OfficeSpeak turns a plain-English description into a small, always-on team of software workers — an office — that passes messages, keeps state, and reacts to the world. No programming needed to try it. Runs on the DisSysLab engine.
See examples of different types of offices.
A sample of what's in DisSysLab's gallery —
see FEATURES.md for the full, categorized list.
News, markets, and social monitoring — competitor watch, stock and weather monitors, an arXiv radar, inbox triage, situation-room briefings, a Kalshi market watcher.
Everyday assistants — a wardrobe assistant that checks your calendar and the weather, a job hunter that filters postings and runs parallel analysts, a lead qualifier, a ticket router.
Beyond text — backyard bird-song identification from audio, wildlife camera-trap image classification, a loudness monitor for a simple sense-detect-respond example.
Validation fixtures and demos — a three-agent debate panel that reaches consensus, an investment-club office (analysts, manager, accountant), an office made of two other offices.
The properties every generated office has.
Detects termination in networks that may have feedback loops.
Periodic global-snapshots — dsl run --snapshot-interval N.
dsl explain-trace merges every agent's activity log,
ordered by a physical-time based logical clock, into one causal
story — narrated by Claude, not a template.
dsl show-checkpoint — what every worker's memory held,
and what messages were still in transit, at one instant.
Test one computational worker alone on hand-picked inputs to localize a bug — no concurrency in the picture.
No installation, no Python, no terminal. A conversation with Claude on claude.ai builds your office, explains it back — including what it assumed — and lets you correct it in plain English.
▶ Watch the 2-minute tourTurns your description into a running system. Needs Python.
▶ Watch the 2-minute tour