claude-mem
claudecodexPersistent memory for Claude Code: the next session starts where the last one left off.
29 skills · 1 MCP server · hooks
Query Intent Solutions' governed knowledge brain from Claude Code — qmd://-cited answers, per-user audit, deterministic governance. Compile, then govern.
Not in a marketplace yet, so it loads for one session with --plugin-dir.
Plugin intent-brain in jeremylongshore/bobs-big-brain-registrar. Commands read from the repo's manifest — today.
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.
brain-saveCreate one Registrar memory proposal or apply a supported lifecycle transition to an existing memory. This is a local operator write and never auto-fires. Use when an administrator needs to preserve one team fact or retire an outdated memory. Trigger with "/brain-save".
brainSearch and analyze Intent Solutions' governed team memory through the Registrar, returning qmd:// citations for supported claims. Use when checking recorded architecture, infrastructure, decisions, runbooks, or conventions. Trigger with "/brain", "ask the team brain", or "check the team knowledge ba
teamkbReview, classify, and capture a bounded set of team insights or explicitly approved Markdown files through the local Registrar operator tools. This is side-effecting and never auto-fires. Use when closing a session, importing a small document batch, reviewing existing memory, or checking local brain
teamkb-classifierCategorizes caller-supplied document text into a MemoryCategory as standalone advisory output. Use only for operator-requested category advice; the caller must supply the document text. This definition does not establish a caller.
teamkb-conflict-checkerCompares a caller-supplied proposed memory and similar-memory list for advisory conflicts. Use only for operator-requested comparison advice; the caller must supply the proposal and comparisons. This definition does not establish a caller.
teamkb-curatorReviews recent session work and proposes team-worthy memories when an operator explicitly requests it. Reads recent tool calls, file changes, and decisions. For each insight worth sharing, calls teamkb_propose MCP tool. The governance pipeline (deterministic, not this agent) decides promotion.
teamkb-scoutDiscovers trending agent tools, MCP servers, and Claude Code plugins that could benefit the team. Use when an operator requests discovery advice. Queue reference proposals only after the operator has established a server-side review gate for this workflow; otherwise return findings for human review.
teamkbruns: node ${CLAUDE_PLUGIN_ROOT}/plugin-runtime/teamkb-remote.cjs
"${CLAUDE_PLUGIN_ROOT}/scripts/bootstrap.sh"
"${CLAUDE_PLUGIN_ROOT}/scripts/flush-spool.sh"
Persistent memory for Claude Code: the next session starts where the last one left off.
29 skills · 1 MCP server · hooks
AI-powered codebase understanding — analyze, visualize, and explain any project
9 skills · 10 agents · hooks
Cross-session memory and token savings for coding agents.
6 skills · 1 agent · 1 MCP server · hooks
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
Code intelligence powered by a knowledge graph. Provides execution flow tracing, blast radius analysis, and augmented search across your codebase.
12 skills · 1 MCP server · hooks
Universal memory runtime for Claude Code with cross-session memory, entity-aware recall, lifecycle hooks, skills, commands, and memory-curator agents
7 skills · 7 commands · 2 agents · hooks
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.