Skip to main content

AI-native cron task runner for per-project scheduled prompts and commands.

Project description

kage 影 - Autonomous AI Project Agent

kage hero

English | 日本語

kage is an autonomous execution layer for project-specific AI agents. It schedules AI-driven tasks via cron, maintains state across runs using a persistent memory system, and allows for layered configuration.

Features

  • Autonomous Agent Logic: Automatically decomposes tasks into GFM checklists and tracks progress.
  • Persistent Memory: Stores task state in .kage/memory/ to maintain context across cron cycles.
  • Markdown-First: Define tasks using simple Markdown files with YAML front matter.
  • Layered System Prompts: Customize AI behavior globally or per-project using system_prompt.md.
  • Flexible Configuration: 4-layer configuration: .kage/config.local.toml > .kage/config.toml > ~/.kage/config.toml > defaults.
  • Web Dashboard: Monitor execution history and real-time logs at http://localhost:8484.

Installation

curl -sSL https://raw.githubusercontent.com/igtm/kage/main/install.sh | bash

Or via PyPI:

pip install kage-ai

Quick Start

  1. Onboard: kage onboard (Setup global dirs and daemon)
  2. Configure: Set default_ai_engine = "claude" in ~/.kage/config.toml.
  3. Initialize Project: kage init in your repo.
  4. Define Task: Edit .kage/tasks/daily_audit.md.

Task Example (.kage/tasks/audit.md)

---
name: Project Auditor
cron: "0 9 * * *"
provider: gemini
---

# Task: Continuous Health Check
Analyze the current codebase for architectural drifts.
On the first run, create a Todo list in the Memory.
In subsequent runs, pick one item and provide a detailed report.

Commands

  • kage onboard: Global setup.
  • kage init: Initialize kage in the current directory.
  • kage run: Manually trigger all scheduled tasks.
  • kage ui: Launch web dashboard.
  • kage task list: List all tasks.
  • kage task run <name>: Run a specific task immediately.
  • kage doctor: Diagnose configuration and environment health.

Configuration

  • ~/.kage/config.toml: Global settings.
  • .kage/config.toml: Project-shared settings.
  • .kage/config.local.toml: Local overrides (usually git-ignored).
  • ~/.kage/system_prompt.md: Global system prompt.
  • .kage/system_prompt.md: Project-specific system prompt.

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

kage_ai-0.1.2.tar.gz (1.9 MB view details)

Uploaded Source

Built Distribution

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

kage_ai-0.1.2-py3-none-any.whl (33.9 kB view details)

Uploaded Python 3

File details

Details for the file kage_ai-0.1.2.tar.gz.

File metadata

  • Download URL: kage_ai-0.1.2.tar.gz
  • Upload date:
  • Size: 1.9 MB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: uv/0.9.18 {"installer":{"name":"uv","version":"0.9.18","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Manjaro Linux","version":null,"id":null,"libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}

File hashes

Hashes for kage_ai-0.1.2.tar.gz
Algorithm Hash digest
SHA256 66954eb345ee8733a4e384237cdd0d7e18344210fba73be6c85c7284bbcb0583
MD5 0478875bd6ed56e11fe8b32259ed4096
BLAKE2b-256 0e78f131cc711d643f296cd6c7208fb5c01daed16ed04d010af1507e2f548343

See more details on using hashes here.

File details

Details for the file kage_ai-0.1.2-py3-none-any.whl.

File metadata

  • Download URL: kage_ai-0.1.2-py3-none-any.whl
  • Upload date:
  • Size: 33.9 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: uv/0.9.18 {"installer":{"name":"uv","version":"0.9.18","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Manjaro Linux","version":null,"id":null,"libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}

File hashes

Hashes for kage_ai-0.1.2-py3-none-any.whl
Algorithm Hash digest
SHA256 2493472eb83d50b4895024870ec81b2f418d05d318b27d502f0eb55ea2c10ebe
MD5 f650ed0e88ea93b1441bb2cc4318ee96
BLAKE2b-256 7a7a7147c0aecf6034b2d7d06a649a2ac2ebffb294b1aa31727ac90a050fd52e

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