Workflows in 📝MythOS are repeatable agent processes written as memos — what starts one, which memos it must load, and the steps it runs — and they are an upcoming extension of 📝Augmentation, the identity layer your AI already carries into every session. Every agent run drags a payload of context nobody can see, so the same process costs a different amount each time it fires and no one can say afterwards which memos actually arrived; a workflow makes that payload a declared contract, classed by what guarantees each load and measured in tokens and characters before anything runs. It is built for 📝Oracle creators who run the same process often enough that its context and its cost are worth pinning down.
Key Capabilities
- The definition is a memo — no second record, so an agent amends a workflow through the same object it reads
- A declared load contract — every memo a run receives, classed as hook, gate, trigger, or search
- Weight before the run — tokens and characters per memo, per class, per workflow, and across a whole portfolio
- A canvas and a memo view — one definition read either as a step graph or as the document it actually is
- A portfolio dashboard — state, mechanism counts and context weight per workflow, filed into folders and pinned
- An execution engine behind a human gate — a run drafts with the declared model, suspends at the workflow's declared approval gate in the review queue, and releases only on a recorded decision
- A run record for every pass — status, per-step spend, duration, and where the output landed, rendered as History beside the portfolio
- Spend that rides your budget — every model call a run makes is metered into the same monthly caps and alerts as chat
Getting Started
Workflows is in build and not yet live on mythos.one. When it opens it will be an Oracle-tier surface reached from the Workflows tab; a workflow is created from a starting template and never fires the moment it exists, so a definition can be read and weighed before it is armed.
FAQ
- How is a workflow different from an ordinary memo? It is an ordinary memo. Marking a memo as a workflow is what puts it on the surface; the trigger, the load contract and the steps are sections in its body.
- What is a load contract? The set of memos a run receives, each classed by what guarantees it: a hook is injected every run, a gate must resolve or the run aborts, a trigger fires on a named condition, and a search retrieves at run time. Only hooks and gates are certain to be there.
- Why does one workflow report two weights? The first is what always lands before step one; the second is the ceiling, adding everything a conditional or retrieved load could add. An uncapped retrieval makes that ceiling unbounded rather than a number.
- Where does the weight come from? It is measured per memo version and cached rather than counted on render, so a portfolio can be sorted by context weight without the cheapest view becoming the most expensive one.
- Do workflows run themselves yet? The engine is built: a queued item becomes one run that drafts with the declared model, suspends at the declared approval gate, and dispatches on approval — leaving a run record either way. Nothing fires on mythos.one until the surface opens.
- What keeps a run from publishing on its own? A workflow that declares a hold gate cannot even compile without a step for that gate to suspend — enforcement is at build time, not by promise — and a suspended run waits in the same review queue as every other held draft until its owner decides.
Related
- 📝Implicit Loading — the sibling mechanism that guarantees your identity context loads before an agent acts
- 📝Semantic Search — the retrieval behind a search-class entry in a load contract