SmythOS

SmythOS lists 76 named integrations grouped into eight classes, workflow triggers, AI models and tools, data and knowledge, business apps, messaging and alerts, analytics and scraping, developer tools, and publishing.

They span CRM (HubSpot, GoHighLevel), project and issue tracking (Jira, Linear, Asana, ClickUp, Trello), commerce and payments (Shopify, Stripe), storage and productivity (Google Workspace, SharePoint, OneDrive, Notion, Airtable), messaging (Slack, Teams, Discord, Telegram, Twilio), email (Gmail, SendGrid, Mailchimp, Resend), databases (Supabase, Firestore, Upstash) and CMS (WordPress, Webflow, Squarespace).

Credentials are stored once in the Vault and actions wired into any flow without HTTP or SDK work, alongside a 40-plus component library and a generic OpenAPI component for anything unlisted.

Sourcesmythos.com/docs/agent-studio/integrationsread 2026-09-01

SmythOS is built for orchestrating several agents together, with cooperative planners, delegators and specialists, one agent able to review and refine another's output, and a SmythOS Agents component that lets an agent call other built-in agents as tools.

The runtime handles orchestration as a kernel responsibility rather than a graph library, with retries, cancellation, priorities, shared memory and message buses, plus packaging, isolation and lifecycle management across local, cloud and edge.

Workflows are built on a drag-and-drop canvas with logic components and multi-step reasoning, and a single agent specification spans Studio, SDK and CLI without rewrites.

Sourcesmythos.com/product/agent-runtime, /docs/agent-studio/overview and /docs/agent-studio/integrationsread 2026-09-01

Studio ships a Data Pool with Data Spaces that centralizes the agent's knowledge base with structured storage and retrieval, which the customer populates. The runtime exposes vector databases as an OS-level abstraction alongside storage and caching, and embeddings are held and encrypted as a first-class data type. Third party document and database connectors sit alongside this store as integrations.

Sourcesmythos.com/docs/agent-studio/overview and /product/securityread 2026-09-01

Components can be disabled or removed entirely from a bundle so they are unavailable to agents, which lets the customer decide what an agent may never do. SmythOS offers no control over sign-off, meaning who approves which actions and what happens when nobody does, and has no approval step per action, no pause to confirm, no review queue and no escalation path. The ACL and Candidate system and the four named roles govern access. SmythOS does not describe a single human handoff point either.

Sourcesmythos.com/product/securityread 2026-09-01

Access runs through fine-grained ACLs in an internal ACL and Candidate system that decides which agents and users reach which resources, least privilege for every component and agent with no implicit trust between them, per-space key vaults and per-tenant and per-agent namespace isolation. Data is encrypted at every stage, with TLS 1.2+ in transit and KMS at rest, HashiCorp Vault and AWS Secrets Manager integration, and logs of agent activity, execution flows and access decisions. SmythOS publishes no SOC 2, ISO 27001 or other attestation and does not describe SSO or SAML.

Sourcesmythos.com/product/securityread 2026-10-01

Full audit logs record agent activity, execution flows and access decisions through the SRE logging interface, with verbosity configurable up to high and the option to track specific components.

Logging and monitoring in real time support debugging and incident response, including third-party token usage, logs aggregate into enterprise SIEM systems for analysis, auditing and alerting, and partial redaction driven by patterns and regular expressions can hide values such as an authentication token.

The canvas walks through each step of the agent's reasoning from raw input received to decision returned, and Studio has an analytics view for token usage and cost.

Sourcesmythos.com/product/security and /docs/agent-studio/overviewread 2026-09-01

Studio builds workflows with logic, memory and multi-step reasoning, the runtime carries shared memory alongside retries, cancellation and priorities as a kernel responsibility, cached memory is encrypted as a first-class data type, and the Upstash integration stores session data using Redis or Kafka. SmythOS does not describe state that persists across sessions and that the agent can address, whether accumulated automatically or wired from these building blocks.

Sourcesmythos.com/docs/agent-studio/overview, /product/security and /product/agent-runtimeread 2026-09-01

SmythOS runs in three ways, each with its own data posture.

The multi-tenant SmythOS SaaS segregates tenants logically, on-premises or VPC deployment inside the customer's own data center or cloud is stated to guarantee that data never leaves the customer's environment and supports internal residency and monitoring policies, and on-device deployment bundles one or more agents with the runtime into a standalone executable for controlled or offline environments.

Studio itself is self-hostable from a Docker community image, the runtime is MIT-licensed at roughly 50 megabytes and runs on cloud, on-premises, edge, desktop, mobile or containers with GPU optional, and storage backends are selectable between local disk or RAM and remote S3 or Redis.

Sourcesmythos.com/product/security, /docs/agent-studio/self-hosted/docker-community and github.com/SmythOS/sreread 2026-09-01

A browsable template catalog at smythos.com/templates offers prebuilt customizable templates for common use cases that a customer picks, drags, drops and deploys with no code, spanning support, research and operations. SmythOS calls them instant agent blueprints organized by department, and starting from a template is one of the main ways into Studio alongside the quickstart. Customers adopt these packaged assets directly, without the vendor's team assembling configurations for them.

Sourcesmythos.com/templates and /docs/agent-templates/overviewread 2026-09-01

Agents can be triggered by forms, calendar events, chat messages or webhooks, through nine trigger integrations, Slack slash commands and mentions, Discord bot messages, Telegram bot commands, Google Calendar and Microsoft Calendar events, Google Chat space triggers, Microsoft Teams channel messages, Ayrshare social post triggers and tl;dv meeting transcripts. Agents deploy to production via chat, API or webhooks, and SmythOS also offers scheduled runs where agents clock in automatically, bulk runs driven by CSV, and web chat and voice as delivery surfaces.

Sourcesmythos.com/docs/agent-studio/integrations and /docs/agent-studio/overviewread 2026-09-01

Customers pick models from three tiers, public API models with OpenAI, Google Gemini, Groq and Perplexity named, hosted enterprise services with Google Vertex AI and AWS Bedrock named, which keep provider-level residency and compliance, and local or self-hosted models run on-premises or in a private cloud so no data leaves the customer's environment. Models can be switched and added on the fly without a rebuild or redeploy, and the integration catalog adds OpenRouter for unified access to GPT, Claude and Mistral, plus Hugging Face and Replicate for open-weight models.

Sourcesmythos.com/product/security, /product/agent-runtime and /docs/agent-studio/integrationsread 2026-09-01

A finished agent can be exposed as an API, a model endpoint, an MCP server, a web chat or a voice interface, so outside systems can call it. The runtime, CLI and SDK are open source under the MIT license with SDK and core documentation and runnable examples, the Studio is available as a Docker image, an embeddable route is available, and an OpenAPI component generates flows from specifications or tests endpoints. SmythOS also publishes an MCP server that spawns Linux sandbox containers for the customer's assistant to call.

Sourcesmythos.com/docs/agent-deployments/overview, github.com/SmythOS/sre and github.com/SmythOSread 2026-09-01

Studio offers no-code debugging and testing that inspects live runs and fixes issues inside the canvas, with a Debugging Agents guide and a step-through of the agent's reasoning from the raw input received to the decision returned. SmythOS does not say what a run is checked against, so the step-through shows what happened without deciding whether it was right, and it offers no evaluation harness, scored test case or gate that passes or fails.

Sourcesmythos.com/docs/agent-studio/overview and /docs/agent-studio/build-agents/debugging; smythos.com/docs/agent-studio/build-agents/debuggingread 2026-09-01

Third-party browser and retrieval engines are wired in as integrations. The Studio catalog includes ScrapingBee as a web scraping API and AvesAPI for SERP scraping, alongside Perplexity and Tavily as search APIs, so the agent reaches pages it has no interface to. SmythOS has no hosted or local browser that it drives itself, no desktop session and no remote computer control, and the Linux sandbox containers spawned by its Docker orchestration MCP server are an execution environment, not interface control.

Sourcesmythos.com/docs/agent-studio/integrations and github.com/SmythOSread 2026-09-01