agent-memory plugins

160 tagged agent-memory, measured the same way as everything else here.

Browse within: agent 32agentic-ai 31ai-memory 25claude-code-plugin 23LLM 16cursor 14knowledge-graph 12local-first 12context-engineering 11cli 10mcp-server 10coding-agents 9knowledge-base 9knowledge-management 8

agent-brain

26

SpillwaveSolutions/agent-brain

Plugin Claude Code

Bundles 2 skills, 30 commands, 3 agents · 925 tokens together

Document search with hybrid BM25/semantic retrieval, GraphRAG knowledge graphs, and pluggable providers for Claude Code. Index documentation and code, then search using keyword matching, semantic similarity, graph relationships, or comprehensive multi-mode fusion.

not rated 119 changed 1mo ago A tokens not measured original MIT

ax

27

Necmttn/ax

Plugin Claude Code

Bundles 12 skills, 2 agents · 1,579 tokens together

ax - the agent experience layer. Local graph of every Claude Code + Codex session, skill invocation, edit, and commit. Surfaces what to use, what to ground on, and which experiments to package next.

not rated 117 +2 10d ago A tokens not measured AGPL-3.0

knowl

28

dat999zx/knowl

Plugin Claude Code

Bundles 1 MCP server

Persistent memory for Claude Code. Facts are typed, sourced, and retired when they change, so a query returns the current answer rather than every answer it has ever held. Local SQLite in your repository — no API key, nothing uploaded.

not rated 102 +24 changed today A tokens not measured original Apache-2.0

causal-memory

30

JingxuanC/causal-memory

Plugin Claude Code

Bundles 1 skill, 2 commands · 118 tokens together

Persistent causal memory for Claude Code — decisions, outcomes, and lessons that survive compaction. Same-context counterfactuals (natural experiments), a falsifiable prediction ledger, and an activation skill that teaches when to recall and record.

not rated 96 +14 changed today A tokens not measured original Apache-2.0

omem

31

seacen/omem

Plugin Claude Code

Bundles 1 skill, 1 MCP server · 458 tokens together

Office Memory (OMem) — local-first, agent-agnostic work-context memory layer. Lets Claude Code answer questions about your emails, calendar, documents, and team notes by querying a unified local wiki built from your Mail.app / Outlook / Calendar / Microsoft 365 / local folders.

not rated 86 3mo ago A tokens not measured

autograph

32

smixs/autograph

Plugin Claude Code

Bundles 1 skill, 1 command · 136 tokens together

Schema-as-code memory engine for Obsidian vaults that AI agents write to: typed cards, entity dedup, link repair, update-in-place (supersede + History), Ebbinghaus decay, MOC generation, and a vault health score. Plain Markdown you own, Python stdlib only. Ships the autograph skill plus a /research slash command that…

not rated 75 +1 1mo ago A tokens not measured original MIT

memxt

35

Yupcha/memXT

Plugin Claude Code

Bundles 1 skill, 2 commands, 3 hooks, 1 MCP server · 80 tokens together

Persistent, private, local-first memory for Claude Code. Your agent remembers your code and decisions across sessions — one static binary, no cloud, nothing leaves your machine.

not rated 49 +8 2mo ago A tokens not measured original MIT

palinode

36

phasespace-labs/palinode

Plugin Claude Code

Bundles 1 MCP server

Persistent memory for AI agents. Git-versioned markdown files as source of truth, hybrid SQLite-vec + FTS5 search, deterministic compaction. Every line in your agent's brain has a git blame.

not rated 46 +2 2d ago A tokens not measured original MIT

memclaw

38

Felo-Inc/memclaw

Plugin Claude Code

Bundles 1 skill · 226 tokens together

Persistent project workspaces for AI agents — task tracking, artifact storage, and semantic retrieval.

not rated 42 5mo ago A tokens not measured original MIT

kage

39

kage-core/Kage

Plugin Claude Code

Bundles 3 commands, 9 hooks · 60 tokens together

Kage manages your memory and agents. It briefs and runs agents in isolated git worktrees for a single run or a multi-wave goal, re-runs the checks itself instead of trusting the agent's report, and remembers what it learns so each brief is smarter than the last.

not rated 41 +1 1mo ago A tokens not measured GPL-3.0

inite-brain

40

inite-ai/inite-brain-service

Plugin Claude Code

Bundles 6 skills, 3 hooks · 520 tokens together

Persistent, bitemporal memory for Claude Code: the MCP tool surface, six skills that teach the model to use it, recall injected at session start, and capture before compaction.

not rated 41 changed today A tokens not measured AGPL-3.0

journal

41

mpazik/Binder

Plugin Claude Code

Bundles 8 skills · 148 tokens together

Personal journaling system built on Binder — morning briefings, day planning, reflections, summaries, and period-level goal tracking.

not rated 40 26d ago A tokens not measured original MIT

graft

43

AEndrix03/Graft

Plugin Claude Code

Bundles 6 skills, 2 hooks · 897 tokens together

Persistent local memory for coding agents: recall past fixes, decisions and gotchas before solving them again, and save what was learned.

not rated 34 +2 9d ago A tokens not measured original Apache-2.0

memini

45

eleboucher/memini

Plugin Claude Code

Bundles 10 skills, 9 commands · 547 tokens together

Persistent memory for AI coding agents via the memini memory service. 7 hooks, MCP tools, and skills that capture tool usage and inject prior context at session start and per prompt.

not rated 25 changed 2d ago A tokens not measured AGPL-3.0

yantrikdb

47

yantrikos/yantrikdb-mcp

Plugin Claude Code

Bundles 2 skills, 2 MCP servers · 136 tokens together

Cognitive memory for AI agents — semantic recall, a knowledge graph, contradiction detection and procedural learning. Local-first: one SQLite file, no account, no telemetry.

not rated 25 +1 yesterday A tokens not measured original MIT

fidelis

48

hermes-labs-ai/fidelis

Plugin Claude Code

Bundles 1 skill, 1 MCP server · 63 tokens together

Local agent memory with verbatim records, correction history, and time-aware recall. Provides fidelisrecall, fidelisstore, fideliscorrect, fidelisget, fidelisrecent, and fidelishealth.

not rated 24 changed 22d ago A tokens not measured original Apache-2.0