Memory plugins

Persists context across Claude Code sessions using a local knowledge graph and SQLite memory store, enabling cross-session recall, project timeline narratives, and AI-powered knowledge bases built from past observations.

Persist and retrieve project context across Claude Code sessions via a semantic memory palace — mine files, conversations, and decisions into searchable knowledge, then recall them automatically or on demand with filtering.

Manage an entire Paperclip AI-agent company through chat: hire governance-aware agents, decompose plans into parallel tasks, monitor work product and costs, and persist knowledge across sessions using PARA file memory.

Save and restore project context across sessions using vector search and token budget management, enabling coherent long-running conversations and multi-agent workflows with semantic memory.

Automatically curate Claude Code's auto-memory by promoting important learnings to CLAUDE.md and .claude/rules, extracting proven patterns into reusable skills, and reviewing memory health with actionable reports.

Retains important information across Claude Code sessions via OpenViking long-term semantic memory, automatically recalling relevant context, capturing session data, and tracking skill usage.

Preserves agent memory decisions, conventions, bugs, and discoveries across coding sessions and compactions without manual saving, while automating session lifecycle hooks in Node.js

Persistent, cross-session semantic memory for Claude Code that surfaces past context and distills recurring workflows into reusable skills, with optional shell hooks for session automation.

Persist and retrieve project-specific knowledge across Claude Code sessions by automatically saving architectural decisions, bug fixes, and implementation details to Supermemory. Scan codebase context on demand and sync configuration remotely for consistent memory across environments.

Search and retrieve past Claude Code conversations to remember decisions, patterns, and solutions, avoiding redundant work and ensuring consistency across sessions.

Automatically capture corrections and feedback from Claude Code sessions, then update CLAUDE.md memory files so Claude learns from mistakes and improves future responses. Analyzes session history, detects patterns, and maintains a learning queue with confidence scoring for efficient memory management.

Retrieve and reuse context from prior Claude-Code and Codex-CLI sessions to resume interrupted work, search past decisions, and avoid re-explaining task state.

Learn any topic using first-principles concept DAGs, Socratic tutoring with free-recall verification, and FSRS-scheduled spaced repetition, plus a telemetry dashboard for retention stats and grader audits.

Provides a suite of creative writing tools for drafting, revising, outlining, character development, and editorial review, enabling writers to plan stories, generate prose, receive reader-simulated feedback, and maintain story consistency.

Automatically saves and indexes Claude Code conversations to an SQLite database with full-text search, enabling context restoration across sessions, retrospective analysis of decisions and patterns, and memory consolidation with automated pruning and verification against codebase ground truth.

Persist your coding lessons, decisions, and playbooks as local JSON files that MCP-compatible tools (Claude Code, Cursor, Codex) can query, with AI proposing additions while high-risk changes wait for your approval and everything stays reversible.

Persist Claude Code's memory across sessions by storing discoveries, decisions, and solutions in a portable .mv2 file. Search, query, and recall past context to maintain continuity in your work.

Enable AI assistants with persistent, relational memory across sessions using graph-vector storage. Store, recall, update, delete, and link memories for durable context awareness.

Persist session context and learn from agent decisions using reinforcement learning, backed by Turso for scalable memory storage across Claude Code sessions.

Persist and recall facts, decisions, and context across Claude Code sessions using local-first memory, reversible context compression to reduce token usage, and code graph intelligence for impact analysis and codebase navigation.

Maintain cross-host durable memory for AI agents using the ling-mem CLI, storing a biographical three-tier model of user identity across sessions and hosts, with optional caveman mode for simplified interactions.

Query and traverse an Obsidian vault as a local knowledge graph — search semantically, find paths between nodes, detect communities, and analyze graph relationships using natural language claims.

Persist and recall working memory across Claude Code sessions — load relevant memories on start, capture decisions and outcomes at session end, search and inspect past context on demand, and automatically consolidate memories over time with decay-aware retention.

Enables structured development workflows from discovery to deployment with sequential thinking, persistent memory across sessions, and business context retrieval for CRM integration.

Continuously remembers context across Claude Code sessions via Honcho, eliminating the need to repeat preferences and project details. Includes interactive setup, preference surveys, and session lifecycle management with shell integration.

Automate memory management for Claude Code sessions by running shell scripts at lifecycle events (session start/end, pre-compact, user prompt submit) to sync with AKB's agent-memory vault, enabling environment setup, cleanup, or logging.

Persist project context, decisions, and progress across Claude sessions by saving and loading a dedicated Logseq graph. Initialize graph structure, repair formatting issues, and view a dashboard of project statuses.

Capture, search, and synthesize project knowledge directly from Claude Code sessions — bookmark URLs, save decisions and meeting notes, sync GitHub issues/PRs, and get automated briefings and deep research summaries from your growing knowledge base.

Automatically searches past Claude Code sessions before web research, planning, debugging, and bash errors to reuse prior solutions and workflows, with manual query support and hooks that enforce tool usage policies

Persists conversation context across Claude Code sessions, automatically injecting relevant memories on new prompts and enabling queries about past work to maintain continuity in long-running projects.

Persist and recall cross-session context for Claude Code using neuroscience-inspired long-term memory, automatically capturing project state and integrating with Obsidian for structured notes

Give Claude Code persistent memory across sessions to recall facts, manage TODOs, record expenses, and restore handoff state using a standalone script or MCP server.

Persist and retrieve developer decisions, corrections, and preferences across Claude Code sessions with a multi-tiered memory system that auto-compacts and evaluates semantic drift

Turns an Obsidian vault into a compiled knowledge base with AI-powered research loops, memory synthesis, contradiction detection, pattern mining, and automated note cleanup. Lets you research topics, connect ideas, review decisions, and maintain vault health through Claude Code.

Index, search, and persist cross-session memory for your codebase — hybrid file search saves tokens by finding relevant docs before reading, while session snapshots and shared dashboards sync knowledge across machines

Persist and retrieve decisions, learnings, and context across Claude Code sessions, organizing knowledge into namespaced memories that are automatically surfaced when relevant via hybrid, vector, or text search, and analyze project artifacts for memory integration gaps.

Maintain persistent project memory across Claude Code sessions, preserving stack information, architectural decisions, coding patterns, safety rules, and previous session handoffs so your agent starts each session with full context.

Build persistent, self-correcting memory for Claude Code sessions — capture lessons, corrections, and facts as structured vault notes, then automatically retrieve them at relevant moments to inform multi-step task execution and subagent routing.

Powers persistent, cross-device memory for AI coding agents via a self-hosted Mori server. Distill every session into durable, searchable knowledge so agents start each session informed. Include /brief to load shared context, /pensieve to search past decisions, and tools to seed, flush, and broadcast memories across agents.

Persistent memory system that enables AI coding assistants to recall past work, decisions, error solutions, and project history across sessions using a 3-layer memory search for token-efficient retrieval.

Captures every Claude Code prompt into deterministic long-term memory, serves role-scoped memories each turn, survives /clear and compaction, and logs every keep/merge/drop decision. Optionally integrates with Obsidian daily notes.

Build a persistent learning and knowledge system within Claude Code: capture decisions, extract reusable patterns from work sessions, maintain quality gates, run maintenance reviews, and teach topics through structured lessons — all backed by markdown files for long-lived team memory.

Ingest knowledge from URLs, files, and chat sessions into a Claude-maintained personal wiki. Query it to get answers synthesized from related pages with citations. The wiki automatically cross-links and indexes new content.

Save and restore project context across sessions using semantic memory and vector search. Supports full, incremental, and diff restoration modes with semantic tagging and multi-session collaboration.

Persist and retrieve Claude Code's conversational memory across sessions using mnemonic phrases and SQLite with FTS5 full-text and vector search, and automate custom shell commands on lifecycle events such as session start/stop, user prompts, tool uses, and subagent stops.

Persist AI memory across coding sessions using a local SQLite database, automatically remembering decisions, patterns, and bugs while reviewing memory health and suggesting cleanup actions.

Store and retrieve long-term associative memory for AI agents using SurrealDB, with spreading activation recall that mimics human memory.

Manage Claude Code's auto-memory by saving key learnings, promoting patterns to permanent rules, and packaging proven solutions into reusable skills. Includes memory auditing, health dashboards, and error capture.

Enforces a disciplined task workflow (understand, track, verify, review) and maintains project-specific memories to prevent Claude from drifting off course.

Persist and recall project knowledge, architectural decisions, and session context across Claude Code sessions using Cognis memory. Automatically index codebases to capture structure and patterns, enabling continuity between sessions.

Captures user prompts and agent responses to Memory Engine for persistent context across sessions, with optional Windows-only automation for gate checks, reminders, and archiving

Losslessly compress Claude Code conversation context using DAG-based summaries that preserve every message, allowing you to explore past discussions, promote insights across sessions, and diagnose memory pipeline health with compaction review and automated diagnostics.

Manage Neo4j graph databases across cloud and local environments, execute Cypher queries, design and model graph schemas, and use Neo4j as persistent memory for structured information across Claude sessions.

Persist and recall context across Claude Code sessions using episodic memory, knowledge progressions, and user preferences. Track evolving understanding of topics, search past sessions across projects, and store tool choices and workflows for consistent behavior.

Persist Claude Code conversation history across sessions with markdown storage, hybrid BM25 and dense retrieval for searching past interactions, and optional Anthropic Haiku enrichment.

Logs user prompts to a SQLite database via a Python script, providing a lightweight journal/memory system with natural language time queries and auto-capture for context recovery.

Store and retrieve persistent memory across AI agent conversations and sessions using vector search (LanceDB), git-based knowledge graphs, and cloud backup to prevent context loss and enable long-term recall.

Preconfigures Claude Code with MCP servers for local file system operations, persistent memory via a knowledge graph, and HTTP web fetching, enabling expanded tool capabilities from a starter template.

Boost Claude Code productivity through ultra-compressed token modes, persistent cross-session memory, and automated skill workflows for code review, git operations, testing, and planning.

Automatically saves each completed Claude Code session as a commit in a jujutsu repository, with pre-prompt linting and post-session reflection to preserve conversation memory.

Retain and retrieve persistent context across Claude Code sessions via a knowledge server — search prior work, ingest meeting notes, and get synthesized summaries of identity, projects, and priorities, with optional session hooks for Obsidian integration and reflection prompts.

Monitors Claude Code session context health by tracking a passphrase through canary messages and reporting it after /compact, helping developers detect context degradation and memory loss during long sessions.

Build and orchestrate multi-step autonomous agent workflows with filesystem operations, GitHub integration, persistent memory, documentation lookup, sequential reasoning, and web scraping.