AI Overview

In Octo, LLM providers are connectors like any database or HTTP endpoint, AI capabilities are blocks you drop into a pipeline, and flows speak MCP in both directions.

LLMs are connectors

You configure an LLM provider the same way you configure Postgres or Slack: a named connector with settings. The Anthropic, OpenAI, and Gemini connectors satisfy the same client interface, so every AI block binds to a provider by connector name and works with any of them.

connectors:
  - name: claude
    type: llm-anthropic
    settings:
      apiKey: ${ANTHROPIC_API_KEY}

Swap llm-anthropic for llm-openai, llm-gemini or llm-openrouter and nothing else in the flow changes. The one exception is ai-embed, which needs a provider that serves embeddings; OpenAI, Gemini and OpenRouter do, Anthropic does not. See LLM Providers.

AI capabilities are blocks

AI in Octo is a family of blocks that compose with everything else in a flow:

Because they are ordinary blocks, they sit in the middle of pipelines: an HTTP source feeds an ai-router, whose route runs an ai-mapping wrapped in an ai-retry, followed by a database write. The full field reference lives at AI Blocks.

Agents are declarative

An ai-agent gets its memory, tools, and skills from YAML. Per-thread conversation memory is one field (memoryThreadId); tools are process chains the model calls with JSON arguments; skills are instruction documents the model loads on demand. Prompt, tools, memory policy and fallback behavior form a single reviewable block in a flow file.

Flows speak MCP

The integration runs in both directions. The mcp-router block turns flows into tools, resources, and prompts that any MCP client (Claude, IDEs, other agents) can call; see Expose an MCP Server and Secure an MCP Server with OAuth. The runtime and editor also expose an MCP endpoint for AI-assisted authoring, so a coding agent can draft, validate, run, and debug integrations against your environment; see The Platform MCP Server.

Explore the section