Flowy lists 28 plugins that ship hooks for Agent Memory, and the most-starred are milla-jovovich-mempalace (59,737 stars), mempalace-mempalace (59,727 stars) and mksglu-claude-context-mode (32,573 stars). The newest push among those Agent Memory plugins with hooks, on October 28, 2026, went to mksglu-claude-context-mode.
Gives Claude Code a private memory that stays on your machine. It stores past conversations word for word, so you can ask what was decided, what happened before, or who was involved and get the original context back. It can also hand tasks to other agents.
@milla-jovovichInstall HookLocal-first memory for Claude Code. It stores conversations verbatim in a private palace you can search before answering about past work, people, projects, or decisions, with optional shared-brain hub setup.
@mempalaceInstall HookKeeps large tool outputs, logs, and files out of Claude Code's context window by processing them in a sandbox and indexing them for focused search. Includes diagnostics and a knowledge base indexer.
@mksgluInstall HookKeeps large command outputs, logs and data files out of your AI assistant's context by running processing in a sandbox and returning only the relevant parts. You also get a searchable index of local files and diagnostics for checking the setup.
@mksgluInstall HookGives coding agents a git-backed wiki for long-term project memory, with skills for retrieval, durable notes, session handoffs between agents, cross-project messaging, and memory consolidation.
@akitaonrailsInstall HookA coding agent harness whose agents keep memory and identity across sessions, so they learn and improve over time. You can run it in a terminal, in the browser, or through Telegram, Slack and Discord.
@letta-aiInstall HookA background agent for Claude Code that watches your sessions and reads your files, builds up memory over time, and offers guidance back during your work.
@letta-aiInstall HookAudits a Claude Code or Codex setup for context-window waste, fixes it with the user's approval, and measures the savings. It also tracks costs, helps resume prior sessions, and offers a usage dashboard.
@alexgreenshInstall HookA self-learning system for Claude Code that captures your corrections during sessions and reminds you to run /reflect to save them to CLAUDE.md as permanent memory. It also discovers recurring workflow patterns.
@bayramannakovInstall HookGive Claude Code photographic memory in ONE portable file. No database, no SQLite, no ChromaDB - just a single .mv2 file you can git commit, scp, or share. Native Rust core with sub-ms operations.
@memvidInstall HookA memory layer that lets AI agents read and write an agent-owned second brain in an Obsidian vault. It works through MCP servers, lifecycle hooks and a command-line tool, and includes skills for recording preferences and setting up semantic search.
@itechmeatInstall HookKeeps a repository's architecture decisions, constraints and cross-module contracts in persistent notes, so coding agents stop rediscovering the codebase each session. Agents pull only what a task needs and check it against the live code.
@tokenrollaiInstall HookReduces AI context cost for coding agents by compressing context in a way that can be reversed, with byte-exact recovery and an auditable receipt for each reduction. Runs locally and works through a proxy, MCP server, SDK, or agent wrapper.
@juyterman1000Install HookGives your AI assistant a persistent memory tree, so what you learn in one conversation carries into the next instead of resetting. It connects new topics to your earlier knowledge and saves useful findings as you go.
@mutable-state-incInstall HookGives Claude Code persistent memory across conversations, with local embeddings, semantic search and a knowledge graph. It runs offline as a single binary, with no cloud service or API keys needed.
@varun29ankusInstall HookA knowledge, decision, and verification governance system for long-running AI-assisted projects. It turns a strong agent's one-off work into shared project capability that future agents can inherit, verify, and evolve.
@qshanxInstall HookGives Claude Code a file-based memory system that records session context, compacts it into a daily, weekly, monthly and root summary tree, and searches it through qmd. No extra infrastructure is needed.
@kevin-hs-sohnInstall HookA transparent Claude Code and Codex plugin that preserves working state around /compact. It does not replace either runtime's compaction algorithm; it augments compaction through documented hooks.
@u-ichiInstall HookYour coding agent starts every session blank. It doesn't know what you worked on yesterday, what conventions your team follows, or what mistakes it already made. You re-explain everything, every time. Claude Remember fixes that.
@digital-process-toolsInstall HookAn opinionated, zero-infrastructure memory protocol for small-scale, local, file-based agent memory, a strict curation discipline plus a validator (tools/engramory_doctor.py), loaded as standing rules (CLAUDE.md / AGENTS.md / your host's rules file).
@tinqiao-ossInstall HookStores and recalls context across Claude Code sessions in local SQLite storage. Fires at session start and end, before compaction, and after tool use.
@hjertefolgerInstall HookStop fixing the same AI mistake twice. A Lean quality system for AI-assisted work, operators turn recurring defects into countermeasures. Built by a manufacturing operator, for people who actually ship.
@primefoldtoolsInstall HookYour CLAUDE.md, always in sync. Minimal tokens. Zero config. Just works. A Claude Code plugin that watches what Claude Code edits, deletes, and moves - then quietly updates your project memory in the background. No manual maintenance needed.
@severity1Install HookReviews your skill files on a schedule to flag stale or contradictory rules and suggests edits. Fires when you ask to audit or refresh your Claude skills or check their drift.
@summerliuuuInstall HookLoads the knowledge. Skips the search. 100% accuracy · 0 tool calls · −66% tokens vs Obsidian+MCP Real agentic sessions. Benchmark →
@guhcostanInstall Hook25 skills for AI coding agents, persistent memory, session awareness, and collaborative tools.
@soul-brews-studioInstall HookA Claude Code plugin that builds persistent, compounding knowledge bases inside Obsidian using the Karpathy LLM Wiki pattern. Ingest sources, query synthesized knowledge, lint for gaps, all from your Claude Code session.
@ekadetovInstall HookRuns persistent memory, self-reflection, and workflow planning across 15 skills and 15 commands for coding. Fires when you plan, debug, review, research, or ask it to recall prior context.
@kaimingwanInstall HookBy GitHub stars (Flowy does not rate quality), the best Agent Memory plugin with hooks for Claude Code is milla-jovovich-mempalace (59,737 stars), ahead of mempalace-mempalace (59,727 stars) and mksglu-claude-context-mode (32,573 stars).
Flowy lists 28 plugins that ship hooks for Agent Memory, and this page draws all 28 Agent Memory plugins with hooks.
