← Open Source
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.

AI EngineeringGive agent knowledgeBuild agent workflow (SDK)JavaScript
Open on GitHub
Momentum
+0stars in 24 hours0.0%
1.15k
Stars
234
Forks
+7
This week
1
Contributors
Created 2026-05-27 · Updated 2026-10-16 · #11387 today
Top developers

withkynam/vibecode-pro-max-kit is ranked 11,387 with 1,152 stars.

Same-category comparison

withkynam/vibecode-pro-max-kit is ranked 11,387 among these 8 peers; JuliusBrussee/cavekit is ranked 11,382.

Same-category comparison
NameRankMetrics
easystats/performance11,354
Language:
R
Stars:
1,159
Forks:
107
udecode/dotai11,365
Language:
JavaScript
Stars:
1,157
Forks:
82
Description:
Skills for agents.
davis7dotsh/better-context11,367
Language:
TypeScript
Stars:
1,156
Forks:
80
Description:
A better way to get up to date context on libraries/technologies in your projects.
JuliusBrussee/cavekit11,382
Stars:
1,152
Forks:
90
hexabot-ai/Hexabot11,392
Language:
TypeScript
Stars:
1,151
Forks:
239
Description:
Hexabot v3 is an AI workflow automation platform, combining workflows, actions, agents, and conversational channels in one runtime.
agent-topia/evolving_personality11,406
Language:
Python
Stars:
1,147
Forks:
104
Description:
Dynamic MBTI Personality Simulation for LLM Agents via Carl Jung's Theory. A framework that enables LLM agents' MBTI personalities to naturally evolve and grow through interaction.
LiuMengxuan04/MiniCode11,412
Language:
TypeScript
Stars:
1,146
Forks:
128
Description:
A lightweight terminal coding assistant with Claude Code-like workflow, tool loop, and TUI architecture, built for learning and experimentation. Multi-language support: TypeScript , Python and Rust implementations available now.
RUC-NLPIR/DeepAgent11,422
Language:
Python
Stars:
1,144
Forks:
144
Description:
[WWW‘26 Oral🔥] DeepAgent: A General Reasoning Agent with Scalable Toolsets.
Key parameters and specifications
Key parameters and specifications
ParameterValue
LanguageJavaScript
CategoryAI Engineering
SubcategoryGive agent knowledge, Build agent workflow (SDK)
KeywordsAgent society, Knowledge base, Memory management, Spec-driven development
Stars1,152
Forks234
Contributors1
Created date2026-05-27
Updated date2026-10-16
Stars in 1 day0
Stars in 7 days7
Rank11,387
Previous rank4,110
Rank change-7,277
7-day stars rank4,765
Previous 7-day stars rank4,791
7-day stars rank change26
Total stars rank10,025
Previous total stars rank10,006
Total stars rank change-19
README summary

* 📦 One-command install One line drops it into any project. returning users and never overwrites your files. 🧭 RIPER-5 plan-first workflow 7 gated phases (Research → Spec → Innovate → Plan → Validate → Execute → Update-Process) stop the agent from jumping straight to code. 🚀 Autopilot mode (quick / fast / full) Start a hands-free run at any phase with a single phrase. Three lanes match the ceremony to the risk. 🔍 vc-autoresearch A reusable find-gaps → fix → repeat loop you can point at plans

, tests, specs, docs, or evals. 🧪 Feasibility probes Test-before-you-build verdicts (VIABLE / NOT-VIABLE) before the agent commits to any design approach. 🎛️ Smart strategy picker Before each phase it weighs one agent vs. 🧮 Smart model use The expensive model only writes code; the cheaper model does everything else. 🤔 Intent clarification When a request is vague, the agent asks a few sharp questions up front instead of guessing and building the wrong thing. 🏗️ Phase programs Large projects are split into

independent phases with quality gates between them, so big work doesn't fall apart. 🧠 Never loses its place Progress notes are written to disk every phase, so a run survives a memory reset and picks up exactly where it left off. 📚 Self-improving project memory It learns your codebase on setup and keeps its own shared notes current after every feature ships, so docs never go stale. ⚡ Quick Fix + Fast Mode Light lanes for small changes skip the heavy ceremony, so

a one-line fix stays a one-line fix. 🤖 15 agents · 33 skills · 10 hooks A full team of specialized agents, reusable skills, and safety hooks, all wired together out of the box. 🎯 Always checks your intent Every later phase measures back against your SPEC: is what we're building actually what you asked for? The simplest, most flexible, team-friendly coding kit for Works across any tech stack, any language, any project Not just for show. When you run , agents

scan your codebase, detect your stack, and build project-specific knowledge groups that every skill reads before it works. This one adapts to any combination above and builds up knowledge as you ship. js ≥ 22, git, bash (macOS / Linux / WSL / **Git Bash**; on Alpine: ). Both work out of the box: the installer detects Windows shells and, when symlinks aren't permitted, automatically falls back to copying (install still completes). For true symlinks (so Codex auto-reflects changes), enable Developer Mode. **There

is only one command, and it works for everyone. It detects whether you are a new or returning user, installs safely without overwriting your files, and then *tells you the exact next thing to say. 🔄 Existing harness (upgrade) Installer detects a prior install and prints: → Open your agent and say vc-update pulls the latest version and, if it finds old-format plans or folders, gives you a ready-to-paste prompt to finish the move with zero data loss

. 💡 **You never have to guess the command. **Codex users:** run (or ) instead of saying it in chat. 📦 What install puts

Frequently asked questions

How many stars and forks are recorded?

withkynam/vibecode-pro-max-kit has 1,152 stars and 234 forks.

What is the repository rank?

withkynam/vibecode-pro-max-kit is ranked 11,387.

What language and category are recorded?

withkynam/vibecode-pro-max-kit has 1,152 stars, uses JavaScript and belongs to AI Engineering.

Which repository is closest in rank?

withkynam/vibecode-pro-max-kit is compared with JuliusBrussee/cavekit, ranked 11,382 with 1,152 stars.

Nearby in the ranking
Similar items