Skip to content

Novita AI command-line client

Lets an agent chat with DeepSeek, GLM and other models via the Novita AI API from a terminal.

Stars
58,084
Licence
Apache-2.0
Files
1 file

What it does

This skill teaches the agent to use a command-line tool called cli-anything-novita, which sends prompts to Novita AI, a service that hosts models such as DeepSeek, GLM and MiniMax. Once installed, the agent can run commands to chat with a model, stream responses, list available models, test the connection and manage a saved config and chat session. It is designed so the agent can request machine-readable JSON output and parse it.

Great for

  • Developers who want to call several hosted open-weight models from scripts or a terminal
  • Agent builders who want a Novita model reachable through a simple command-line interface
  • People already holding a Novita API key who want quick model testing

Skip it if

  • Anyone without a Novita account or API key, since every request needs one
  • Sending sensitive or confidential prompts, because chat content is transmitted to a third-party hosted service (reason: data leaves your machine)

Try asking

  • “Ask DeepSeek V3.2 to explain a concept from the terminal”
  • “List which models Novita currently offers”
  • “Test whether my Novita API key and connection are working”
  • “Stream a generated Python function from GLM or DeepSeek”
Step-by-step guide: how to use Novita AI command-line clientInstall, first run, examples, tips and FAQs

Install in 3 steps

  1. 1

    Download the skill

    The ZIP contains the 1 original files, the Apache-2.0 licence and an attribution note.

    cli-anything-novita.zip
  2. 2

    Add it to your agent

    Claude Code (all projects)

    mkdir -p ~/.claude/skills && unzip cli-anything-novita.zip -d ~/.claude/skills/

    Claude Code / Agent SDK (this project only)

    mkdir -p .claude/skills && unzip cli-anything-novita.zip -d .claude/skills/

    Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.

  3. 3

    Ask for the task

    No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.

Get better results

  • Store the API key with config set or an environment variable rather than pasting it into prompts or chat logs
  • Use the --json flag when the agent needs to parse output, and check return codes
  • Run the test command first to confirm connectivity before longer tasks

What's inside

  • SKILL.md

Redistributed unmodified from HKUDS/CLI-Anything under the Apache-2.0 licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.