Memory and context plugins

1,146 tagged Memory and context, measured the same way as everything else here.

Browse within: claude-code-plugin 208agent-memory 115ai-memory 94LLM 68mcp-server 62ai-tools 51cli 47knowledge-management 46agents 45context-engineering 44knowledge-base 43local-first 43knowledge-graph 41ai-coding 40

amber

673

yanfeid/claude-amber

Plugin Claude Code

Bundles 4 skills, 3 hooks · 244 tokens together

Zero-dependency context survival kit for Claude Code. Auto-checkpoints your session state to plain Markdown before compaction, restores it after — plus focus skills that keep Claude lean and on-task. No database, no background process, no AI compression. Just files you can read.

not rated 2 2mo ago A tokens not measured original MIT

aesth

674

zircote-plugins/aesth

Plugin Claude Code

Bundles 1 skill, 5 commands · 125 tokens together

Craft-focused design system management powered by Subcog memory. Build interfaces with elegance, consistency, and semantic memory.

not rated 2 2mo ago A tokens not measured

llm-language

675

Silence-view/llm-language

Plugin Claude Code

Bundles 4 skills, 5 hooks · 783 tokens together

Self-evolving prompt meta-compiler for the Fable 5 / Opus 4.8 era (Mythos-class aware) with xhigh/max effort, adaptive thinking, task budgets, dual-layer memory (ROSETTA.md + auto-memory), AND skill-level meta-refinement. v4.4: FABLE-5-ERA RETARGET — complexity map gains a model dimension (Opus 4.8 workhorse default…

not rated 2 2mo ago A tokens not measured original MIT

heptabase-linking

676

madeyexz/heptabase-skill

Plugin Claude Code

Bundles 2 skills · 235 tokens together

Skills for working with Heptabase via the CLI. Bundles a general CLI skill (notes, journals, tags, cards, whiteboards, AI Tutor) and a focused cross-linking skill that explains the ProseMirror card/date node schema and ships a helper script.

not rated 2 4mo ago A tokens not measured

turing

677

agenisea/turing

Plugin Claude Code

Bundles 2 commands, 2 hooks · 40 tokens together

Autonomous state machine for cognitive continuity. Preserves session state before context compaction and restores it on session start. Features priority-based selective restore, token budget tracking, auto decision extraction, and state archiving. Based on Alan Turing's 1936 paper 'On Computable Numbers'.

not rated 2 7mo ago A tokens not measured original MIT

continuity

678

vikcena01/ai-continuity-plugin

Plugin Claude Code

Bundles 1 skill, 3 commands, 2 hooks · 121 tokens together

Durable project state across AI sessions: decisions, constraints, and rejected paths, versioned in git as plain markdown. Not a memory tool — it answers what is true about the project now, and what must not change.

not rated 2 changed yesterday A tokens not measured original MIT

lore

679

docwilde/LORE

Plugin Claude Code

Bundles 1 skill, 16 commands, 4 hooks · 323 tokens together

Memory for Claude Code that reasons about you and improves itself: Honcho-pattern belief store with deriver, dreamer and dialectic (/lore:ask), automatic skillification with a closed judge/update/retire loop, on a Hermes-pattern core — hard-capped curated memory, FTS5 session search, staged review.

not rated 2 8d ago A tokens not measured AGPL-3.0

fragcap

680

fragcap/plugin

Plugin Claude Code

Bundles 9 skills, 1 hook · 245 tokens together

Most explorations die with the session. FragCap captures them as structured capsules — the problem, the dead ends, the open threads — and makes them searchable by anyone starting something similar. Your unfinished thinking becomes their shortcut.

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

c-brain

681

Yuno15-bb/c-brain

Plugin Claude Code

Bundles 3 skills, 8 agents, 5 hooks · 585 tokens together

A memory that grows. Your agent is brilliant within a session and amnesic between two — this gives it a persistent knowledge trunk on your machine: what you work out once is distilled into a note, filed, linked, and surfaced automatically next time, from any project. It makes no request of its own — no telemetry, no…

not rated 2 11d ago A tokens not measured original Apache-2.0

llm-wiki-init

683

vijay-athithyaa-GV/llm-wiki-init

Plugin Claude Code

Bundles 2 commands · 38 tokens together

Provides the /wiki-init and /wiki-status commands for scaffolding and inspecting a persistent, LLM-maintained knowledge base on any topic.

not rated 2 1mo ago A tokens not measured original MIT

second-brain

687

shofer-dev/claude-code-second-brain

Plugin Claude Code

Bundles 5 commands, 6 hooks · 214 tokens together

A cheap background model that watches your Claude Code session over its shoulder and, rarely, drops one short advisory into it — asynchronously, without ever blocking. It reads only the agent's emissions (29% of the transcript), never its tool results, so it is affordable to leave running for the whole session.

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

compact-manager

690

msshives-gif/claude-plugins

Plugin Claude Code

Bundles 5 commands, 5 hooks · 60 tokens together

Warns the main session as its own context fills, captures a wake packet before compaction, and reorients the session after it — so an autonomous orchestrator survives past one context window.

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

jambavan

691

beingmartinbmc/jambavan

Plugin Claude Code

Bundles 5 skills · 292 tokens together

Local-first codebase memory for coding agents: AST-aware context, durable decisions, failure records, review packs, and a local graph GUI. Twenty tools are advertised by default; writefile, patchfile, prompt compression, and bash are opt-in. Discipline protocols ship as MCP prompts rather than tools. Pre-2.0 tool nam.

not rated 2 3d ago A tokens not measured original MIT

hive-loop

692

Hivemind-OSS/Hivemind

Plugin Claude Code

Bundles 5 hooks

Closes the memory loop mechanically: recall before changing code, recall before storing, and a turn that cannot end with an unmade decision left silent. Requires Node >= 23.6 (the hooks run TypeScript directly).

not rated 2 1mo ago A tokens not measured original Apache-2.0

koshi

694

jsharma1105/Koshi

Plugin Claude Code

Bundles 5 agents · 340 tokens together

Koshi MCP — retrieval, context engineering, persistent memory, and quality scoring for AI agents. 100% offline.

not rated 2 15d ago A tokens not measured original MIT

universal-memory

695

goldenwo/universal-memory

Plugin Claude Code

Bundles 3 commands, 4 hooks · 44 tokens together

Cross-session, cross-device memory for Claude Code. Markdown-first captures, vector-backed recall. Points at any universal-memory server — local Docker, remote self-hosted, or cloud-backed. Auto-starts the server on demand when configured to.

not rated 2 changed yesterday A tokens not measured original MIT

turtle

696

contactandrewchl-wq/turtle-mcp

Plugin Claude Code

Bundles 26 skills · 1,660 tokens together

Memoria persistente y coordinación multi-agente para agentes de IA, eficiente en tokens.

not rated 2 2mo ago A tokens not measured original MIT