StackMap
Subscribe

core vs openworker

Self-hosted, always-on "personal AI OS": watches your apps, keeps a persistent memory graph, and acts autonomously within guardrails — a product, not a library for building agents. — versus — Andrew Ng's local-first desktop AI coworker: give it an outcome and it works across your files, terminal and 25+ apps — Slack, Jira, Notion, Gmail — then hands back the finished deliverable.

The curated verdict

Same 'personal AI OS' ambition, different shape: Core watches your apps continuously and keeps a persistent memory graph, OpenWorker is task-shaped — you ask for a deliverable and approve each consequential step. Core for ambient autonomy, OpenWorker for finished output.

coreopenworker
Stars1.9k15k
Forks1872.1k
LanguageTypeScriptPython
LicenseNOASSERTIONMIT
Last activity5 days agoyesterday
Topicsagents, memoryagents
Curated connections94

core — the curator's take

Reach for CORE when you want an event-driven, self-hosted personal assistant that notices things on its own, remembers across sessions via a memory graph, and acts across your apps with per-action approval gates. NOT the pick if you want a framework to embed agents inside your own software (it's a product/OS, not a toolkit), nor if you need to run a multi-agent team/company with org charts and budgets — that's paperclip's lane.

openworker — the curator's take

Use it when you want an agent that produces artifacts rather than chat: it plans, works across your desktop and connected apps, and stops for approval before sending, writing or running anything. The agent loop, conversations, connector tokens and model keys all stay in the app's local store; bring your own key for 13-plus providers or point it at Ollama. Scheduled automations park their questions in an inbox instead of acting alone. Caveats: it's an open beta desktop app (macOS signed and notarized, Windows builds not yet code-signed), a small cloud service brokers connector OAuth unless you paste credentials by hand, and 'finished work' is only as good as the model you plug in.