claude Code
Bundles 4 commands, 1 hook · 92 tokens together
GFT (Git for Thought) — bring your white-box thinking map into Claude Code: /gft:list & /gft:login answer instantly (zero tokens), /gft:link & /gft:save connect your maps to the conversation.
Plugin Claude Code
Local-first shared memory for AI tools. Plain files are the source of truth; relevant context is injected before your prompt instead of burned on agentic search loops.
Plugin Claude Code
Ephemeral (7-day TTL) hybrid vector + BM25 memory server for Claude Code, backed by Redis Stack. Multilingual out of the box (NFKC + CJK / Hangul / Thai / Lao / Myanmar / Khmer bigram + diacritic fold). Prerequisites: (1) Redis Stack running on localhost:6379 (docker run -d --name redis-stack -p 6379:6379…
Plugin Claude Code
Bundles 12 skills, 2 hooks, 1 MCP server · 901 tokens together
The memory Claude Code is missing. Your team's decisions and context persist across sessions and across teammates, recorded with the author and the date attached, and injected when the session starts.
adelaidasofia/graph-autotagger-mcp
Plugin Claude Code
FastMCP server that reads a pre-computed Obsidian knowledge graph and suggests wikilinks, God Node connections, and community memberships for vault notes. Companion to graphify.
Plugin Claude Code
Bundles 4 commands, 1 agent · 125 tokens together
Financial-grade agent memory for Claude Code — bitemporal recall, SEC 17a-4 audit chain, GDPR/HIPAA crypto-shred, and information barriers. Built for finance, healthcare, and legal teams.
Plugin Claude Code
Bundles 1 skill, 3 hooks · 79 tokens together
Working-memory shelf for Claude Code: the /shelve skill plus a SessionStart hook that injects the shelf INDEX (recall bootstrap) and a SessionEnd/PreCompact hook that pushes the shelf so episodes survive an ephemeral container.
Plugin Claude Code
Search and pull context from your AI chat history (ChatGPT, Claude, Codex, Claude Code) without copy-pasting. Reads your vault live from your own Google Drive — read-only, zero server-side storage.
Plugin Claude Code
KMP by Underpass.
Plugin Claude Code
Bundles 4 skills, 1 MCP server · 215 tokens together
Connect to an Orcha context workspace and teach agents how to use it well.
Plugin Claude Code
Persistent AI memory for Cursor, Claude Code, and ChatGPT. Save and search memories via Zdravo.
Openly-Useful/operations-pulse
Plugin Claude Code
Bundles 1 skill, 1 MCP server · 68 tokens together
Run governed local operational heartbeats and maintain durable ticket memory.
Plugin Claude Code
Bundles 4 skills, 1 hook · 222 tokens together
Save and resume session handoffs — capture intent at session end, surface it at the next SessionStart.
TerminallyLazy/tree-ring-memory-claude-plugin
Plugin Claude Code
Bundles 1 skill, 7 commands · 136 tokens together
Local-first memory lifecycle, project bootstrap, and receipt-backed harness guidance for Claude Code using Tree Ring Memory v0.15+.
Plugin Claude Code
tsumugi memory integration — 3 inject-only hooks (SessionStart, UserPromptSubmit, PreToolUse(Read)) that surface past memory and guide agent-driven saveobservation calls. Does NOT create observations from raw tool output (avoiding the contamination problem documented in ADR-011).
Plugin Claude Code
Bundles 12 skills · 1,262 tokens together
Local org-roam-style knowledge graph (SQLite) with paper-ingest + loop skills and an MCP server.
Plugin Claude Code
Bundles 1 skill, 1 MCP server · 101 tokens together
Hybrid search + code graph + semantic memory for Claude Code, via the nexus-mcp-ci pip package. Requires pip install nexus-mcp-ci first — this plugin registers the MCP server and teaches Claude when to use it, it does not install the Python package.
MemoryNexus/memory-nexus-plugins
Plugin Claude Code
Bundles 1 skill, 1 hook, 1 MCP server · 0 tokens together
Persistent knowledge layer for Claude Code. Store context, retrieve briefings, and maintain continuity across sessions.
Plugin Claude Code
Bundles 5 skills · 61 tokens together
Persistent AI memory — remember, recall, and build knowledge across every session. Your AI never starts from zero again.
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: