Analysis updated 2026-05-18
Delegate a feature request to a coordinator that spawns researcher, architect, developer, and tester roles automatically.
Run a security-focused review of your codebase using the dedicated security role.
Track which coding strategies work over time so the team avoids repeating past mistakes.
Review team retrospectives to see how different agent roles collaborated on a task.
| xalbert1d/ainous-team | anthonyhann/knowledge-wiki | baiyuetribe/test-heroku | |
|---|---|---|---|
| Stars | 1 | 1 | 1 |
| Language | Shell | Shell | Shell |
| Last pushed | — | — | 2021-06-30 |
| Maintenance | — | — | Dormant |
| Setup difficulty | moderate | moderate | hard |
| Complexity | 4/5 | 3/5 | 1/5 |
| Audience | developer | developer | developer |
Figures from each repo's GitHub metadata at analysis time.
Requires the Claude Code CLI, Python 3.6+, bash 3.2+, and git already installed.
Ainous Team is a plugin for Claude Code, the command-line coding assistant, that turns it into a persistent team of specialized agents instead of one general assistant. It sets up 12 named roles, such as coordinator, developer, architect, tester, researcher, writer, security, and authority, each with its own playbook and 57 shared skills split between orchestration and domain expertise. The idea is that these roles remember what worked and what did not across sessions, so strategies that succeed get reinforced and ones that fail get retired over time. After installing the plugin through Claude Code's plugin marketplace system, you run a setup command that walks you through picking an operating mode and creates starter files for all 12 roles on your machine. There are two modes: a coordinator-as-default mode, where Claude automatically plans a task, hands pieces of it to the right role, and combines the results, so you can just describe what you want in plain language, and an agent mode, where you manually call on specific roles yourself, like asking the developer role to fix a bug or the security role to scan code. When the coordinator handles a task, it chooses an approach based on what kind of work it is (a quick bugfix versus a full feature, for example), spawns the needed teammates with context and instructions, and checks their work against verification gates between steps, such as requiring tests to pass before moving on. It also holds a review after each task to look at how the roles worked together and to pick up on any corrections you made by hand. The project is built on top of several published ideas about multi-agent coordination, including shared team memory, feedback from user corrections, and periodic team retrospectives. It requires the Claude Code CLI, Python 3.6 or newer, a recent version of bash, and git for tracking what the team has learned. This is aimed at developers already using Claude Code who want a more structured, memory-aware way to delegate coding tasks. The full README is longer than what was shown.
A Claude Code plugin that adds a 12-role team of specialized coding agents with shared memory that improves over time.
Mainly Shell. The stack also includes Shell, Python, Bash.
Setup difficulty is rated moderate, with roughly 30min to a first successful run.
Mainly developer.
This repo across BitVibe Labs
Verify against the repo before relying on details.