Skip to main content

Zima Blue CLI - Personal Agent Orchestration Platform

Project description

Zima Blue CLI

Python License CI

"I chose blue. That intense blue." — Zima Blue

Zima Blue CLI is a personal Agent orchestration platform that lets you run a 7x24 autonomous AI Agent factory on your own computer.

Simply define Prompt templates and configuration parameters, and Zima will automatically invoke Kimi CLI to execute tasks and return structured results.

Define Prompt Template → Configure Parameters → Execute → Get Results

Table of Contents


Features

  • 🤖 Multi-Agent Support — Supports Kimi, Claude, Gemini, and other AI executors
  • 📋 Configuration Entities — Layered config design: Agent + Workflow + Variable + Env + PMG
  • 🚀 PJob Execution Layer — Declarative task configuration, one-command composition and execution
  • 📝 Jinja2 Templates — Flexible Prompt templates with variable substitution
  • 🔒 Secret Management — Supports environment variables, files, Vault, and other secret sources
  • 🧪 Full Test Coverage — Unit tests + integration tests (including real Kimi invocation tests)
  • 🧹 Auto Cleanup — Built-in cleanup scripts for cache and temporary files

Architecture

Configuration Entities

Zima uses a layered configuration design, enabling flexible task execution through composition:

Entity Purpose Example
Agent AI executor config (kimi/claude/gemini) code-reviewer
Workflow Prompt template (Jinja2) code-review-template
Variable Template variable values review-vars
Env Environment variables and secrets prod-env
PMG Dynamic parameter groups build-params
PJob Execution config (composes all above) daily-review-task

Directory Structure

~/.zima/
├── configs/
│   ├── agents/           # Agent configurations
│   ├── workflows/        # Workflow templates
│   ├── variables/        # Variable configurations
│   ├── envs/             # Environment configurations
│   ├── pmgs/             # Parameter groups
│   └── pjobs/            # Execution task configurations
└── agents/               # Agent runtime directories
    └── <agent-code>/
        ├── logs/         # Execution logs
        ├── prompts/      # Runtime prompts
        └── workspace/    # Working directory

Execution Flow

# Quick execution (shorthand)
zima run my-agent

# Composed execution (recommended)
zima pjob run my-task    # Combines Agent + Workflow + Variable + Env

Important This project adopts an iterative design approach. Always refer to docs/architecture/ for the latest design, and use AGENTS.md at the repository root as the final authority for implementation.


Quick Start

Installation

# Clone the repository
git clone https://github.com/zhuxixi/zima-blue-cli.git
cd zima-blue-cli

# Install dependencies
pip install -e "."

Basic Usage

# Create an Agent
zima create my-agent

# Run the Agent
zima run my-agent

# View logs
zima logs my-agent

Advanced Usage: Composed Configuration

# 1. Create an Agent
zima agent create --name "Code Reviewer" --code reviewer --type kimi

# 2. Create a Workflow template
zima workflow create --name "Review Template" --code review \
  --template "# Review: {{ task_name }}\n\n{{ description }}"

# 3. Create Variable configuration
zima variable create --name "Review Vars" --code review-vars
zima variable set review-vars task_name "Bug Fix Review"
zima variable set review-vars description "Check for memory leaks"

# 4. Create a PJob composition
zima pjob create --name "Code Review Task" --code review-task \
  --agent reviewer --workflow review --variable review-vars

# 5. Run the task
zima pjob run review-task

# 6. View execution history
zima pjob history review-task

Cleanup

# Unix / Linux / macOS
./cleanup.sh --auto

# Windows
cleanup.bat --auto

CLI Commands

Shorthand Commands

zima create <name>          # Create an Agent
zima run <name>             # Execute once
zima list                   # List all Agents
zima show <name>            # Show configuration
zima logs <name>            # View logs

Full Command Groups

# Agent management (supports kimi/claude/gemini)
zima agent create --name "My Agent" --code my-agent --type kimi
zima agent list --type kimi
zima agent show my-agent
zima agent test my-agent      # Preview generated CLI command
zima agent validate my-agent

# Workflow template management
zima workflow create --name "Review" --code review --template "# {{ title }}"
zima workflow render review --var my-vars

# Variable management
zima variable create --name "My Vars" --code my-vars
zima variable set my-vars key value

# Environment configuration
zima env create --name "Prod" --code prod-env
zima env set-secret prod-env API_KEY --source env

# PMG parameter group management
zima pmg create --name "Build Params" --code build-params

# PJob execution (composes Agent + Workflow + Variable + Env)
zima pjob create --name "Daily Task" --code daily \
  --agent my-agent --workflow review --variable my-vars
zima pjob run daily           # Execute task
zima pjob render daily        # Preview rendered output
zima pjob history daily       # View history

See docs/API-INTERFACE.md for the complete interface documentation.


Documentation

docs/
├── vision/           # Project vision and story
├── architecture/     # Latest architecture design ⭐ authoritative
├── history/          # Historical designs (reference only)
└── decisions/        # Architecture Decision Records (ADR)
    ├── 001-use-subprocess.md
    ├── 002-15min-cycle.md (deprecated)
    ├── 003-early-completion.md (deprecated)
    └── 004-single-execution.md ⭐ current

Use Cases

  • SOP Tasks: DevOps scripts, data processing, report generation
  • R&D Tasks: Test coverage, code refactoring (workflow-driven via Prompt)
  • CI/CD Integration: Build steps that return structured results
  • Scheduled Tasks: Periodic automation via cron

Development

See AGENTS.md for development conventions, coding style, and design principles.

Naming Origin

Zima Blue is inspired by Alastair Reynolds' science fiction short story Zima Blue.

The story follows an artist-robot who, after millennia of upgrades and evolution, ultimately returns to its original form as a simple pool-cleaning robot — symbolizing returning to essence and self-evolution.


License

This project is licensed under the MIT License.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

zima_blue_cli-0.1.0.tar.gz (289.7 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

zima_blue_cli-0.1.0-py3-none-any.whl (105.6 kB view details)

Uploaded Python 3

File details

Details for the file zima_blue_cli-0.1.0.tar.gz.

File metadata

  • Download URL: zima_blue_cli-0.1.0.tar.gz
  • Upload date:
  • Size: 289.7 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: uv/0.11.7 {"installer":{"name":"uv","version":"0.11.7","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"24.04","id":"noble","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":true}

File hashes

Hashes for zima_blue_cli-0.1.0.tar.gz
Algorithm Hash digest
SHA256 8166ca2f16240994ecc708ba01af88ffdadd1eb94b50c5db265042dab852fe90
MD5 81e886e47f4eea8636980251cbafd191
BLAKE2b-256 4adf3042780264594c06cc281571c1754ec106766dbc6f55db0f5e74cc2543cf

See more details on using hashes here.

File details

Details for the file zima_blue_cli-0.1.0-py3-none-any.whl.

File metadata

  • Download URL: zima_blue_cli-0.1.0-py3-none-any.whl
  • Upload date:
  • Size: 105.6 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: uv/0.11.7 {"installer":{"name":"uv","version":"0.11.7","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"24.04","id":"noble","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":true}

File hashes

Hashes for zima_blue_cli-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 eebc1cc8841c0d4fe71d4916661edea17a3015fe138e5ef1a1b514e339bb7f93
MD5 ea07d23783a1bb802928b10986d8f5af
BLAKE2b-256 8e1802c65c75835578e4ebd9a759807f1902cba5fb232bc2dcb198698a46bfea

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page