Write agents, don't wire them
Declare agents, tools, sandboxes and workflows in a clean, YAML-like format. No boilerplate, no glue code.
A language for agent ecosystems
Describe your models, agents, subagents, sandboxes, tools, skills and workflows in one clean .nt file. One command brings it all up.
age.nt — example
Explorer
⌄ example
⌄ subagents
age.nt
1# age.nt — the entry file for this ecosystem.
2# It imports every capability, then wires them onto one agent.
3
4import ./config.nt
5import ./sandboxes.nt
6import ./skills.nt
7import ./tools.nt
8import ./subagents/researcher.nt
9
10agent age
11 description: Estimates a person's most likely age from clues.
12 model: anthropic/claude-sonnet-5
13 thinking: high
14 sandbox: workspace
15 skills:
16 - estimation
17 tools:
18 - current_year
19 - fs_write
20 subagents:
21 - researcher
22 instructions: |
23 You estimate a person's most likely age from the clues provided.
24 Call current_year whenever a clue implies a birth year.
25 Delegate to the researcher to pin down the year of an event.
26 Follow the estimation checklist, then commit to one integer.
27 input:
28 clues:
29 type: string
30 description: Any details that hint at the person's age.
31 output:
32 age:
33 type: number
34 description: The single best age estimate.
35 reason:
36 type: string
37 description: A one-sentence justification.
NTUTF-8Spaces: 2Ln 37, Col 1
One CLI to run it all
Validate, graph, run and chat. A single nt command brings your whole ecosystem up against a live model.
As easy as writing English
Describe what an agent should do in plain language. The engine wires the model, tools and delegation for you.
Install the CLI and run your first agent in minutes. Build your first agent →