Are you an LLM? Read llms.txt for a summary of the docs, or llms-full.txt for the full context.
Skip to content

Developer Overview

This section documents the underlying Toolang design. It is meant for people who need the model behind the CLI, runtime, storage layout, and integration boundaries.

What this section covers

The developer docs are organized around stable runtime concepts:

  • filesystem layout and agent identity
  • capability resolution and scope rules
  • execution, scheduling, and durability
  • tasks, chores, and collaboration
  • local APIs and shared projections
  • plugins, memory, and implementation constraints

Each page owns one topic so the same rule does not need to be repeated in multiple places.

Core vocabulary

  • toolang root the local Toolang system directory
  • agent home the local directory that hosts one or more .too files
  • agent room the private machine-managed area for one agent
  • agent_uri the canonical identity string
  • agent_id a short stable hash derived from agent_uri
  • ref, inline, local the three capability forms
  • agent, shared, global the three capability scopes
  • runtime loop a long-lived trigger source such as server, poll, hook, or pulse
  • execution strategy the strategy used to complete one turn
  • run one continuous active interval of one agent process
  • thread a durable execution context
  • turn one complete handling attempt inside a thread
  • step one internal action inside a turn

Design rules

  • local files and databases are the primary execution truth
  • .too source is authored state, not the final runtime input
  • toolang sync materializes exact runtime inputs before execution
  • runtime loops decide when work starts
  • execution strategies decide how one turn completes
  • plugins stay at the edge and do not replace runtime lifecycle or scheduling

Read next

© 2026 Toolang