By alivecontext
Manage personal context across Claude Code sessions by organizing projects into structured workspaces (walnuts), capturing external content, checkpointing work, and rebuilding context from logs and transcripts.
Create new skills, rules, and hooks for your world. Checks plugin compatibility, writes to the human's space (not plugin cache), validates against the system, and suggests when repeated work should become a skill. For marketplace-ready plugins, hands off to the contributor plugin.
Create, share, and graduate bundles โ the unit of focused work within a walnut. Manages the full bundle lifecycle from creation through sharing to graduation.
Use when external content arrives in the session โ emails, transcripts, screenshots, documents, files, or in-session research worth keeping. Also use when there's nothing obvious to capture โ the skill checks 03_Inbox/ for unrouted files and enters inbox scan mode. Stores raw content, routes to bundles, extracts tasks and insights into the stash.
Something new is emerging. A venture, an experiment, a person entering the orbit, a life area getting serious. It needs its own walnut โ its own identity, history, and future. Scaffolds the full structure, maps existing context sources, and optionally migrates files across.
The human mentions a walnut to work on, asks about a specific venture/experiment/project, or wants to check status โ not just explicit 'load X'. Load the brief pack (3 files), resolve the people involved, check the active bundle โ then surface one observation and ask what to work on. Context loads in tiers: walnut and people are automatic, bundle depth is offered.
Modifies files
Hook triggers on file write and edit operations
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
โโโโโโ โโโ โโโโโโ โโโโโโโโโโโ
โโโโโโโโ โโโ โโโโโโ โโโโโโโโโโโ
โโโโโโโโ โโโ โโโโโโ โโโโโโโโโ
โโโโโโโโ โโโ โโโโโโโ โโโโโโโโโโ
โโโ โโโ โโโโโโโโโโโ โโโโโโโ โโโโโโโโ
โโโ โโโ โโโโโโโโโโโ โโโโโ โโโโโโโโ
The agent is replaceable. The runtime is portable. The walnut is permanent.
claude plugin install alive@alivecontext
Or from the Claude Code UI: /plugins โ add marketplace alivecontext/alive โ install alive

Open Claude Code at your ~/world. The runtime is already loaded.
ALIVE structures your context into plain files on your machine. Agents read them at session start and save what matters at session end. Everything in between โ the decisions, the research, the people, the knowledge โ gets structure instead of dying with the session.
Orient. Before you say a word, the runtime has already oriented the agent โ a lightweight index of your world, your preferences, and the behavioural rules that make the agent yours. When you load a walnut โ a venture, an experiment, a person, a life area โ three files give the agent its identity, current state, and standing knowledge. No re-explaining. No pasting context. The agent knows what you're building, who's involved, and what happened last time.
Work. Every AI session is a context event. You're injecting context โ files, transcripts, research, screenshots. You're generating context โ decisions, architecture choices, domain knowledge. You're discovering context โ connections between people, patterns across projects, insights that only surface mid-conversation. Right now, all of that is ephemeral. It dies when the window closes. ALIVE catches it as it happens.
โญโ ๐ฟ๏ธ +4 stash (8)
โ Decided: React Native for mobile app โ my-startup
โ Task: Chase Jake for API specs by Friday โ my-startup
โ Note: Jake prefers async comms, hates standups โ [[jake-chen]]
โ Action: Connected ElevenLabs API for voiceover โ my-startup
โ โ drop?
โฐโ
Decisions route to the log. Tasks route to the queue. People updates route to their person walnut. Actions get tracked. Nothing gets lost.
Save. When you checkpoint, everything routes to where it belongs โ decisions to the log, tasks to the queue, knowledge to insights, people updates to their own files. External content gets captured into bundles. Scripts compute a fresh snapshot. The ephemeral becomes structural.
Compound. Next session inherits everything the last one produced. And the one before that. Context accumulates. Sessions build on each other instead of starting from zero.
Each meaningful thing in your life gets a walnut โ your startup, your people, your health, your side project.
A walnut has a kernel โ three source files that move at different speeds:
my-startup/
_kernel/
key.md โ What it is (identity, people, links โ rarely changes)
log.md โ Where it's been (prepend-only, signed decisions)
insights.md โ What it knows (evergreen domain knowledge)
tasks.json โ What needs doing (script-operated)
now.json โ Current state (generated on save, never hand-written)
The agent writes to source files. Scripts compute the projection. Judgment and aggregation stay separate.
Work gets done inside bundles. Each bundle has a goal and owns its own tasks.
# context.manifest.yaml
goal: "Ship the website from strategy deck to production"
status: prototype # draft | prototype | published | done
Two species: outcome bundles ship a deliverable and graduate. Evergreen bundles accumulate context over time โ meeting notes, research, reference material.
Bundles are shareable โ your workflow becomes a context product anyone can install.
The squirrel is the agent runtime โ rules, hooks, skills, and policies that any AI agent inhabits when working inside your world. Why squirrel? ๐ฟ๏ธ Squirrels scatter-hoard โ bury context now, retrieve by value later. That's the mechanic.
npx claudepluginhub alivecontext/alive --plugin alivePersistent context for AI coding assistants
Persistent memory system for Claude Code with enforced context
Multi-project context management: switch projects, save/load sessions. Designed for non-CLI interfaces (Cowork desktop, Telegram).
Extended Second Brain that learns as you work in Claude Code
Save and resume Claude Code session context across multiple windows. Preserves work progress, pending tasks, key files, and technical notes. Perfect for complex projects requiring context switching between sessions.
Personal AI Infrastructure โ persistent memory, session continuity, and knowledge graph for Claude Code