vibecosystem turns Claude Code into a full AI software team — 138 specialized agents that plan, build, review, test, and learn from every mistake. No configuration needed — just install and code.

v2.0: 13 new agents (sast-scanner, mutation-tester, graph-analyst, mcp-manager, community-manager, benchmark, dependency-auditor, api-designer, incident-responder, data-modeler, test-architect, release-engineer, documentation-architect) + 23 new skills (SAST, compliance, product, marketing, MCP) + 4 new hooks + Agent Monitoring Dashboard + GitHub Actions CI/CD + MCP Auto-Discovery. See UPGRADING.md for details.

v2.1: 7 new skills (minimax-pdf, minimax-docx, minimax-xlsx, pptx-generator, frontend-dev, fullstack-dev, clone-website) + 2 new agents (document-generator, website-cloner). Document generation, pixel-perfect website cloning, and enhanced frontend/fullstack patterns.

v2.1.1: 7 new skills from oh-my-claudecode (smart-model-routing, deep-interview, agent-benchmark, visual-verdict, ai-slop-cleaner, factcheck-guard, notepad-system) + 1 new rule (commit-trailers).

v2.2: 5 features from Claude Code source — Agent Memory (persistent per-agent memory), Magic Docs (auto-updating docs), Dream Consolidation (cross-session memory cleanup), Smart Recall (frontmatter-based memory scoring), Plugin Toggle (hook enable/disable CLI). +7 hooks, skill references for 21 agents.

v2.2.1: Monetization stack — 1 new agent (monetization-expert), 2 new skills (paywall-optimizer, codex-orchestration), 3 updated skills (revenuecat-patterns, paywall-strategy, subscription-pricing). AI-powered paywall optimization with 14-category benchmarks, RevenueCat SDK patterns, Codex + Claude Code orchestration.

v2.3: vibeco CLI tool (stats, doctor, profiles, dashboard), 6 preset profiles for token savings, one-liner install (curl | bash).

v2.4: Terminal HUD (real-time statusline), prompt auto-improver (enriches vague prompts with context), persistent planning system (PLAN.md/PROGRESS.md/CONTEXT.md for 96.7% task completion). Competitive gap closure from analysis of 20+ ecosystem repos.

v3.0: npx vibecosystem init npm installer, plugin.json for official plugin ecosystem, worktree isolation on 60 producer agents, multi-LLM model routing (Haiku/Sonnet/Opus tiers), knowledge graph integration (6-71x token savings), dashboard v2 with token/cost tracking.

The Problem

Claude Code is powerful, but it's one assistant. You prompt, it responds, you review. For complex projects you need a planner, a reviewer, a security auditor, a tester — and you end up being all of them yourself.

The Solution

vibecosystem is a complete Claude Code ecosystem that creates a self-organizing AI team:

1. 138 agents — specialized roles from frontend-dev to security-analyst
2. 296 skills — reusable knowledge from TDD workflows to Kubernetes patterns
3. 74 hooks — TypeScript sensors that observe, filter, and inject context
4. 20 rules — behavioral guidelines that shape every agent's output
5. Self-learning — every error becomes a rule, automatically

After setup, you say "build a feature" and 20+ agents coordinate across 5 phases.

Quick Start

npm (recommended)

npx vibecosystem init

One-liner

curl -fsSL https://raw.githubusercontent.com/vibeeval/vibecosystem/main/install-remote.sh | bash

Manual

git clone https://github.com/vibeeval/vibecosystem.git
cd vibecosystem
./install.sh

That's it. Use Claude Code normally. The team activates.

vibeco CLI

After install, the vibeco command is available:

vibeco stats                          # ecosystem statistics
vibeco list agents --search security  # browse components
vibeco profile frontend               # switch profile (saves tokens)
vibeco doctor                         # health check
vibeco dashboard                      # start monitoring UI
vibeco update                         # pull latest & reinstall

Profiles

Save tokens by loading only what you need:

Honest note on smart: it does not disable any agent or skill — capability is identical to all. The difference is session-start token cost: smart expects reduced context-injection budgets (via the env section of ~/.claude/settings.json), cutting startup overhead roughly 30-35% against vanilla all.

vibeco profile frontend  # switch to frontend profile
vibeco profile all       # back to everything

How It Works

YOU SAY SOMETHING                VIBECOSYSTEM ACTIVATES              RESULT
┌──────────────┐                 ┌──────────────────────┐            ┌──────────┐
│ "add a new   │──→ Intent ──→  │ Phase 1: scout +     │──→ Code   │ Feature  │
│  feature"    │   Classifier   │   architect plan     │   Written │ built,   │
│              │                 │ Phase 2: backend-dev │   Tested  │ reviewed,│
│              │                 │   + frontend-dev     │   Reviewed│ tested,  │
│              │                 │ Phase 3: code-review │           │ merged   │
│              │                 │   + security-review  │           │          │
│              │                 │ Phase 4: verifier    │           │          │
│              │                 │ Phase 5: self-learner│           │          │
└──────────────┘                 └──────────────────────┘            └──────────┘

Hooks are sensors — they observe every tool call and inject relevant context:

"fix the bug"       → compiler-in-loop + error-broadcast      ~2,400 tok
"add api endpoint"  → edit-context + signature-helper + arch   ~3,100 tok
"explain this code" → (nothing extra)                          ~800 tok

Agents are muscles — each one specialized for a specific job:

GraphQL API      → graphql-expert   (backup: backend-dev)
Kubernetes       → kubernetes-expert (backup: devops)
DDD modeling     → ddd-expert       (backup: architect)
Bug reproduction → replay           (backup: sleuth)
... 70 more routing rules

Self-Learning Pipeline turns mistakes into permanent knowledge:

Error happens → passive-learner captures pattern (+ project tag)
→ consolidator groups & counts (per-project + global)
→ confidence >= 5 → auto-inject into context
→ 2+ projects, 5+ total → cross-project promotion
→ 10x repeat → permanent .md rule file

No manual intervention. The system writes its own rules — and shares them across projects.

What's New in v2.0

• SAST Security Scanner — static analysis agent + hook for automated vulnerability detection
• Agent Monitoring Dashboard — real-time web UI for agent activity and performance
• MCP Auto-Discovery — automatic MCP server recommendations based on project type
• Changelog Automation — automatic changelog generation at session end
• Compliance Skills — SOC2, GDPR, HIPAA compliance checking
• Product & Marketing Skills — PRD writer, analytics setup, growth playbooks
• GitHub Actions CI/CD — automated PR review + issue fix workflows
• Mutation Testing — test quality measurement via mutation analysis
• Code Knowledge Graph — codebase structure analysis with graph-analyst

Core Features

Agent Swarm

Say "add a new feature" and 20+ agents activate across 5 phases.

Phase 1 (Discovery):    scout + architect + project-manager
Phase 2 (Development):  backend-dev + frontend-dev + devops + specialists
Phase 3 (Review):       code-reviewer + security-reviewer + qa-engineer
Phase 4 (QA Loop):      verifier + tdd-guide (max 3 retry → escalate)
Phase 5 (Final):        self-learner + technical-writer

Self-Learning Pipeline

Every error becomes a rule. Automatically.

Dev-QA Loop

Every task goes through a quality gate:

Developer implements → code-reviewer + verifier check
→ PASS → next task
→ FAIL → feedback to developer, retry (max 3)
→ 3x FAIL → escalate (reassign / decompose / defer)

Cross-Project Learning

Patterns learned in one project automatically benefit all your projects.

Project A: add-error-handling (3x) ─┐
                                     ├→ 2+ projects, 5+ total → GLOBAL
Project B: add-error-handling (4x) ─┘
                                     ↓
Next session in ANY project → "add-error-handling" injected as global pattern

Each project gets its own pattern store. When the same pattern appears in 2+ projects with 5+ total occurrences, it's promoted to a global pattern that benefits every project — even brand new ones.

node ~/.claude/hooks/dist/instinct-cli.mjs portfolio      # All projects
node ~/.claude/hooks/dist/instinct-cli.mjs global          # Global patterns
node ~/.claude/hooks/dist/instinct-cli.mjs project <name>  # Project detail
node ~/.claude/hooks/dist/instinct-cli.mjs stats           # Statistics

Canavar Cross-Training

When one agent makes a mistake, the entire team learns from it.

Agent error → error-ledger.jsonl → skill-matrix.json
→ All agents get the lesson at session start
→ Team-wide error prevention

Adaptive Hook Loading

74 hooks exist but they don't all run at once. Intent determines which hooks fire.

Architecture

┌─────────────────────────────────────────────────────────┐
│                    Claude Code                          │
│                                                         │
│  ┌──────────┐  ┌──────────┐  ┌──────────┐              │
│  │  Hooks   │  │  Agents  │  │  Skills  │              │
│  │  (74)    │→ │  (138)   │← │  (296)   │              │
│  └────┬─────┘  └────┬─────┘  └──────────┘              │
│       │              │                                   │
│       ▼              ▼                                   │
│  ┌──────────┐  ┌──────────┐                              │
│  │  Rules   │  │  Memory  │                              │
│  │  (20)    │  │ (PgSQL)  │                              │
│  └──────────┘  └──────────┘                              │
│                                                         │
│  ┌──────────────────────────────────────┐                │
│  │  Self-Learning Pipeline             │                │
│  │  instincts → consolidate → rules    │                │
│  │  + cross-project promotion          │                │
│  └──────────────────────────────────────┘                │
│                                                         │
│  ┌──────────────────────────────────────┐                │
│  │  Canavar Cross-Training             │                │
│  │  error-ledger → skill-matrix → team │                │
│  └──────────────────────────────────────┘                │
└─────────────────────────────────────────────────────────┘

Agent Categories

Comparison

What's Included

Tech Stack

Philosophy

hooks are sensors. observe, filter, signal.
agents are muscles. build, produce, fix.
the bridge between them: context injection.
no direct RPC. no message passing. by design.
implicit coordination through context.

Data & Privacy

• All data stays on your machine (~/.claude/)
• No network requests, no telemetry, no cloud sync
• Self-learned rules go to ~/.claude/rules/
• Hooks run locally via Claude Code's native hook system

Multi-CLI Support

vibecosystem works with multiple AI coding tools:

# For Cursor IDE users:
./install-cursor.sh /path/to/your/project

# For Codex CLI users:
./install-codex.sh

See docs/codex-setup.md for Codex CLI setup, or copy .cursor/rules/ into any Cursor project.

Inspired By

vibecosystem stands on the shoulders of great open-source projects:

• Shannon by KeygraphHQ — Result<T,E> pattern, pentest pipeline, comment philosophy
• UI UX Pro Max by nextlevelbuilder — Named UX rules, UI style catalog, design token architecture
• Game Studios by Donchitos — Context resilience, incremental writing, gate-check system
• Skill Gateway by buraksu42 — Invisible skill routing, external catalog, one-question rule
• Pyxel by kitao — Retro game engine patterns, pixel art constraints, MML audio
• copilot-orchestra by ShepAlderson -- Phase-gated commits, plan documentation trail, 90% confidence threshold
• RevenueCat -- Subscription infrastructure, category benchmarks, paywall patterns
• Trail of Bits Skills by trailofbits -- Security audit patterns, variant analysis, false positive verification, sharp edges detection

Contributing

Contributions welcome! Areas where help is needed:

• More agent definitions — specialized roles for your domain
• More skill patterns — framework-specific knowledge (Rails, Flutter, etc.)
• Better hooks — new sensors, smarter context injection
• Documentation — tutorials, guides, examples
• Translations — improve existing or add new languages

Türkçe

Nedir?

vibecosystem, Claude Code'u tam donanımlı bir yapay zeka yazılım ekibine dönüştürür. Sadece tek bir asistan değil — planlayan, geliştiren, kod incelemesi (review) yapan, test eden ve yaptığı her hatadan öğrenen 138 uzman ajandan (agent) oluşan bir ekip.

Özel bir model yok. Özel bir API yok. Sadece Claude Code'un hook + agent + rules sistemi sonuna kadar kullanılmış durumda.

Hızlı Başlangıç

git clone https://github.com/vibeeval/vibecosystem.git
cd vibecosystem
./install.sh

Nasıl Çalışır?

1. Hook'lar sensördür — gözlemler, filtreler ve işaret eder.
2. Agent'lar kas gibidir — çalışır, üretir ve düzeltir.
3. Aralarındaki köprü: Context (bağlam) enjeksiyonudur.
4. Doğrudan RPC yoktur — bu kasıtlı bir mimari tercihtir.
5. Context üzerinden örtük (implicit) koordinasyon sağlanır.

Felsefe

Kullanıcının hiçbir şey hatırlamasına gerek yoktur.
Her şey otomatiktir.

License

MIT