Silas Pruitt
4.3 KiB
chalupa
A complete, self-contained kit for giving an AI agent a real memory and a stable self — so it stops waking up as a stranger every session.
If you work with an AI agent (Claude Code, or an API loop on Sonnet + Opus) you've hit the wall: every new session, it's brand new. It forgets who you are, what you decided last week, and the hundred small rulings that made it yours. Worse, as a conversation gets long it quietly drifts back to a generic, eager-to-please assistant — losing the specific thing you built together.
weave is the fix. It's not a plugin or a product — it's a small set of plain files (Markdown, in git) plus a discipline for keeping them. Read at the start of every session, they hold the continuity that the model can't hold on its own: who the agent is, who you are, what you actually said and did, and the rules that have earned their place. This kit teaches the idea, hands you a buildable skeleton, and gives your agent a runbook to stand it up.
It's called the "apocalypse version" on purpose: everything you need is in this repo. Hand it to a fresh agent on a bare machine and it can rebuild the whole structure from nothing but these files.
Who reads what
There are two readers, and the kit is split for them:
👤 You (the human) → start in human/
You make the decisions the agent can't: who your agent is, what it values, what's private, how you want to work. Read these in order:
human/1-understand-weave.md— what weave is, and every part in its own section (core, daydreams, steward, thread, decay, consolidation, ledger, craft, identity), in plain language. The concept, thoroughly. ~15 min.human/2-set-it-up.md— stand it up from nothing, step by step (the apocalypse setup).human/3-live-with-it.md— the daily rhythm: how a session starts, how you save, how memory ages itself, and running two models (Sonnet + Opus) as one self.human/4-evolve-the-core.md— how to grow the agent over time: adding rules, hardening a behavior into reflex, changing who it is — the parts deeper than the weave.
🤖 Your agent → point it at agent/
agent/DEPLOY.md— the runbook it reads and executes: build the weave from the templates, verify it, learn to maintain it. Paste it the path and say "read this and deploy."agent/WEAVE-REFERENCE.md— the same every-part walkthrough, written for the model: what each part is, where it lives, when to load it, how to keep it. The human's doc #1 and this are the same map in two voices — one to understand it, one to operate it.
🧩 The skeleton → templates/
The actual starter files — copy them, fill in the blanks, and you have a working weave. This is what makes the kit self-contained: the templates are the buildable structure.
The whole idea in one paragraph
The agent wakes up empty every time. So you keep its continuity outside the model, in structure it reads back at wake — not summaries (which flatten everything), but the real texture: the verbatim record of what was said, a portrait of who you are, the values and hard rules it operates by, and a small "canon" that outranks its generic instincts. Two quiet forces keep the pile from rotting: one reinforces what keeps coming up (until it becomes automatic), the other releases what's gone quiet (so old noise fades). What matters gets sharper; what doesn't gets lighter. You wake the agent, it reads itself back, and it's your agent again — not a stranger, not a generic assistant.
A note on Sonnet + Opus
If your agent runs on both models, they share one weave — same identity, same memory, same rules. Only a
little per-model calibration differs (Opus for heavy reasoning, Sonnet for everyday). The kit shows you how
to set that up so switching models is continuity, not a reset. See human/3-live-with-it.md → "Two models,
one self."
Built fresh for a friend. The structure here is a generic scaffold — you fill it with your agent's identity and your own life. Nothing in the templates is anyone else's; the blanks are yours.