# withkynam/vibecode-pro-max-kit

Your AI forgets. This remembers. Spec-driven coding harness for vibecoders, product owners, CEOs and real builders — self-improving context memory, 15 agents, 33 skills working with /goal, agent-team, & workflow on autopilot loops with 0 need for human gate. Kills context rot, ships features, not spaghetti. Claude Code & Codex. Any stack

Repository: https://github.com/withkynam/vibecode-pro-max-kit
Canonical: https://ross.abutalabs.com/products/vibecode-pro-max-kit
Language: JavaScript
License: MIT
License Family: permissive
Topics: agentic, ai-agents, ai-coding-assistant, ai-development, ai-workflow, anthropic, claude, claude-code, cli-tools, code-quality, codex, coding-agents, cursor, developer-tools, llm, openai, prompt-engineering, typescript, vibe-coding, vibecoding
Last push: 2026-06-21T08:31:44+00:00

## Health v2 (maintenance only)
Score: 72/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 88, release rhythm 89, longevity 7
- inputs: {"age_days": 98, "days_push": 73, "days_rel": 73, "gap_med": 0.5, "n_releases_24m": 9}
- flags: young
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1096, forks 229 (observed 2026-08-28T04:03:34.569977+00:00)

## What it is
A spec-driven coding harness that gives AI coding agents (Claude Code, Codex, Cursor, etc.) a plan-first workflow with gated phases, self-healing check loops, and autopilot runs. It installs into any project via a one-line curl command and provides 15 agents, 33 skills, and persistent context memory to prevent context rot.

## Use cases
- stop my AI coding agent from jumping straight to code without a plan
- run Claude Code on autopilot until a feature is done
- prevent context rot in long AI coding sessions
- add a spec-driven workflow to my AI-assisted development
- make my AI agent remember project context across sessions
- coordinate multiple AI coding agents on a task
- validate feasibility before an AI agent commits to a design

## When to choose
- you use AI coding agents like Claude Code, Codex, or Cursor and want structured, plan-first workflows
- you want hands-free autopilot runs with self-healing plan/test loops
- your AI agent loses context or produces spaghetti code on larger features
- you want a stack-agnostic harness that drops into any existing project

## When to avoid
- you prefer lightweight, unstructured AI coding without gated phases or ceremony
- you don't use AI coding agents in your development workflow
- you need a fully human-gated review process rather than autopilot loops
- you want a standalone application rather than a drop-in project harness

## Facets
- artifact type: framework
- maturity: active
- function: agent-framework, prompt-engineering, workflow-automation, developer-tools, cli
- domain: developer-tools, artificial-intelligence, large-language-models
- platform: cli, cross-platform
- tags: vibe-coding, claude-code, codex, cursor, spec-driven-development, context-memory, autopilot, ai-coding-agents, ripd-5-workflow, self-healing-loops, automation, ai-agents, nodejs

## Member repositories
- withkynam/vibecode-pro-max-kit (main) score 72

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:34.569977+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T06:47:12.813483+00:00, confidence not recorded.
  - readme: https://github.com/withkynam/vibecode-pro-max-kit (fetched 2026-08-28T04:03:34.569977+00:00, sha afa4a60d1445)
- Data as of 2026-08-30T08:39:29.467469+00:00.