context-management plugins

kevin-hs-sohn/hipocampus

Plugin Claude Code

Bundles 5 skills, 3 hooks · 215 tokens together

Persistent agent memory that survives across sessions — auto-compacting 3-tier memory with hybrid search. Your agent remembers what it learned, decided, and built.

davegoldblatt/total-recall

Plugin Claude Code

Bundles 10 skills, 10 commands, 2 hooks · 148 tokens together

Curated persistent memory for Claude Code. Write gate prevents bloat — only behavior-changing facts get saved. Tiered architecture: daily logs, structured registers, and auto-loaded working memory.

joseairosa/recall

Plugin Claude Code

Bundles 7 commands, 3 agents, 6 hooks · 142 tokens together

Recall Memory-as-a-Service — persistent memory, semantic search, and context management across Claude Code sessions. Connects to recallmcp.com or self-hosted instances.

Ethan-YS/project-brain

Plugin Claude Code

Bundles 1 skill · 318 tokens together

Folder structure + collaboration protocol so AI sessions can resume project context after compaction or window switch. One brain/ folder, 5 core files (PROJECT/MAP/STATUS/DECISIONS/HANDOFF), and a topic taxonomy.

Patdolitse/piia-engram

Plugin Claude Code

Bundles 1 skill, 1 MCP server · 175 tokens together

Local-first personal AI identity layer for MCP-compatible coding tools. Stores your lessons, decisions, playbooks, and project context as local JSON. AI proposes; high-risk items wait for your review, and everything stays visible and reversible. Local-first, no cloud, no account.

alivecontext/alive

Plugin Claude Code

Bundles 17 skills, 5 hooks · 1,077 tokens together

Local, user-owned context for Claude Code. Keep your work in files you control.

egorfedorov/claude-context-optimizer

Plugin Claude Code

Bundles 27 skills, 3 agents, 6 hooks · 1,005 tokens together

Spend less of your Claude usage on re-reading. In chat: a fresh-start handoff, token checks and prompt sharpening. In Claude Code and Cowork: Haiku 5.5 subagents do the reading and test runs so the expensive model's context stays small, plus read dedup, budget and cache-break warnings, and /cco-audit of your own…

simpx/loopat

Plugin Claude Code

Bundles 1 skill · 133 tokens together

Built-in loopat platform skills (promote, help).

Rylaa/fable5-opus5-orchestrator

Plugin Claude Code

Bundles 1 skill, 4 hooks · 53 tokens together

Token-frugal multi-agent orchestration for Claude Code, built for a Claude Fable 5 chair: Fable plans and decides, Sonnet 5 carries the volume, Opus 5 takes the hard slices and escalations, each worker's effort sized by the chair. Delegation is the DEFAULT, not the escalation — and a solo guard watches the chair…

svy04/ballast

Plugin Claude Code

Bundles 16 skills, 4 hooks · 877 tokens together

Builds up to a goal in a field you have no expertise in: splits it into the foundations that goal actually needs, mobilizes what you already hold, learns what is missing, and leaves every solved path behind for the next goal. Nothing is called done until a check passes.

oldskultxo/aictx

Plugin Claude Code

Bundles 1 skill · 48 tokens together

Use AICTX repo-local operational continuity in Claude Code.

primeline-ai/evolving-lite

Plugin Claude Code

Bundles 2 skills, 16 commands, 6 hooks · 256 tokens together

Self-evolving Claude Code system that learns from corrections, manages context, and improves every session.

paceaitian/paceflow

Plugin Claude Code

Bundles 4 skills, 5 commands, 1 agent, 12 hooks · 310 tokens together

PACE workflow enforcement system — Plan-Artifact-Check-Execute-Verify-Review protocol with hooks.

awrshift/agent-memory-kit

Plugin Claude Code

Bundles 10 skills, 4 agents, 4 hooks · 1,943 tokens together

Persistent memory for your agent as plain files in your folder: a hot cache injected every session and held under three size caps, per-session handoffs, and promotion into knowledge articles and rules only on your yes. Carries the builder's layers too — executor/recon/idea-validator agents, session review, second…

jmcentire/kindex

Plugin Claude Code

Bundles 3 skills, 4 hooks, 1 MCP server · 111 tokens together

The memory layer Claude Code doesn't have. A persistent knowledge graph that learns from your conversations — your AI assistant never starts a session blind.

fomyio/claude-context-monitor

Plugin Claude Code

Bundles 5 hooks

Real-time context window tracking, semantic relevance evaluation, proactive compact suggestions, and smart compact instructions that carry forward memory across compactions for Claude Code.

tim-mccrimmon/structured-context-spec

Plugin Claude Code

Bundles 7 skills · 208 tokens together

Structured Context for Teams - Initialize, build, validate, and version structured context from your PRDs, architecture docs, and compliance requirements. Compiles to Claude Code rules automatically.

GodsBoy/lossless-code

Plugin Claude Code

Bundles 1 skill, 7 hooks, 1 MCP server · 23 tokens together

DAG-based lossless context management for Claude Code. Every message from every session is persisted in a SQLite vault with FTS5 search. Summaries form a directed acyclic graph - nothing is ever lost.

AnamKwon/agent-skill-router

Plugin Claude Code

Bundles 5 skills, 1 command, 1 hook · 161 tokens together

Skill routing plugin that exposes category routers, keeps leaf skills in a hidden library, and organizes new skills through agent-authored routing plans.

iampantherr/SecureContext

Plugin Claude Code

Bundles 27 skills · 808 tokens together

Secure memory + persistent context + skill-admission gate for Claude Code. HMAC-chained toolcalls + outcomes, per-agent HKDF subkey isolation, Postgres RLS, work-stealing task queue, MemGPT-style persistent memory, Agent Notebook Model (Read→Summary redirect), and v0.26.0+ Anthropic-style filesystem skills with AST.

boksajang/vibebox

Plugin Claude Code

Bundles 1 skill, 2 hooks · 62 tokens together

Local-first structured memory middleware for Claude Code and other AI coding agents.

Zenetusken/consolidate-memory

Plugin Claude Code

Bundles 1 skill, 8 commands, 1 hook · 424 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.

sh008/claude-lore

Plugin Claude Code

Bundles 1 skill · 155 tokens together

Persistent project knowledge base for Claude Code. Records current state, phased roadmap, decisions and their rejected alternatives, and failed approaches — so a new session resumes from what was recorded instead of re-reading the whole codebase.

cukas/remembrall

Plugin Claude Code

Bundles 6 skills, 12 commands, 4 hooks · 388 tokens together

Context-aware session continuity for Claude Code — Pensieve session memory, Time-Turner parallel agents, Marauder's Map visualization, autonomous overnight runs, git patch snapshots, team handoffs, smart replay, and auto-resume.