OpenViSTAI · Agents · Blockchain · Crypto
Menu
Agent Infrastructure

Nasiko

Nasiko is a Rust-based runtime and CLI for discovering coding-agent harnesses, collecting optional session and cost information, and routing supported agents’ model calls through a configurable control plane.

Independent OpenViST project profile, based on linked sources.

Nasiko — OpenViST project profile in Agent Infrastructure.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use Nasiko when you want a runtime around existing coding-agent CLIs for discovery, optional reporting or model routing, rather than replacing those harnesses.

Who it is for

  • Developers who run coding-agent CLIs and want to identify which harnesses are installed.
  • Teams seeking session reporting and cost visibility across supported coding agents.
  • Developers who want to route supported agents to selected models while keeping their existing harness workflows.

Documented uses

  • Detect supported coding-agent CLIs and inspect their versions and configuration locations.
  • Enable session reporting through local harness hooks.
  • Review costs by harness and model.
  • Route supported coding agents' model calls to selected models.
Before you choose

Requirements & limits

The documented discovery command requires no account. Reporting and routing require an active control plane and valid login. The Docker Compose path requires Docker Engine with Compose V2; the CLI requires Rust 1.85 or later.

  • Cursor CLI is listed for discovery and reporting, but not LLM routing.
  • Discovery is read-only; reporting installs local hooks and routing updates harness settings.
  • The Docker setup requires configured secrets and administrator credentials; the default OpenAI-backed routing and chat setup also requires an OpenAI API key.
  • Local coding-agent routing requires a separate agent JWT secret.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Run read-only discovery of installed coding agents

Install the CLI from the repository and list supported coding-agent harnesses detected on the local machine.

Before you start

  • Rust toolchain; the repository specifies Rust 1.85 or later for the CLI.
  • Git and a terminal.

Steps

  1. Clone the Nasiko repository and change into its directory.

  2. Install the CLI with the command below.

    Documented command
    cargo install --path cli/ --force
  3. Run nasiko agents discover.

Expected outcome

The command prints detected harnesses, connection status, versions and configuration locations, then exits. The README describes discovery as read-only, requiring no account and sending nothing off the machine.

Guide limitations

  • The listed supported harnesses are Claude Code, Codex, OpenCode and Cursor CLI.
  • Discovery does not enable session reporting or model routing.
Source-based practical guide

Prepare the Docker Compose platform

Configure and start the self-hosted Nasiko platform using the documented Docker-only setup.

Before you start

  • Docker Engine with the Docker Compose V2 plugin.
  • Git and a terminal.
  • An OpenAI API key for the default OpenAI-backed routing and chat setup.

Steps

  1. Clone the repository, enter its directory and copy .env.example to .env.

  2. Set the documented encryption key, user-login JWT secret, separate agent JWT secret, administrator credentials and provider key in .env.

  3. Start the platform with the command below.

    Documented command
    docker compose up -d

Expected outcome

Docker Compose builds and starts the platform; the README directs users to open `http://localhost:8080` and log in.

Guide limitations

  • The repository warns that the encryption key must be retained across restarts to access existing encrypted secrets.
  • Starting the platform alone does not connect local coding agents; reporting or routing requires agent setup and a valid login.
COMPARE OPTIONS

Compare options for AI coding assistance

These projects document a common task and share a project role. This is a source-based comparison, not an execution benchmark or a guarantee of interchangeability.

ProjectDocumented purposePlatformAccess and requirements
NasikoDetect supported coding-agent CLIs and inspect their versions and configuration locations.CLIThe documented discovery command requires no account. Reporting and routing require an active control plane and valid login. The Docker Compose path requires Docker Engine with Compose V2; the CLI requires Rust 1.85 or later.
ParitokRoute coding-agent requests through a local proxy.Self-hosted, ServerThe project is public and licensed under Apache-2.0. The documented self-hosted quick start uses Python 3.11 or later and Ollama.
SandboxdPrompt a coding agent to build an app in an isolated container and open its preview URL.Docker, Self-hosted, ServerThe self-hosted project is open source under the MIT license. The repository documents a live browser demo with sample data and no installation. Self-hosting requires Docker with the Compose plugin and Git on Linux; macOS via Docker Desktop is best-effort.
Evidence and transparency

Sources & review

Source record details
Source availability
Active
Sources checked
16 October 2026
Original website title
Nasiko-Labs/nasiko · Official homepage title · retained in its source language