Memory and context plugins

1,156 tagged Memory and context, measured the same way as everything else here.

Browse within: claude-code-plugin 207agent-memory 113ai-memory 89ai-tools 50knowledge-base 44knowledge-management 44context-engineering 43ai-coding 42local-first 42knowledge-graph 41context-management 38obsidian 28claude-plugin 27embeddings 21

lean-context

505

asarnaout/lean-context

Plugin Claude Code

Bundles 1 skill · 49 tokens together

Distills verbose project documentation into terse, agent-optimized context files.

not rated 5 6mo ago A tokens not measured original MIT

metacog

506

houtini-ai/metacog

Plugin Claude Code

Bundles 2 hooks

Real-time metacognition for Claude Code. Six senses detect stuck loops, validation bias, repeated errors, and circular actions. Learns what works across sessions.

not rated 5 4mo ago A tokens not measured original Apache-2.0

g-akshay/ClaudeShrink

Plugin Claude Code

Automatically compress large natural text or log files before processing using LLMLingua to save tokens. Trigger when the user pastes massive text blobs, asks to analyze a large file (logs, docs, transcripts), or provides a prompt too large for the context window.

not rated 5 4mo ago C tokens not measured original MIT

reliquery

510

the-essential/reliquery

Plugin Claude Code

Bundles 6 skills, 1 MCP server · 967 tokens together

AI memory and context management system for worldbuilding, co-writing, and roleplaying. Turns raw content into structured vault relics, indexes them into semantic memory, and maps entity relationships so Claude remembers your world between sessions.

not rated 5 3mo ago A tokens not measured original MIT

Jyo238/checkpoint

Plugin Claude Code

Lists 1 plugin

Persistent memory archival skill for AI coding assistants. Systematically captures breakthroughs, failed approaches, user preferences, and project context — so your AI never solves the same problem twice.

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

ideal-harness

515

bharat3645/The-Ideal-Harness

Plugin Claude Code

Bundles 10 skills, 4 agents, 3 hooks, 5 MCP servers · 606 tokens together

Control plane around a stateless model: guard (deny-wins policy), compress (cache-safe toolresult compression), memory (code-graph + episodic), orchestrate (task ledger + subagent flow), web (SSRF-guarded fetch + live package docs), core (loader/validation/skills).

not rated 5 2d ago A tokens not measured original MIT

auto-context

517

SkardiLabs/skardi-skills

Plugin Claude Code

Bundles 1 skill · 431 tokens together

Turn a folder of documents, a table you already have, or documents fetched out of a service (wiki, cloud docs, mail) into governed, searchable context an agent can query — hybrid search (vector + full-text) served by skardi-server over SQLite, Postgres+pgvector, MongoDB, or Lance. Three raw-material entries, one flow.

not rated 5 yesterday A tokens not measured

second-brain

519

mrelph/claude-agents-skills

Plugin Claude Code

Bundles 1 skill · 141 tokens together

Conducts an interview or ingests existing material, then runs the second-brain CLI to scaffold a personal knowledge base your AI assistant can maintain.

not rated 5 2mo ago A tokens not measured

get-my-context

521

sdi2200262/cc-get-my-context

Plugin Claude Code

Bundles 1 skill · 76 tokens together

A Claude Code skill that lets Claude check its own context window usage on demand. Reads the session transcript, computes used percentage with the same formula Claude Code uses internally, and injects the result into the skill content via dynamic context injection — no settings.json edits required.

not rated 5 4mo ago A tokens not measured original MIT

nyx

522

imdigitalashish/NYX

Plugin Claude Code

Bundles 1 skill · 120 tokens together

Token-saving context compression: renders bulky files/logs/reports as dense PNG images the agent reads instead of raw text. 45% fewer tokens on dense reports, 66-80% on source code. Lossy for exact identifiers. Best on gemini-3.1-pro-preview.

not rated 5 2mo ago A tokens not measured

note-tree

523

Tlkh201313/note-tree

Plugin Claude Code

Bundles 1 skill, 1 command, 3 hooks · 87 tokens together

Token-lean shared memory for coding agents. Saves only what matters and injects a ranked, hard-capped slice of it at session start — and every note is a leaf on a tree that grows with your project.

not rated 5 21d ago A tokens not measured original MIT

llm-wiki

524

hacnam0306/llm-wiki

Plugin Claude Code

Bundles 1 skill · 0 tokens together

Bootstrap or operate a Karpathy-style LLM-maintained personal knowledge base.

not rated 5 4mo ago A tokens not measured

dgclaw

525

DGatoM/DG-Claw

Plugin Claude Code

Bundles 3 skills, 3 hooks, 1 plugin · 231 tokens together

DG Claw — instala e gerencia um agente pessoal seu no Telegram, com nome, personalidade e memoria persistente. Dois modos: LOCAL (roda no seu proprio computador Windows/Mac, so com a assinatura Pro/Max, sem servidor e sem API key) e SERVIDOR (24/7 numa VPS Linux via systemd). O wizard /dgclaw:setup detecta o ambiente.

not rated 5 15d ago A tokens not measured original MIT

corivo

527

Principle-Labs/Corivo

Plugin Claude Code

Bundles 2 commands, 3 hooks · 21 tokens together

A plugin that gives a coding agent local memory storage and context retrieval through Corivo. Corivo is a tool for saving and finding information from previous conversations.

not rated 5 4mo ago 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: