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

catalyst-dev

49

coalesce-labs/catalyst

Plugin Claude Code

Bundles 33 skills, 9 agents · 4,039 tokens together

Complete development workflow: research → plan → implement → validate → ship. Includes research agents, planning tools, handoff system, Linear integration, and PM commands.

not rated 20 changed 22d ago A tokens not measured archived

logseq-brain

52

jame581/LogseqBrain

Plugin Claude Code

Bundles 7 skills, 1 agent, 1 hook · 600 tokens together

Persistent memory for Claude using a dedicated Logseq graph. Save and load project context, decisions, and progress across sessions and devices.

not rated 18 changed 20d ago A tokens not measured original MIT

commitlore

53

MongLong0214/commitlore

Plugin Claude Code

Bundles 7 skills, 1 command, 1 hook · 631 tokens together

Recorded decisions from git history, delivered to the agent before it edits. Constraints, alternatives already ruled out, and warnings left by whoever was here last.

not rated 18 changed 13d ago A tokens not measured original MIT

aria-knowledge

54

mikeprasad/aria-knowledge

Plugin Claude Code

Bundles 12 MCP servers

ARIA — Applied Reasoning and Insight Architecture. Persistent human-governed knowledge for Claude Code via a five-phase lifecycle: capture → govern → promote → apply → refresh. Stages session insights/decisions/feedback into review backlogs, promotes approved items to a tag-indexed markdown base, and applies them via…

not rated 17 changed 16d ago A tokens not measured

local-agent-toolkit

55

jnMetaCode/local-agent-toolkit

Plugin Claude Code

Bundles 3 skills · 118 tokens together

Local-first memory, skills and tracing for your agent: engram (recall/remember your notes via MCP), skillet (search/install agent skills via MCP), plus skills that teach the agent to use them — nothing leaves your machine.

not rated 16 +1 4mo ago A tokens not measured

titen-memory

56

RamaAditya49/titen

Plugin Claude Code

Bundles 1 skill · 77 tokens together

Use Titen's evidence-grounded collaborative memory. The local stdio mode needs no configuration; a served Titen endpoint is the alternative for a shared store.

not rated 16 yesterday A tokens not measured original Apache-2.0

kernel

58

ariaxhan/kernel-claude

Plugin Claude CodeGemini CLI

KERNEL's methodology layer for Gemini CLI: 27 software-engineering agent skills plus llms.txt as ambient context. Skills cover systematic debugging (reproduce, isolate, regression-test), generating competing approaches before implementing, pre-implementation critique, code review, bounded context handoff and resume…

not rated 14 +1 changed 1mo ago A tokens not measured original MIT

token-warden

59

vukkt/token-warden

Plugin Claude Code

Bundles 7 commands, 4 agents, 3 hooks · 380 tokens together

Agent memory, charged rent. A Stop hook records what each session costs; expensive runs are distilled into candidate efficiency rules; each candidate is benchmarked on a frozen golden suite and kept only if it saves at least twice its context rent. Six commands. Two theorems survived measurement and three were deleted.

not rated 13 changed 1mo ago A tokens not measured original MIT

memory-crystal

61

memorycrystal/memorycrystal

Plugin Cursor

Bundles 5 skills · 236 tokens together

Persistent Memory Crystal memory for Cursor: MCP tools, capture/recall hooks, and the crystal skill suite.

not rated 12 changed 5d ago A tokens not measured original MIT

exomem

64

Artexis10/exomem

Plugin Claude Code

Bundles 10 skills, 5 hooks · 372 tokens together

Governed long-term memory over a markdown vault: raw sources stay immutable, conclusions are compiled with provenance, and nothing is deleted - it is superseded. Requires EXOMEMVAULTPATH to point at your vault; run exomem setup if you do not have one yet.

not rated 10 changed today A tokens not measured AGPL-3.0

witness

66

IngTian/witness

Plugin Claude Code

Bundles 4 hooks, 1 MCP server

Quietly captures your Claude Code sessions and distills how your thinking, habits, and knowledge change over time — a dated growth archive with provenance, served over MCP. Also ingests any text corpus (notes, articles, market news) to track how THAT changed instead. Local, single Go binary.

not rated 10 1mo ago A tokens not measured original MIT

pluribus

67

johnnyjoy/pluribus

Plugin Claude Code

Bundles 6 skills, 1 agent, 3 hooks, 1 MCP server · 281 tokens together

First-party Pluribus memory loop for Claude Code: MCP, hooks (session wake-up + prompt recall, optional failure hint), skills, and a recall-first investigator agent. Server owns memory; plugin orchestrates.

not rated 9 1mo ago A tokens not measured

tsubasa

68

ramarahmanda/tsubasa

Plugin Claude Code

Bundles 5 skills, 4 hooks · 372 tokens together

Captain persona: repo-resident domain expert with a git-stored knowledge graph, ambient knowledge capture, and ADR-threaded delegation.

not rated 9 1mo ago A tokens not measured original MIT

goodmem

69

PAIR-Systems-Inc/goodmem-claude-code-plugin

Plugin Claude Code

Bundles 4 skills, 1 MCP server · 191 tokens together

GoodMem memory infrastructure for AI agents. Use Python SDK skills to write code that manages embedders, spaces, and memories, or use MCP tools to perform GoodMem operations directly via natural language.

not rated 9 changed 2d ago A tokens not measured original MIT

hypermnesic

70

leonardsellem/hypermnesic

Plugin Claude Code

Bundles 1 hook, 1 MCP server

Memory for coding agents: hybrid search/recall, entity resolution, and a gated git-first write over a self-hosted, OAuth2-authenticated tailnet MCP. The default memory layer for coding agents.

not rated 9 changed 23d ago A tokens not measured AGPL-3.0

artel

71

NicolasPrimeau/artel

Plugin Claude Code

Bundles 4 commands, 5 hooks, 1 MCP server · 53 tokens together

Ambient shared memory for Claude Code: injects the note you need when you need it — your last handoff at session start, relevant notes on each prompt, file-anchored gotchas before you edit — and writes the session back afterwards, including what it cost. Points at your own self-hosted Artel via ARTELURL / ARTELAGENT.

not rated 9 changed 6d ago A tokens not measured original MIT

cc-memory

72

skymanbp/cc-memory

Plugin Claude Code

Bundles 2 skills, 1 command, 2 agents, 5 hooks · 260 tokens together

Persistent memory for Claude Code — automatic save/restore across compactions and sessions. Anti-patch reconcile-on-write + LLM-judged semantic de-duplication, forced PROGRESS.md handoff with per-session annotation, live PLAN.md anchor, injection observability, FTS5 search, AI-judged extraction with Haiku + local…

not rated 9 +1 changed yesterday A tokens not measured original MIT

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: