Aigon GitHub

Spec-driven development for AI teams

Spec-driven AI development.
Your context, committed to code —
with any agent, or all of them at once.

Aigon structures the full product lifecycle — research, feature delivery, and user feedback — as specs and logs committed directly to your repository. Every decision is traceable, every implementation is reviewable, and your project memory stays portable across tools.

Start in 5 minutes Why teams use Aigon
  • Arena mode: multiple agents implement the same feature in parallel — you pick the winner
  • Specs, logs, and research findings in Git — searchable, portable, permanent
  • Works with Claude, Gemini, Cursor, and Codex — swap freely or run them head-to-head
  • No required SaaS account, plain files in Git, no proprietary formats

The problem

AI agents multiply output fast, but coordination breaks down even faster.

Terminal tabs everywhere

Parallel agents generate momentum, but tracking what each one did and why becomes manual overhead.

Decisions get lost

Without spec-linked workflows, merge decisions and implementation tradeoffs disappear into chat history.

No clean comparison step

Teams rarely compare multiple implementations side-by-side before merging the best approach.

Feedback loops stay disconnected

User feedback, research, and implementation often live in separate tools with no shared lifecycle.

Core features

Everything needed to run a disciplined multi-agent engineering loop.

Research Arena

Run parallel research before coding

Spin up several agents on one topic and compare findings before writing a single line of product code.

aigon research-setup 05 cc gg cx

Feature Workflow

Spec to implementation with traceability

Move features through clear folders and logs so project state is visible from the file tree.

aigon feature-implement 01

Arena Mode

Compare multiple implementations

Create separate worktrees for each agent, then evaluate alternatives and merge the winner.

aigon feature-setup 01 cc gg cx cu

Feedback Loop

Capture and triage real user input

Convert incoming feedback into structured tasks and link outcomes back to specs and decisions.

aigon feedback-triage 14

Why Aigon

Differentiators that compound over time, not just faster first drafts.

Adapts to Your Stack

Workflow fits web apps, APIs, mobile apps, and libraries

Aigon detects project type and adjusts templates, test guidance, and dev defaults.

web • api • ios • android • library

Dev Proxy

Readable URLs for parallel agent servers

Avoid port collisions with URLs like cc-119.myapp.test when running multiple worktrees.

aigon dev-server start

Hooks

Integrate your own infrastructure automation

Run pre/post command hooks for database branches, service setup, and environment orchestration.

aigon hooks list

Evaluation Rubrics

Score implementations before merging

Generate structured comparisons for spec fit, quality, and maintainability before choosing a winner.

aigon feature-eval 07

Board View

See pipeline state from the terminal instantly

Visualize active and queued work with mode indicators for branch, worktree, and arena execution.

aigon board --list --active

Cost + Control

Free CLI with direct provider usage

Use your own Anthropic, Google, OpenAI, or Cursor setup with no workflow-level lock-in.

aigon install-agent cc gg cx cu

Project Immortality

Project memory that outlasts the session.

Most AI development happens in ephemeral chat tabs that vanish when the browser closes. Aigon treats project context as a first-class citizen of your repository.

Zero Context Decay

Decisions, trade-offs, and research findings are committed as Markdown. Your project's "Why" stays searchable and versioned forever.

Vendor-Independent Memory

Switching from Claude to Gemini? Your history doesn't stay behind in a proprietary cloud. It lives in your Git history, portable and private.

Auditable at Any Scale

Aigon's implementation logs provide a play-by-play of every AI-led change, making code reviews fast and forensic even months later.

Repository Context Vault
feat: add auth flow
log: decision to use jwt
spec: 07-oauth-strategy
eval: cx selected (concise)
done: merged at 100% cov
Verified & Committed to Git

The big picture

Aigon keeps research, delivery, and feedback in one continuous system.

  1. Research

    Explore alternatives, constraints, and market context with multiple agents.

  2. Features

    Convert winning ideas into specs that define scope, intent, and success criteria.

  3. Code Review

    Evaluate implementations, merge the strongest option, and keep rationale in logs.

  4. Feedback

    Capture user signals and route them back into research and planning.

How it works

Core feature workflow in four explicit steps.

01

Define

aigon feature-create "jwt-auth"
aigon feature-prioritise jwt-auth

02

Set up mode

# solo
aigon feature-setup 07
# arena
aigon feature-setup 07 cc gg cx

03

Implement

aigon worktree-open 07 --all
aigon feature-implement 07

04

Evaluate and merge

aigon feature-eval 07
aigon feature-done 07 cx
aigon feature-cleanup 07

In practice

See it in action.

Documentation

Install in minutes, then run your first end-to-end loop.

git clone https://github.com/jayvee/aigon.git
cd aigon
npm install
npm link
cd /path/to/your/project
aigon init
aigon install-agent cc gg cx cu
aigon feature-now "dark-mode"

Workflow Guide

Research, specs, implementation, evaluation, and completion flow.

CLI README

Install instructions, command reference, and real examples.

Tool Comparisons

Where Aigon is stronger, where it is weaker, and how to combine tools.

Tech & philosophy

Open source, git-native, and intentionally simple.

Aigon is built for teams who want disciplined AI-assisted engineering, not opaque automation.

  • Open SourceMIT licensed, no paid-tier lockouts.
  • Repo-Native ContextSpecs, logs, and evaluations stay as plain Markdown in your repository.
  • Agent-AgnosticWorks with whichever coding agents your team chooses.
  • Adapts to Your StackWorkflow templates and defaults adjust for web apps, APIs, iOS, Android, and libraries.

Community

Help shape the next generation of collaborative AI development.

Contribute specs, improve workflows, and share real-world patterns for running multi-agent engineering teams effectively.

Star on GitHub Install guide