Skip to main content
Scaffold an agent in any framework, run it on your laptop, deploy it to your Nasiko cluster, and chat with it. Every model call it makes is routed through Nasiko and attributed in TokenOps. You don’t add an SDK or change the agent’s code.
Here to measure the coding agents you already use? Start with the Quickstart instead.

​
Prerequisites

  • Docker, to build and run agent images
  • Rust, to install the CLI
  • A Nasiko cluster with a model provider key configured — run one locally with Deploy the stack, or use your organization’s
  • An account with deploy permission — see access control

​
Build and deploy

1

Install the CLI and sign in

Your token is stored in ~/.nasiko/config.json. More options, including nasiko up: Install and connect.
2

Scaffold an agent

This writes an AgentCard.json (the agent’s identity and skills), a Dockerfile, and starter source in src/. Run nasiko new with no arguments to pick a framework interactively. See Scaffold an agent.
3

Run it locally

This builds the image and runs it on localhost:8000. When a cluster is connected, the local container gets the same model settings the cluster injects at deploy time, so you don’t need to copy an API key into the project. A project .env file, if present, is loaded too.In a second terminal:
More: Run and chat locally.
4

Deploy it

This builds the image, pushes it to your cluster’s built-in registry, then registers and starts the agent. It prompts for a version (use -y to accept the suggested one) and writes .nasiko/agent.json, which binds this directory to the deployed agent.No local Docker? Run nasiko upload . and the cluster builds the image for you. See Deploy an agent.
5

Chat with the deployed agent

Omit the agent name (nasiko chat "...") to let the orchestrator pick from every agent you can access.
6

See it in the dashboard

Sign in at your cluster URL. Your agent is already:

​
How the agent reaches a model

At deploy time, Nasiko points the agent’s model SDK at the cluster’s LLM router and gives it a short-lived identity credential instead of a real provider key. The router selects the provider and key server-side, so no agent and no log ever holds the real key. To route this agent to a different model or provider, attach an LLM config:
To give the agent its own provider key or any other secret, store it encrypted and restart:
See agent secrets.

​
Next steps

Versions and rollback

Ship a new version, or roll back to an earlier one.

Set access policy

Control who can use and manage this agent.

Connect tools over MCP

Give the agent permission-filtered tools.

Compose agents

Chain agents into a multi-agent workflow.
Stuck? Ask in Discord or email support@nasiko.com.