Memory and context plugins

Laotree/logs-locally-plugin

Plugin Claude Code

Bundles 1 skill, 1 hook · 14 tokens together

Store and browse AI agent session logs locally with a SQLite database and web UI.

ankitkr3/compounded

Plugin Claude Code

Bundles 5 skills, 9 commands, 1 agent, 3 hooks · 759 tokens together

Turns your agent into a trainable employee. Learns rules from your corrections (with your approval), and skills earn autonomy through demonstrated reliability — proposed → verified → trusted → autonomous. No daemon. No cloud.

soolaugust/vMem

Plugin Claude Code

Bundles 7 hooks

Kernel-grade persistent memory for Claude Code. Remembers decisions, constraints, and context across sessions — designed like an OS memory subsystem, not a database.

Zenetusken/consolidate-memory

Plugin Claude Code

Bundles 1 skill, 3 commands, 1 hook · 268 tokens together

Cross-project, verification-first memory for Claude Code — the layer beyond the built-in Auto Dream. Shares memory across enrolled projects in the same trust domain (a governed store, replicated into those projects) and verifies facts against the live code (grep/file/git), dropping what it can't confirm — fact-checked.

gideondk/strata

Plugin Claude Code

Bundles 24 skills, 2 agents, 5 hooks, 1 MCP server · 2,621 tokens together

Typed, local-first memory for Claude Code — decisions, domain rules, and runbooks Claude reads on its own. Human-confirmed writes, read-only MCP, benchmarked supersession-aware recall. Branch/PR-aware and team-shareable.

TC407-api/Titan-Memory

Plugin Claude Code

Bundles 2 skills, 1 MCP server · 27 tokens together

5-layer cognitive memory for Claude Code — surprise filtering, semantic highlighting, Cortex classification, adaptive decay, cross-project learning. 30 MCP tools. 90.7% benchmark accuracy.

victor-hac-work/loop-engineering-skills

Plugin Claude Code

Bundles 1 skill · 95 tokens together

Design production-grade, memory-backed agent loops. Classify deterministic vs non-deterministic, scan your harness (skills/agents/MCP/hooks), derive durable state from the goal, separate done-gates from guardrails, and emit a /loop-ready prompt behind a human approval gate.

zimalabs/code-decisions

Plugin Claude Code

Bundles 1 skill, 5 hooks · 23 tokens together

Gives your codebase a memory for why. Captures decisions automatically, surfaces them when you edit affected files.

Cfvillarroel/carryover

Plugin Claude Code

Bundles 1 skill, 13 commands, 4 hooks · 184 tokens together

Carry your context across AI coding tools. Adds /carryover and /headroom commands plus a save-to-memory prompt at the end of each session, backed by the headroom proxy.

codeprakhar25/smartcompact

Plugin Claude Code

Bundles 1 command, 1 hook · 17 tokens together

Human-in-the-loop context compaction for Claude Code. You choose which turns survive; a SessionStart hook re-injects them deterministically after every compact and resume.

tigerquoll/claude-brief

Plugin Claude Code

Bundles 1 command, 4 hooks · 14 tokens together

A live, auto-refreshing per-session summary brief docked beside your Claude Code terminal — to quickly get up to speed when switching between parallel sessions.

asarnaout/lean-context

Plugin Claude Code

Bundles 1 skill · 49 tokens together

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

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.

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.

cyrus-cai/claude-cobrain

Plugin Claude Code

Bundles 7 skills, 1 command, 1 hook · 107 tokens together

Screen activity memory daemon - captures active windows and summarizes them using local VLM.

NeoZhouCHN/github-stars-radar

Plugin Claude Code

Bundles 1 skill, 1 MCP server · 29 tokens together

Local-first GitHub stars memory MCP server and skill bundle for Claude Code.

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.

MohmmedAshraf/symbiote

Plugin Claude Code

Bundles 3 agents, 9 hooks, 1 MCP server · 71 tokens together

AI coding companion with persistent memory — code knowledge graph, developer DNA, and architectural intelligence via MCP.

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.

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).

primeline-ai/claude-code-starter-system

Plugin Claude Code

Bundles 1 skill, 4 commands · 73 tokens together

A complete session management system for Claude Code. Memory persistence, session handoffs, context awareness, and delegation basics - extracted from a 650-node production AI system.

Primadetaautomation/primadata-marketplace

Plugin Claude Code

Plugin marketplace listing 13 plugins: claude-dev-toolkit, superpowers, superpowers-chrome, elements-of-style, episodic-memory.

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.

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.