Vibe Code Catalog Commands SOPs Market Radar GitHub

v0.1.0unverified

Claw Starter — one model, one memory, one schedule, one chat surface

The layer above agents is the claw: persistent, scheduled, memory-bearing

(Willison's and Karpathy's term — Karpathy's runs his house). OpenClaw has

250k stars and NVIDIA now ships a governance stack for it; this kit is the

opinionated 4-file starter that works on **Claude Code, Hermes Agent, and

OpenClaw** — same SKILL.md standard everywhere.

Quick start

Preview (free): skills/claw-init/ is included — copy into

.claude/skills/ (or ~/.hermes/skills/), run /claw-init, answer the

interview, get your claw's config + memory scaffold.

Full kit ($39): heartbeat skill, SOUL.md persona template, memory

conventions, per-harness install notes (incl. NemoClaw/OpenShell sandboxing).

What you get

FileJobIn preview?
skills/claw-init/SKILL.mdinterview → writes CLAW.md (duties, boundaries, schedule) + MEMORY.md scaffold✅ free
skills/heartbeat/SKILL.mdthe scheduled run: read memory → standing duties → write memory → one-line reportpaid
SOUL.md templatestable persona/identity file (Hermes-native; works as CLAUDE.md section elsewhere)paid
MEMORY-CONVENTIONS.mdwhat a claw remembers vs forgets; append-only logs vs living statepaid
HARNESSES.mdinstall + safety notes: Claude Code routines, Hermes tiers, OpenClaw/NemoClaw sandboxpaid

The four decisions a claw is

Duties (what runs every heartbeat) · boundaries (what it never does

unattended) · memory (what survives between runs, in files not chat) ·

schedule (when it wakes). /claw-init makes you decide all four before

anything runs. Window-surfer's /goal is the natural work engine inside a

heartbeat.

Proof

Unbenchmarked — v0, not yet for sale. First benchmark: 7 days of scheduled

heartbeats, measuring duties completed and memory-file usefulness on resume.

Changelog

Get new packs + re-verification alerts

One email when a pack ships or gets re-benchmarked on a new model. No noise.