claude-mem
claudecodexPersistent memory for Claude Code: the next session starts where the last one left off.
29 skills · 1 MCP server · hooks
Shared memory for Claude Code, Codex, and DOXA: capped curated facts, evidence-backed beliefs, FTS5 session search, staged review, learned skills, and signed sync.
Plugin lore from marketplace lore in docwilde/LORE. Commands read from the repo's manifest — yesterday.
This plugin runs code on your machine — its hooks fire automatically on events like tool use. The exact commands are listed below; read them before installing.
loreRead and maintain LORE's shared user and repo memory, or search indexed Claude and Codex sessions when past context matters. Use for requests to remember or recall facts and when stored preferences may affect a task.
lore-exportExport LORE memory, beliefs, pending proposals, file maps, and learned skills to a signed offline bundle when the user wants to carry them to another machine without a sync service.
lore-importImport a signed LORE offline transfer bundle from another machine, merging portable memory and beliefs through LORE's normal conflict and pending gates.
/lore:approveReview and approve one exact staged LORE proposal
/lore:askAsk the lore belief store a question (dialectic — synthesized, cited answer)
/lore:backfillFull-transcript backfill — page every message of a session (or all sessions of a project) through the deriver, not just the newest window
/lore:configView and toggle LORE stages (inject, index, review, beliefs, skills, streaming)
/lore:contextShow exactly what lore holds in context right now — user, project and machine memory as tables, interaction model, belief count
/lore:doctorDiagnose lore — environment checks, effective config, memory/index state. Read-only.
/lore:filemapProject file map — where the load-bearing files live (show the table, or add an entry)
/lore:graphBelief graph — backfill the edges the store implies, then inspect or draw it
/lore:helpOne-screen reference card for all lore commands and the memory model
/lore:motdDelta view — what changed in lore since you last looked (new beliefs, pending count)
/lore:pendingList lore's staged memory/skill proposals from background review
/lore:rejectReview and reject one exact staged LORE proposal
/lore:rememberStore a fact in lore memory (decides user, project or machine scope)
/lore:reviewTrigger lore background review of the current session now (TUI-visible task)
/lore:setupGet lore working — run doctor, then fix each finding behind its own gate
/lore:statusLore memory usage, session index and pending counts
"${CLAUDE_PLUGIN_ROOT}/bin/lore" hook --engine claude --event session-start
"${CLAUDE_PLUGIN_ROOT}/bin/lore" hook --engine claude --event prompt
"${CLAUDE_PLUGIN_ROOT}/bin/lore" hook --engine claude --event pre-compact
"${CLAUDE_PLUGIN_ROOT}/bin/lore" hook --engine claude --event session-end
Persistent memory for Claude Code: the next session starts where the last one left off.
29 skills · 1 MCP server · hooks
Open-source AI job search that runs locally in your AI coding CLI: scan job portals, evaluate listings into a structured A-H report with a 1-5 score, tailor your CV, track applications
5 skills · 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
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
Long-term semantic memory for Claude Code, powered by OpenViking
5 skills · 1 command · 1 MCP server · 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.