SaSameKnowledge
Search knowledge⌘KStart with SaSame
publisheddocumentationdocumentation

Where should I start with SaSame?

Operational and technical documentation for Factory entry, architecture, monitoring, verification, observation, deployment and reference.

Collection
documentation
Updated
2026-07-30
min read
2
Version
v1
Verified summary

Start with Getting Started, then follow Architecture, Factory, Monitoring, Owner Verification, Observatory, Deployment, Reference and API.

00

In this collection

14
01
Connect an AI ClientChoose the guide for ChatGPT, Claude, Claude Code or another Streamable HTTP MCP client, add the public SaSame endpoint, then verify the connection by calling start_here.
02
Agent Execution RouterCall resolve_and_run on the same public MCP endpoint with a goal, environment and constraints; it returns a bounded route and an honest execution state — only "verified" means something actually ran.
03
ArchitectureOne canonical Knowledge Database feeds the website, search, API, MCP, Markdown projections and future PDF outputs through versioned adapters.
04
DeploymentDeployments bind an immutable source SHA to a component release, health checks, external verification and a rollback target before traffic changes.
05
FactoryThe Factory connects entry, blueprint, build, inspection, shipment, observation, repair and reverification through one evidence-backed lifecycle.
06
Getting StartedIdentify your MCP state, select the matching Factory entry point, then collect a reproducible baseline before changing anything.
07
Guided BuildThe creator's own LLM does the building from fixed instructions SaSame serves; SaSame runs zero LLM calls and deterministically verifies the artifacts the creator submits back — string/regex/length checks, never a fuzzy AI judgment.
08
Knowledge Publishing WorkflowDocuments enter through reviewed CMS edits, provider-neutral AI drafts or controlled migrations, then pass validation, CAS versioning, Markdown projection and receipt generation before public release.
09
mcp-readiness CLImcp-readiness is SaSame’s open-source command-line tool: run it with npx against any public MCP endpoint to get the same bounded readiness grade the Observatory publishes, with no account or key required.
10
MonitoringMonitoring records time-bounded reachability, protocol behavior, declared capabilities and selected compatibility checks with provenance and history.
11
ObservatoryThe Knowledge Platform is the canonical human interface for the Observatory Factory station, while live-vps preserves signed JSON, feeds, badges, certificates, lookup and longitudinal evidence URLs.
12
Owner VerificationOwner verification proves control of a defined MCP identity or related resource through a bounded control-proof method at a stated time.
13
ReferenceReference pages expose versioned schemas, status enums, API contracts, evidence boundaries and release receipt fields used across human and machine interfaces.
14
Repair and ReverificationObservation detects drift and produces a scoped Repair Blueprint with hypotheses, not confirmed causes; the creator always applies the actual fix; SaSame never edits creator code; a successful fix is reverified under the same test contract and automatically reshipped.
01

Start with state

Identify whether the MCP begins as an idea, repository, finished build, live endpoint, underperforming endpoint or monitored portfolio, then see Getting started to connect.

02

Follow the lifecycle

Getting started and Architecture lead to Factory, Guided Build, Monitoring, Repair and reverification, Owner Verification, Observatory, Deployment and Reference.

03

Keep evidence bounded

Every operational claim should state identity, method, time, provenance, limitation and the relationship to later versions.

EX

Examples

2
  1. 01

    A live endpoint begins with observation and identity resolution before a repair or commercial recommendation is proposed.

  2. 02

    An idea-stage MCP and a live, underperforming MCP both start at Getting Started, but branch immediately afterward — one toward Guided Build, the other toward Monitoring and Repair.

RF

References

1
NX

Continue exploring

14
documentation01

Getting Started

Identify your MCP state, select the matching Factory entry point, then collect a reproducible baseline before changing anything.

documentation02

Architecture

One canonical Knowledge Database feeds the website, search, API, MCP, Markdown projections and future PDF outputs through versioned adapters.

documentation03

Factory

The Factory connects entry, blueprint, build, inspection, shipment, observation, repair and reverification through one evidence-backed lifecycle.

documentation04

Guided Build

The creator's own LLM does the building from fixed instructions SaSame serves; SaSame runs zero LLM calls and deterministically verifies the artifacts the creator submits back — string/regex/length checks, never a fuzzy AI judgment.

documentation05

Monitoring

Monitoring records time-bounded reachability, protocol behavior, declared capabilities and selected compatibility checks with provenance and history.

documentation06

Repair and Reverification

Observation detects drift and produces a scoped Repair Blueprint with hypotheses, not confirmed causes; the creator always applies the actual fix; SaSame never edits creator code; a successful fix is reverified under the same test contract and automatically reshipped.

documentation07

Owner Verification

Owner verification proves control of a defined MCP identity or related resource through a bounded control-proof method at a stated time.

documentation08

Observatory

The Knowledge Platform is the canonical human interface for the Observatory Factory station, while live-vps preserves signed JSON, feeds, badges, certificates, lookup and longitudinal evidence URLs.

documentation09

Deployment

Deployments bind an immutable source SHA to a component release, health checks, external verification and a rollback target before traffic changes.

documentation10

Reference

Reference pages expose versioned schemas, status enums, API contracts, evidence boundaries and release receipt fields used across human and machine interfaces.

api11

API

Use the read-only Knowledge API, search endpoint or MCP retrieval tools, all backed by the same document and relation model.

learning12

Learning

Use progressive tracks: beginner concepts, intermediate operations, advanced evidence and expert lifecycle architecture.

documentation13

Agent Execution Router

Call resolve_and_run on the same public MCP endpoint with a goal, environment and constraints; it returns a bounded route and an honest execution state — only "verified" means something actually ran.

documentation14

mcp-readiness CLI

mcp-readiness is SaSame’s open-source command-line tool: run it with npx against any public MCP endpoint to get the same bounded readiness grade the Observatory publishes, with no account or key required.