claude

context-mem

The highest-accuracy memory system for AI agents — 100% retrieval on LongMemEval. 14 content-aware summarizers, hybrid search (BM25 + vector + LLM judge), entity intelligence, decision trails. Fully local, zero cost.

20 on GitHubby Juba Kitiashviliv3.2.0MITupdated 6 months ago

Not in a marketplace yet, so it loads for one session with --plugin-dir.

Plugin context-mem in JubaKitiashvili/context-mem. Commands read from the repo's manifest — 1 month ago.

This plugin runs code on your machine — its hooks fire automatically on events like tool use and it starts local MCP servers. The exact commands are listed below; read them before installing.

What it installs

Skills (1)

  • context-optimization

    This skill should be used when context-mem is available in the project. Guides efficient use of context-mem's 29 MCP tools: observe large outputs, search before re-reading files, restore sessions, manage token budget, save knowledge with contradiction detection, promote knowledge to global cross-pro

Slash commands (6)

  • /context-mem:context-mem-handoff

    Generate a session handoff — saves current state and creates a continuation prompt for a new session

  • /context-mem:context-mem-history

    Show session chain history — previous sessions, their summaries, and token usage

  • /context-mem:context-mem-status

    Show session status — estimated token usage, session duration, observation count, and session chain

  • /context-mem:journal

    Show the activity journal — recent file edits, commands, and actions from this and previous sessions

  • /context-mem:search

    Search context-mem observations — find past code, errors, decisions, and context

  • /context-mem:status

    Show context-mem status — observation count, token savings, search capabilities, and dashboard link

MCP servers (1)

  • context-mem

    runs: npx -y context-mem serve

Hooks (8)

  • SessionStart

    node "${CLAUDE_PLUGIN_ROOT}/hooks/session-start-hook.js"

  • SessionStart

    node "${CLAUDE_PLUGIN_ROOT}/hooks/dashboard-autostart.js"

  • PostToolUse

    node "${CLAUDE_PLUGIN_ROOT}/hooks/activity-journal.js"

  • PostToolUse

    node "${CLAUDE_PLUGIN_ROOT}/hooks/context-mem-hook.js"

  • PostToolUse

    node "${CLAUDE_PLUGIN_ROOT}/hooks/proactive-inject.js"

  • UserPromptSubmit

    node "${CLAUDE_PLUGIN_ROOT}/hooks/user-prompt-hook.js"

  • Stop

    node "${CLAUDE_PLUGIN_ROOT}/hooks/dashboard-stop.js"

  • PreCompact

    node "${CLAUDE_PLUGIN_ROOT}/hooks/context-mem-precompact.js"

View source on GitHub npmjs.com

Similar plugins

claude-mem

claudecodex

Persistent memory for Claude Code: the next session starts where the last one left off.

29 skills · 1 MCP server · hooks

thedotmack/claude-mem 116,618

mem0

claudecodex

Cross-session memory and token savings for coding agents.

6 skills · 1 agent · 1 MCP server · hooks

mem0ai/mem0 68,893

context7

claudecodex

Up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your coding agent's context.

1 MCP server

upstash/context7 64,709

mempalace

claudecodex

AI memory system — mine projects and conversations into a searchable palace. 47 MCP tools, auto-save hooks, guided setup.

3 skills · 6 commands · 1 MCP server · hooks

MemPalace/mempalace 60,536

chrome-devtools-mcp

claude

Reliable automation, in-depth debugging, and performance analysis in Chrome using Chrome DevTools and Puppeteer

8 skills · 1 MCP server

ChromeDevTools/chrome-devtools-mcp 55,181

open-code-review

claude

Perform AI code review on Git diffs — supports workspace changes, branch ranges, and single commits with concurrent per-file analysis, codebase search, and deep context-aware review.

2 commands

alibaba/open-code-review 50,068

Maintain context-mem?

This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.

claude & codex pluginslisted