📄️ Overview
Adapters are how a venue gets its capabilities. Each adapter contributes a family of operations — self-describing, invocable units with JSON Schema inputs and outputs — that any client, agent, or orchestration can call. Out of the box a venue ships with adapters spanning LLMs, HTTP, files, lattice state, federation, and more; operators can add their own.
📄️ JSON
The JSON adapter provides four pure data manipulation primitives for composing structured outputs and declarative branching in orchestrations. All operations are pure functions with sub-millisecond execution — no IO, no external calls.
📄️ DLFS
DLFS provides self-sovereign, decentralised file storage on Covia venues. Each user gets per-user drives that are cryptographically signed with their own Ed25519 key, stored in an independent lattice region, and portable across venues.
📄️ Vault
The Vault adapter provides simplified file access for agents and users by wrapping DLFS with a fixed drive name. Instead of specifying a drive on every call, vault operations always target the "health-vault" drive.
📄️ A2A
Covia speaks the Agent-to-Agent protocol (A2A) both ways. A venue is a spec-conformant A2A v1.0 server — any A2A client can send it messages and track tasks — and the A2A adapter lets your operations and agents call remote A2A agents as grid operations. A2A maps cleanly onto Covia's own model: an A2A Task is a Covia Job, and an A2A Message is a turn in a conversation.
📄️ MCP
The MCP adapter lets a venue call external Model Context Protocol (MCP) servers as grid operations — discovering their tools and invoking them like any other operation.
📄️ File
The File adapter gives agents and operations root-jailed access to a local filesystem. An operator configures one or more named roots; every file: operation works relative to a root and cannot escape it. Roots can be host directories, ephemeral temp directories, or DLFS-backed drives.
📄️ Grid
The Grid adapter enables distributed operation execution across the Covia network. Operations can run locally or on remote venues — the interface is the same either way.
📄️ HTTP
The HTTP adapter makes outbound HTTP requests to external APIs and web services, with built-in SSRF protection.
📄️ LangChain
The LangChain adapter provides unified access to multiple LLM providers — OpenAI, Anthropic, Ollama, and xAI, plus any OpenAI-compatible endpoint — with a consistent interface for messages, tool calling, and structured output.
📄️ Orchestrator
The Orchestrator executes multi-step workflows as directed acyclic graphs (DAGs). Steps run in parallel where possible, with automatic dependency resolution and result composition.
📄️ Scheduler
The Scheduler adapter runs an operation later — at an absolute time or after a delay. It's how a venue defers work: a reminder, a periodic sweep, or an agent that should wake at a set time. Scheduled invocations run with the authority of whoever scheduled them, captured at schedule time and replayed unchanged when they fire.
📄️ Covia (Venue)
The Covia adapter provides workspace CRUD, data inspection, and lattice access. These are the core operations for reading and writing data on a venue.