How SayeOS Core works: getting started, the core concepts, the agnostic architecture, building with Skills and Python, and the governance behind it.
Getting started
A free, governed workspace for persistent intelligent work. Core is model, system, and connection agnostic, and public distribution is coming soon.
Core is not yet publicly distributed. Join the preview from the homepage for release updates and early access.
As of July 2026, supported environment details are being finalized. Preview members receive environment updates first.
Connect the model or token provider you prefer. You connect and pay your provider separately where applicable.
Work in Core happens in persistent workstreams that carry intent, context, state, evidence, decisions, and history.
Core concepts
A persistent unit of work that continues across sessions and contributors, holding everything the work depends on.
The human originated purpose that authorizes work. Intent is declared, not inferred.
What matters for this work: the understanding the workstream carries.
What is currently true in the work right now.
What supports a conclusion or action, sufficient to reconstruct it later.
The point where a human checks work before it counts. Worker output is draft until reviewed.
Bounded, executable capabilities with defined inputs, allowed tools, permitted actions, and review.
How understanding persists and evolves over time while keeping source, context, confidence, and sharing boundaries. See the Continuum page.
Architecture
SayeOS coordinates work around existing systems of record rather than replacing them. Those systems keep their authority.
Different models contribute by task, cost, capability, privacy, environment, and policy. Changing providers does not restart the work.
Connections include APIs, local tools, files, databases, approved services, Edge mediated access, and defined interfaces. No one method is universal.
Python is a first class execution layer. Python workers run defined analysis inside the workstream, bounded by security, dependencies, and permissions.
Operational systems remain the authoritative source for their own data. SayeOS references them rather than absorbing them.
People, models, Python workers, APIs, software services, and reviewers can all contribute to one workstream.
Build
Models reason. Python executes. Skills and Context Packs make capability reusable. See the Build page.
Define inputs, required context, allowed tools, permissions, validation, and review, then test, package, and publish.
Package governed knowledge with known provenance and scope for reuse.
Use appropriate libraries for the domain. Execution is bounded, not unrestricted.
Bundle a capability with its metadata: version, permissions, dependencies, and limitations.
Define the checks a Skill must pass before its output is trusted.
Governance
SayeOS runs under a public Constitution. Read the governing text.
Consequential work should run under rules you can read. The Constitution is public and versioned.
Human authority stays primary. Intelligence may analyze, simulate, and propose, but may not decide or approve.
A person can delegate scoped authority in advance. Systems execute inside that scope while it is valid and not revoked.
When an instruction is ambiguous or would require guessing intent, halting and escalating is the correct behavior.
Escalations surface to a human authority who can resolve them. They are not resolved by retries or heuristics.