Skip to main content

chico

chico logo


CI PyPI - Python Version PyPI - License

chico is an agent-native configuration control plane — a deterministic reconciliation engine for distributed configuration state, designed for both humans and agents.

📖 Full documentation

✨ Why chico?

  • Keep your AI agent configuration in a Git repository and sync it automatically
  • Plan/apply lifecycle — preview every change before it happens
  • Automatic scheduling via cron (macOS/Linux) or Task Scheduler (Windows)
  • Structured JSON logging for full auditability
  • Works with any GitHub repository, public or private

⚡ Quick Start

Initialize chico with a GitHub source in one command:

chico-ai init \
  --source github \
  --repo Chico-inc/agents-patterns \
  --path patterns \
  --source-prefix patterns/ \
  --target kiro \
  --branch master

Then sync:

chico-ai sync

That's it — chico fetches every file under patterns/ from the repository and applies it to ~/.kiro/.

✅ Features

  • Sync configuration files from GitHub repositories to your local agent environment
  • Plan/apply lifecycle — see exactly what will change before committing
  • chico-ai sync — plan and apply in a single step
  • Automatic scheduling — chico-ai schedule install --every 30 sets up a recurring sync
  • Recursive directory traversal — syncs nested folder structures automatically
  • UTF-8 and Latin-1 encoding support for international content
  • 100% test coverage

🔧 Requirements

Python
3.11+

💽 Installation

pip install chico-ai

Or with uv:

uv tool install chico-ai

Or run without installing:

uvx chico-ai --help

📦 Usage

Initialize

chico-ai init \
  --source github \
  --repo Chico-inc/agents-patterns \
  --path patterns \
  --source-prefix patterns/ \
  --target kiro \
  --branch master

Creates ~/.chico/config.yaml pre-populated and ready to use. For an empty config to edit manually:

chico-ai init

Plan

Preview what would change without writing anything to disk:

chico-ai plan

Apply

Apply the changes computed by plan:

chico-ai apply

Sync

Plan and apply in one step:

chico-ai sync

Schedule

Install a recurring sync (every 30 minutes by default):

chico-ai schedule install
chico-ai schedule install --every 15
chico-ai schedule status
chico-ai schedule uninstall

Environment variables

Variable Description
GITHUB_TOKEN GitHub personal access token for private repositories

⚙️ Configuration

chico reads ~/.chico/config.yaml:

sources:
  - name: agents-patterns
    type: github
    repo: Chico-inc/agents-patterns
    branch: master
    path: patterns
    source_prefix: patterns/
    target: kiro

providers:
  - name: kiro
    type: kiro
    level: global
Field Description
repo GitHub repository in owner/repo format
path Directory inside the repo to sync
source_prefix Prefix stripped from source paths when mapping to local files. Defaults to path
branch Branch to read from
target Provider name this source feeds into

👩🏼‍⚖️ License

This project is licensed under the terms of the MIT license.

Metadata

Release files for chico-ai 1.0.1

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for chico-ai 1.0.1
File Size Uploaded Provenance Actions
chico_ai-1.0.1.tar.gz 1.7 MB With provenance Details for chico_ai-1.0.1.tar.gz

Built distribution (wheel)

Table of built distributions (wheels) for chico-ai 1.0.1
File Interpreter ABI Platform Actions
chico_ai-1.0.1-py3-none-any.whl Python 3 none any Details for chico_ai-1.0.1-py3-none-any.whl

Total release size: 1.7 MB

Release files / chico_ai-1.0.1.tar.gz

Download URL chico_ai-1.0.1.tar.gz
Size 1.7 MB
Tags Source
SHA-256 checksum
How to use checksums
478e630a548c52e3e3cbcc47b6408d8ed38fd9c1eb70c4ab500d43b4f79b1bf6
BLAKE2b-256 checksum
How to use checksums
7929d5d6e6359a5cb9b54998755491ce21f1a2aa2fa74277a8b3ebf9bfbd8baf
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/6.1.0 CPython/3.13.12

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Apr 25, 2026.

Transparency log

Release files / chico_ai-1.0.1-py3-none-any.whl

Download URL chico_ai-1.0.1-py3-none-any.whl
Size 40.3 kB
Tags Python 3
SHA-256 checksum
How to use checksums
bb941bba1707ca4655a2d45505e876019031908fd96ac4d6429a15a08e5a7842
BLAKE2b-256 checksum
How to use checksums
b18c11dea389bed8564e3d5c9ce11de3c52feffe0e0ea2610b3e7a5856e59410
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/6.1.0 CPython/3.13.12

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Apr 25, 2026.

Transparency log

Security for chico-ai 1.0.1

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

Full provenance

All 2 files in this release have been uploaded with provenance metadata.

Select from 2 files

Attestation for chico_ai-1.0.1.tar.gz

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Apr 25, 2026.

Transparency log

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page