GitHub - bkawa-bot/planet-maiko: A local dev tool where your agents are weird alien dogs. Would you let them in? · GitHub

Skip to content

Navigation Menu

Toggle navigation

Sign in

Appearance settings

PlatformAI CODE CREATIONGitHub CopilotWrite better code with AIGitHub SparkBuild and deploy intelligent appsGitHub ModelsManage and compare promptsMCP RegistryNewIntegrate external toolsDEVELOPER WORKFLOWSActionsAutomate any workflowCodespacesInstant dev environmentsIssuesPlan and track workCode ReviewManage code changesAPPLICATION SECURITYGitHub Advanced SecurityFind and fix vulnerabilitiesCode securitySecure your code as you buildSecret protectionStop leaks before they startEXPLOREWhy GitHubDocumentationBlogChangelogMarketplaceView all featuresSolutionsBY COMPANY SIZEEnterprisesSmall and medium teamsStartupsNonprofitsBY USE CASEApp ModernizationDevSecOpsDevOpsCI/CDView all use casesBY INDUSTRYHealthcareFinancial servicesManufacturingGovernmentView all industriesView all solutionsResourcesEXPLORE BY TOPICAISoftware DevelopmentDevOpsSecurityView all topicsEXPLORE BY TYPECustomer storiesEvents & webinarsEbooks & reportsBusiness insightsGitHub SkillsSUPPORT & SERVICESDocumentationCustomer supportCommunity forumTrust centerPartnersView all resourcesOpen SourceCOMMUNITYGitHub SponsorsFund open source developersPROGRAMSSecurity LabMaintainer CommunityAcceleratorGitHub StarsArchive ProgramREPOSITORIESTopicsTrendingCollectionsEnterpriseENTERPRISE SOLUTIONSEnterprise platformAI-powered developer platformAVAILABLE ADD-ONSGitHub Advanced SecurityEnterprise-grade security featuresCopilot for BusinessEnterprise-grade AI featuresPremium SupportEnterprise-grade 24/7 supportPricing

Search or jump to...

Search code, repositories, users, issues, pull requests...

Search

Clear

Search syntax tips

Provide feedback

We read every piece of feedback, and take your input very seriously.

Include my email address so I can be contacted

Cancel

Submit feedback

Saved searches

Use saved searches to filter your results more quickly

Name

Query

To see all available qualifiers, see our documentation.

Cancel

Create saved search

Sign in

Sign up

Appearance settings

Resetting focus

You signed in with another tab or window. Reload to refresh your session.
You signed out in another tab or window. Reload to refresh your session.
You switched accounts on another tab or window. Reload to refresh your session.

Dismiss alert

bkawa-bot

/

planet-maiko

Public

Notifications
You must be signed in to change notification settings

Fork
0

Star
7

Code

Issues
5

Pull requests
3

Actions

Projects

Security and quality
0

Insights

Additional navigation options

Code

Issues

Pull requests

Actions

Projects

Security and quality

Insights

bkawa-bot/planet-maiko

 mainBranchesTagsGo to fileCodeOpen more actions menuFolders and filesNameNameLast commit messageLast commit dateLatest commit History1,085 Commits1,085 Commitsdocsdocs  frontendfrontend  hookshooks  scriptsscripts  src/planet_maikosrc/planet_maiko  teststests  .gitignore.gitignore  BUILD.mdBUILD.md  LICENSELICENSE  MANIFEST.inMANIFEST.in  MakefileMakefile  README.mdREADME.md  SECURITY.mdSECURITY.md  pyproject.tomlpyproject.toml  View all filesRepository files navigationREADMELicenseSecurityPlanet Maiko

These alien dogs want to live in your computer. Would you let them in?

Planet Maiko is a free local dev tool made by 1 dev, for other devs, to make your working day a bit more fun!
What does Planet Maiko do?
All the required agent orchestration work. Automatically kicks off agents, lets them yell at each other (with Maiko as the mediator), agent task lifecycles, context sharing... but also some more interesting features as well such as conflict detection, (experimental) fine-tuning, self-curated shared memory and insights etc...

How is Planet Maiko different from RinkStack, Mazino.ai, or QuatroForce? (I just made all of those up)
A self-maintaining rulebook from your team's PR history
Internal knowledge and specific gotchas get captured automatically, no manual write-ups. When an agent works on something, it only sees the handful of rules that matter for that change. You can keep a pool of hundreds of very specific nits without drowning every prompt.

The dogs confess their own mistakes
When one gets something wrong it writes down what it learned, and the whole pack reads it. Future agents inherit those notes in their preamble, so a gotcha gets discovered once.

Build a plugin for any tool you never want to have to look at again.
Plug in any data you need by building 1 python class. Internal tools, big names, whatever shiny new GSD task manager you are trying this week.
Current integrations:

PagerDuty
Linear
Calendar
GitHub

Stays yours

Runs locally on your laptop. Nothing leaves your machine.
No telemetry, no hosted account, no cloud.

Open source, free forever, no paid tiers or subscriptions.
In-app diff review, agent chat view (no terminal needed), cost-aware model routing, automations, and more!

Most importantly: agents are weird alien dogs, cause why not?

Full feature list
Install
Prerequisites

macOS (or Linux/Windows for development)
Python 3.10+
Node.js 18+
gh CLI
Claude Code (the agent runtime), installed and on your PATH

Setup
git clone https://github.com/bkawa-bot/planet-maiko.git
cd planet-maiko

python3 -m venv .venv && source .venv/bin/activate # Windows: .venv\Scripts\activate
pip install -e .
cd frontend && npm install && cd ..

gh auth login # GitHub: repo discovery + worktrees

SSL errors with Linear or other integrations? pip install --upgrade certifi, then open /Applications/Python\ 3.12/Install\ Certificates.command.

Run
One command:
maiko up
That starts the backend, starts the frontend, and opens
http://localhost:5173 for you. Ctrl+C stops both. First run creates
its own database and config, then shows a setup wizard.
Prefer two terminals? maiko serve (backend, port 8420) and, in
another, cd frontend && npm run dev (frontend, port 5173).

There's an experimental Tauri desktop shell (make app), but it's
currently buggy. The terminal launch above is the supported path.

Full guide (mental model, architecture, plugin system, extending, CLI reference): see docs/GUIDE.md.
About
Planet Maiko is named lovingly after my real dog Maiko.
I made this as one person in my free time for fun, sorry if it is buggy or bad.
Created by Brigitte Kawaguchi

About

A local dev tool where your agents are weird alien dogs. Would you let them in?

bkawa-bot.github.io/planet-maiko/

Topics

python

productivity

mcp

multi-agent

developer-tools

ai-agents

claude

local-first

llm

anthropic

agentic-ai

ai-orchestration

claude-code

Resources

Readme

License

View license

Security policy

Security policy

Uh oh!

There was an error while loading. Please reload this page.

Activity
Stars

7
stars
Watchers

0
watching
Forks

0
forks

Report repository

Releases
No releases published

Packages
0

Uh oh!

There was an error while loading. Please reload this page.

Contributors

Uh oh!

There was an error while loading. Please reload this page.

Languages

Python
63.9%

JavaScript
25.0%

CSS
10.7%

Other
0.4%

Footer

© 2026 GitHub, Inc.

Footer navigation

Terms

Privacy

Security

Status

Community

Docs

Contact

Manage cookies

Do not share my personal information

You can’t perform that action at this time.

Planet Maiko is presented as a free, local development tool created by one developer designed to enhance the developer workflow by incorporating agent orchestration. At its core, the system manages complex agent interactions through a mediator named Maiko, handling agent kickoff, task lifecycles, context sharing, and conflict detection. It introduces advanced features such as self-curated shared memory and experimental fine-tuning mechanisms for the agents.

The system distinguishes itself from existing multi-agent frameworks by focusing on capturing and operationalizing institutional knowledge directly from the development process. It establishes a self-maintaining rulebook derived automatically from the history of pull requests, ensuring that agents operate within specific, relevant constraints for a given change. Furthermore, the system incorporates a mechanism where agents learn from their errors; when an agent makes a mistake, it records what it learned, and future agents inherit these learned notes in their foundational instructions, thereby ensuring that discovered shortcomings are resolved across the team.

Planet Maiko supports integrations with external services, including PagerDuty, Linear, Calendar, and GitHub, allowing it to manage and contextualize agent activities across various developer tools. Architecturally, the tool emphasizes a local-first approach, running entirely on the developer's laptop without requiring telemetry or a hosted cloud account, ensuring data sovereignty and privacy.

The system is designed to be extensible through a plugin architecture, allowing developers to integrate custom data and tools by building Python classes. This capability enables agents to interact with internal tools or other external systems, facilitating flexibility in task management beyond the core orchestration features. The technology stack requires prerequisites such as macOS or Linux/Windows, Python 3.10+, Node.js 18+, and the GitHub command-line interface, alongside the Claude Code runtime.

The operational setup is managed via straightforward commands, initiating both the backend and frontend services locally. This allows for direct interaction with the system, and while an experimental desktop shell exists, the supported path involves launching the services via the terminal. The project demonstrates a strong emphasis on agentic AI concepts, utilizing technologies like LLMs and Anthropic models for agent execution within a collaborative and self-correcting environment to manage complex software development tasks.