# Synedrix OS documentation > The governed operating layer for agentic business systems. Synedrix OS is a reusable multi-agent operating system that enables specialized agents to… Every page of the public documentation at https://docs.synedrix.io/, grouped as in the site navigation. The full text of all pages, in the same order, is at https://docs.synedrix.io/llms-full.txt. ## Overview - [Synedrix OS documentation](https://docs.synedrix.io/): The governed operating layer for agentic business systems. Synedrix OS is a reusable multi-agent operating system that enables specialized agents to… - [Documentation README](https://docs.synedrix.io/docs-readme/): Synedrix OS is a reusable multi-agent operating system that enables specialized agents to coordinate across workflows, tools, and data while preserving human… ## Reference - [Canonical Facts](https://docs.synedrix.io/canonical-facts/): This section is a compact reference for the names, numbers and identifiers used throughout the documentation: the agents, the principles, the layers and the… - [Agent registry](https://docs.synedrix.io/agent-registry/): Synedrix OS owns and ships 12 agents across three families. Cite by name and identifier, for example "Audit & Lineage Agent (os-agt-008)". - [Layer taxonomy](https://docs.synedrix.io/architecture/): Synedrix OS has a 12-layer architecture. The layers stacked in their slices: Which platform in the tech stack implements each layer. - [Deployment modes](https://docs.synedrix.io/deployment-modes/): Three canonical deployment modes are governed by Principle 11 (Open by default, sovereign by design). - [Core principles](https://docs.synedrix.io/principles/): Synedrix OS is guided by 12 core principles. Numbering is canonical and fixed. Cite by name and number, for example "Principle 4 (Governance before execution)". ## Layers - [Layer reference](https://docs.synedrix.io/layers/): One page per canonical layer in the Synedrix OS architecture: what it owns, what it must not own, who it interfaces with, and how Synedrix OS implements it… - [Agent Registry](https://docs.synedrix.io/layer-agent-registry/): The Agent Registry Layer defines discoverable capabilities and boundaries. It is the shared discovery, versioning, and lifecycle surface for every agent… - [Agent Runtime](https://docs.synedrix.io/agent-runtime/): The Agent Runtime Layer executes agents with bounded scope and lifecycle management. It owns agent lifecycle, invocation context, execution state, and… - [Business Instance](https://docs.synedrix.io/business-instance/): The Business Instance Layer configures a concrete runtime. Everything above it — the OS layers and whichever domain packs are selected — is a reusable… - [Domain Pack](https://docs.synedrix.io/domain-pack/): The Domain Pack Layer is where Synedrix OS stops being domain-agnostic. Everything below it — orchestration, agent runtime, registry, tools, memory, events… - [Event](https://docs.synedrix.io/event/): Event standardizes how a fact enters, travels through, and leaves Synedrix OS. Signals, approvals, state changes, failures, anomalies and callbacks all… - [Goal & Intent](https://docs.synedrix.io/goal-intent/): Goal & Intent is the layer where a business objective becomes something the rest of the system can act on: a structured goal schema, an objective definition… - [Governance & Controls](https://docs.synedrix.io/governance-controls/): Governance & Controls enforces policy, permissions, approvals, and compliance. It is the layer that decides whether a proposed action is allowed to happen… - [Human Interface](https://docs.synedrix.io/human-interface/): Human Interface is the layer where a person meets the system: it captures human intent, carries approval requests to a reviewer and back, and gives operators… - [Memory & Data](https://docs.synedrix.io/memory-data/): Memory & Data persists business state and contextual knowledge, and — per ADR-OS-002 — also owns the memory control plane: the governed process by which a… - [Observability](https://docs.synedrix.io/layer-observability/): Observability makes execution measurable, explainable, and reviewable. It is the layer that answers what happened, how well did it perform, and can it be… - [Orchestration](https://docs.synedrix.io/orchestration/): The Orchestration Layer routes work, decomposes goals, sequences tasks, and manages retries and approvals. - [Tool Abstraction](https://docs.synedrix.io/tool-abstraction/): Tool Abstraction normalizes how an agent reaches an external system. Every capability an agent may invoke — a database read, a write to canonical state, a… ## OS specifications - [OS Specifications](https://docs.synedrix.io/os-specifications/): The normative Synedrix OS specifications: the consolidated canonical master, core principles, taxonomy, tech stack, workflow contract, event taxonomy, and the… - [Consolidated Canonical Reference](https://docs.synedrix.io/canonical-master/): Provide one coherent, end-to-end view of Synedrix OS for architects, engineers, governance stakeholders, and operators. - [Core Principles](https://docs.synedrix.io/core-principles/): Synedrix OS is a multi-agent operating system: the governed operating layer for agentic business systems. - [Agentic Enterprise Manifesto Outline](https://docs.synedrix.io/agentic-enterprise-manifesto-outline/): Companies were designed for slower information flow, human-mediated coordination, and rigid departmental boundaries. - [Technical Platform Thesis](https://docs.synedrix.io/technical-platform-thesis/): This thesis defines a reusable technical architecture for building domain-specific multi-agent systems on top of a common operating-system platform. - [Vocabulary](https://docs.synedrix.io/vocabulary/): Canonical reference for how every key concept is named, defined, and used across all blog posts, website copy, documentation, and marketing material. - [Taxonomy & Platform Spec](https://docs.synedrix.io/taxonomy-spec/): This document defines the canonical taxonomy, naming model, architectural boundaries, and packaging structure for Synedrix OS and all domain packs. - [Layer Taxonomy Table](https://docs.synedrix.io/layer-taxonomy-table/): Formalizes the canonical architecture layers of Synedrix OS and defines the owned responsibilities, interfaces, and exclusions for each layer. - [Naming Convention Spec](https://docs.synedrix.io/naming-convention-spec/): This document is the single authoritative reference for all machine identifiers and human-readable names in Synedrix OS and its domain packs. - [Platform Architecture & Tech Stack](https://docs.synedrix.io/tech-stack/): Synedrix OS is a multi-agent operating system built primarily on open-source infrastructure platforms. - [Deployment Model Spec](https://docs.synedrix.io/deployment-model-spec/): Synedrix OS supports three canonical deployment modes. All modes run the same platform code, the same agent architecture, and the same governance model. - [Agent Spec](https://docs.synedrix.io/agent-spec/): This specification defines what an agent is in Synedrix OS as a governed, versioned, registry-discoverable software actor that participates in orchestrated… - [Agent Registry Spec](https://docs.synedrix.io/agent-registry-spec/): The Agent Registry is the shared discovery, versioning, and lifecycle layer for all agents running on Synedrix OS. - [Agent Registry](https://docs.synedrix.io/agent-registry-catalog/): The agent registry is the authoritative catalog of what agents exist in the system, what they are responsible for, what they are permitted to do, and where… - [Agent Runtime Policy Spec](https://docs.synedrix.io/agent-runtime-policy-spec/): The Agent Runtime Policy defines how an agent executes — model selection, latency and cost budgets, tool authorization, retry behaviour, fallback degradation… - [Tool Authorization Model](https://docs.synedrix.io/tool-authorization-model/): This document answers: what is a tool set and how does tool authorization work in Synedrix OS? The Agent Runtime Policy Spec is the authoritative schema… - [Agent Evaluation Spec](https://docs.synedrix.io/agent-evaluation-spec/): This spec defines how a Synedrix OS agent is tested, scored, and approved across three quality dimensions: output quality, policy compliance, and operational… - [Observability Metrics Spec](https://docs.synedrix.io/observability-metrics-spec/): This specification defines the canonical observability metrics required for Synedrix OS to measure retrieval quality, groundedness and hallucination risk… - [Agent DB Schema](https://docs.synedrix.io/agent-db-schema/): This document defines the canonical relational database schema for the Synedrix OS agent layer. All tables live in Supabase Postgres (PG17) as the canonical… - [Goal Model Spec](https://docs.synedrix.io/goal-model-spec/): This specification defines the canonical goal model for Synedrix OS. A goal expresses a desired business or operational outcome. - [Goal Planning Strategy](https://docs.synedrix.io/goal-planning-strategy/): This specification defines how the Orchestrator Agent transforms a Goal Instance into a validated Runtime Task Graph Instance. - [Task Graph Spec](https://docs.synedrix.io/task-graph-spec/): This specification defines the canonical executable work model for Synedrix OS. A Runtime Task Graph Instance is the versioned, persisted execution plan… - [Workflow Contract Spec](https://docs.synedrix.io/workflow-contract-spec/): Defines the standard structure and governance rules for workflows running on Synedrix OS. Workflow contracts make execution predictable, testable, and… - [Outcome Spec](https://docs.synedrix.io/outcome-spec/): Defines the canonical outcome envelope — the standard structured JSON type returned by every agent invocation and every workflow execution in Synedrix OS. - [Event Taxonomy Standard](https://docs.synedrix.io/event-taxonomy-standard/): Synedrix OS is event-driven and contract-first (Core Principle 8). Events are the first-class triggers that move work through the system: signals, approvals… - [Orchestration & Runtime Strategy](https://docs.synedrix.io/orchestration-runtime-strategy/): This document defines the target architecture in which n8n owns orchestration (Layer 3) and LangGraph owns the agent runtime (Layer 4), with LangChain as the… - [n8n Implementation Guide](https://docs.synedrix.io/n8n-implementation-guide/): The Synedrix OS specifications define abstract contracts for agents, workflows, outcomes, and governance. - [LangGraph Runtime Implementation Guide](https://docs.synedrix.io/langgraph-runtime-implementation-guide/): This guide bridges the abstract Synedrix OS agent specifications to concrete LangGraph constructs, for agents that run in the Agent Runtime (Layer 4) rather… - [Interoperability & Protocol Strategy](https://docs.synedrix.io/interoperability-protocol-strategy/): Synedrix OS is standards-aware at the interoperability layer. An agentic operating system needs a clear strategy for how agents connect to tools, context… - [Memory Fabric Spec](https://docs.synedrix.io/memory-fabric-spec/): Synedrix OS has always had a memory substrate. This document gives it a memory architecture. Layer 7 owns the seven-store memory fabric — working memory… - [Memory Runtime Integration Guide](https://docs.synedrix.io/memory-runtime-integration-guide/): This guide bridges the Memory Fabric Spec to concrete LangGraph and NAMS constructs. It is the memory counterpart of the LangGraph Runtime Implementation… - [Layer 7 Data Plane Architecture](https://docs.synedrix.io/layer7-data-plane-architecture/): Answer two questions after the Layer 7 schema completion work: Largely complete for OS + Trading schema specification after Architecture §6 items 2–5. - [Neo4j Implementation Guide](https://docs.synedrix.io/neo4j-implementation-guide/): The Neo4j platform page establishes what the store is and why the OS uses it. The Memory Fabric Spec and the Memory Runtime Integration Guide fix the graph… - [Agent Graph Data Model](https://docs.synedrix.io/agent-graph-data-model/): Before this document, the graph tier had exactly one node type — Outcome — and agent identity existed only as a property on it. - [Responsibility Matrix](https://docs.synedrix.io/responsibility-matrix/): Defines the split of responsibilities between Synedrix OS, domain packs, and business instances. The goal is to prevent architectural drift by making… - [AI-Native Org Chart](https://docs.synedrix.io/ai-native-org-chart/): Synedrix OS should not be modelled as twelve AI employees reporting to a CEO. A better abstraction is an AI-native operating layer underneath a relatively… - [Tenancy Spec](https://docs.synedrix.io/tenancy-spec/): Synedrix OS has had no model of who owns a record. A business instance was a deployed runtime, which in practice meant a stack per customer, and the memory… - [Identity and Access Spec](https://docs.synedrix.io/identity-access-spec/): The canon names the humans that matter. It gives them six control roles, derived from agent escalation paths and the Responsibility Matrix. - [Metering and Entitlement Spec](https://docs.synedrix.io/metering-entitlement-spec/): ADR-OS-012 decided what Synedrix OS counts and how it is protected: the metered unit is the governed goal, every deployment writes a tamper-evident usage… - [Domain Pack Template](https://docs.synedrix.io/synedrix-domain-pack-template/): Use this template to define a Synedrix domain pack such as Trading, Commerce, Support, Finance, or Operations. - [Space Usage Guide](https://docs.synedrix.io/space-usage-guide/): This Space is the authoritative working environment for: This Space is not the primary build environment for domain-specific implementation details such as… ## Platforms - [Platform reference](https://docs.synedrix.io/platforms/): One page per platform in the Synedrix OS tech stack: what it is, what it is normally used for, and how and why Synedrix OS uses it. - [n8n — Orchestration](https://docs.synedrix.io/n8n/): n8n describes itself as "a fair-code licensed workflow automation tool that combines AI capabilities with business process automation." - [LangGraph — Agent Runtime](https://docs.synedrix.io/langgraph/): LangGraph describes itself as "a low-level orchestration framework and runtime for building, managing, and deploying long-running, stateful agents." - [Hookdeck — Ingress Gateway](https://docs.synedrix.io/hookdeck/): Hookdeck describes itself as providing "reliable infrastructure to work with webhooks and external events — without managing it yourself." The inbound product… - [Hookdeck Outpost — Egress Gateway](https://docs.synedrix.io/hookdeck-outpost/): Outpost's documentation describes it as "outbound webhooks infrastructure and an open-source implementation of Event Destinations that enables delivery of… - [Supabase PG17 — Canonical Relational Truth](https://docs.synedrix.io/supabase/): Supabase is a platform built around Postgres, not a database in its own right. Its own architecture documentation is explicit about the relationship… - [Redis — Coordination Bus & Hot State](https://docs.synedrix.io/redis/): Redis describes itself as "an in-memory data store used by millions of developers as a cache, vector database, document database, streaming engine, and… - [Qdrant — Semantic Memory](https://docs.synedrix.io/qdrant/): Qdrant is a vector database. Its documentation frames the purpose as vector search that "goes beyond keyword matching to find data based on semantic meaning"… - [Neo4j — Context Graph & Lineage](https://docs.synedrix.io/neo4j/): Neo4j's Operations Manual opens with: "Neo4j is the world's leading graph database. The architecture is designed for optimal management, storage, and… - [QuestDB — Time-Series Data Fabric](https://docs.synedrix.io/questdb/): QuestDB's documentation describes it as "an open source time-series database engineered for low latency", built on "a column-oriented, time-partitioned… - [Langfuse — LLM Engineering](https://docs.synedrix.io/langfuse/): Langfuse describes itself as "an open-source AI engineering platform that helps teams collaboratively debug, analyze, and iterate on their LLM applications." - [Grafana LGTM Stack — Operational Monitoring](https://docs.synedrix.io/grafana-lgtm/): The Grafana LGTM Stack is not one product. It is five separately released open-source projects from Grafana Labs that are designed to compose into a single… - [PostHog — Behavioural Analytics & Feature Flags](https://docs.synedrix.io/posthog/): PostHog describes itself as "the open source platform for building self-driving products", which "provides every tool you need to build a successful product… ## Lab components - [Lab components](https://docs.synedrix.io/lab-components/): Reference material for components under evaluation in the governed lab lane — not part of the Synedrix OS tech stack, not counted among the twelve platforms… - [Docling — Lab Component](https://docs.synedrix.io/docling/): Docling (docling-project/docling, MIT) is a document-conversion library that parses PDFs, Office documents, HTML, and Markdown into a unified structural… - [EverOS — Lab Component](https://docs.synedrix.io/everos/): EverOS (EverMind-AI/EverOS) is an open-source, local-first agent-memory runtime, self-classified Production/Stable at v1.2.3. - [LanceDB — Lab Component](https://docs.synedrix.io/lancedb/): LanceDB describes itself as a "developer-friendly OSS embedded retrieval library for multimodal AI," built on the open Lance columnar data format. - [Semantica — Lab Component](https://docs.synedrix.io/semantica/): Semantica (semantica-agi/semantica) is a Python knowledge-graph and GraphRAG toolkit — real, active, MIT licensed, at PyPI version v0.6.5. - [Laya — Lab Component](https://docs.synedrix.io/laya/): Laya (laya on PyPI, from Convai Innovations) is a System One decision model: a non-autoregressive model that answers typed questions about a piece of state in… - [Jev — Lab Component](https://docs.synedrix.io/jev/): Jev, from TypeSafe AI, is a System One decision model offered as a managed API. You send it a piece of state and one or more typed questions, and it returns… ## OpenWiki - [OpenWiki](https://docs.synedrix.io/openwiki/): OpenWiki is a generated overview of Synedrix OS. A language model writes it from the repository sources, and a maintainer reviews the text before it is… - [Documentation Quickstart](https://docs.synedrix.io/openwiki/os/quickstart/): The primary sources already exist in the repository and this wiki treats them as such, not duplicates: Future agents editing this repository: never write… - [Platform Architecture Overview](https://docs.synedrix.io/openwiki/os/architecture-overview/): The core bet is that coordination quality, not model power, is the durable value in a multi-agent system (Principle 2). - [Governance and Controls](https://docs.synedrix.io/openwiki/os/architecture-governance-and-controls/): Synedrix OS Layer 9 is where execution meets accountability. Governance is not a surface applied to agents after the fact — it is load-bearing infrastructure… - [Memory Fabric](https://docs.synedrix.io/openwiki/os/architecture-memory-fabric/): This page covers Layer 7's memory architecture: the tier taxonomy, the memory record envelope, the full memory lifecycle, the recall and promotion contracts… - [Observability](https://docs.synedrix.io/openwiki/os/architecture-observability/): The observability layer (Layer 10) of Synedrix OS is responsible for making every agent execution measurable, explainable, and reviewable. - [Agent Runtime & Orchestration](https://docs.synedrix.io/openwiki/os/architecture-agent-runtime-and-orchestration/): This page explains how an "agent" and a "workflow" in the abstract specs (Agent Spec, Workflow Contract Spec) become concrete execution — and specifically why… - [Tech Stack & Deployment](https://docs.synedrix.io/openwiki/os/operations-tech-stack-and-deployment/): Every component below is a deliberate, non-overlapping-responsibility choice — Principle 11 (open by default, sovereign by design) is architectural, not… - [Tenancy, Identity, and Metering](https://docs.synedrix.io/openwiki/os/operations-tenancy-and-identity/): This page covers three interlocking operational concerns that govern who owns data, who may act on it, and how the platform accounts for work delivered: the… ## Optional - [Sitemap](https://docs.synedrix.io/sitemap/): Every page above as plain links, with descriptions. The same list as JSON: https://docs.synedrix.io/sitemap.json