Vreko

How It Works

94%
AI Detection
<50ms
Analysis Time
<1s
Context Injection
100%
Local-First

Git tracks what changed. Vreko understands who changed it. And more importantly, why.

The Journey

TimelineWhat Vreko DoesYou Get
Day 1Detects AI tools, catches common risks94% accuracy right out of the box (no tuning needed)
Day 30Learns YOUR codebase patterns”Cursor breaks this auth module”
Day 90Predicts problems proactivelyIssues caught before you notice

Detection

Vreko watches every save. Two systems work together:

Identifies which AI tool is active. Cursor, GitHub Copilot, Claude Code, Windsurf. We track contribution percentage too. 94% accuracy across the common ones (the ones everyone uses).

Scans for common AI-introduced risks:

Risk TypeWhat It Catches
SecretsAPI keys, JWT tokens, database strings
MocksTest data in production code
Phantom depsImports missing from package.json

Automatic Snapshots

Vreko decides when to create snapshots based on context:

TriggerAction
AI tool makes substantial changesSnapshot
Critical files modified (auth, config)Snapshot
Multiple files changed rapidlySnapshot
High-risk patterns detectedSnapshot

Protected by default: Source code, configs, environment files, documentation.

Not protected: .git/, node_modules/, build outputs, binaries.

Sessions

Vreko groups related changes automatically:

Session: "Claude refactored auth" (14:05 - 14:23)
β”œβ”€β”€ src/auth.ts      (3 snapshots)
β”œβ”€β”€ src/user.ts      (2 snapshots)
β”œβ”€β”€ src/index.ts     (2 snapshots) ← undefined reference!
└── AI Detection: HIGH RISK

Navigate entire sessions with one click. Not file-by-file like Git or Cmd+Z.

Protection Levels

LevelBehaviorDefault Files
🟒 WatchSilent auto-snapshotsSource code, docs
🟑 WarnProceed with risk boostpackage.json, tsconfig.json
πŸ”΄ BlockHard stop, no writeLock files, .env*

Timeline vs Git

AspectGitVreko
TracksCommits you makeEvery save, automatically
GranularityCommit-levelSave-level
AI awarenessNoneFull attribution
ContextCommit messageCursor position, AI tool, risk score

Use both: Git for version control. Vreko for understanding AI-assisted development.

Privacy

100% Local-First

All analysis happens on your machine. Your code never leaves your device. Optional cloud features use metadata only-never source code.

Stored locally:

  • Snapshots and file states
  • Pattern learnings and risk scores
  • Session metadata

Never collected:

  • Source code content
  • File diffs
  • Proprietary logic

Configuration

Customize with .vrekorc:

{
  "protection": [
    { "pattern": "src/auth/**/*", "level": "block" },
    { "pattern": ".env*", "level": "block" }
  ],
  "ignore": ["*.test.ts"]
}

Recommendation: Let Vreko learn for 30 days before adding custom rules. Pattern detection improves over time.

Next Steps